Journal of Artificial Intelligence and Engineering Applications (JAIEA)

Improving the Education Development Contribution Payment Model at SMK Istiqomah Maruyung Using the C4.5 Algorithm

2024-12-08T10:40:32+07:00

Payment of tuition fees is one of the important aspects of school financial management. At SMK Istiqomah Maruyung, the management of SPP payments is still done manually, which causes student non-compliance in paying on time. The purpose of the research is to improve the SPP payment model by using the C4.5 algorithm to classify the level of student compliance and identify the main factors that influence late payments. The method used is the Knowledge Discovery in Databases (KDD) approach which includes the stages of data selection, preprocessing, transformation, data mining, and result evaluation. The research data was taken from 206 students in the 2023/2024 academic year with attributes such as parental income, number of siblings, scholarship status, and academic grade point average. The C4.5 algorithm was applied to build a decision tree model, with evaluation using five-fold cross validation. The result of this study is that the C4.5 algorithm is able to classify student compliance levels with an average accuracy of 93.55%. The main factors that influence late payment are academic grade point average, class, and parental income. Although the model is very good at predicting compliant students (precision 95%, recall 98%), it shows weakness in predicting lateness (precision 67%, recall 40%). It is concluded that the C4.5 algorithm can improve the efficiency of managing tuition payments and provide data-driven insights for policy making. With further implementation, this algorithm is expected to be adopted by other educational institutions to address similar challenges in financial management.

K-Means Algorithm for Clustering High-Achieving Student at Madrasah Tsanawiyah Yami Waled

2024-12-18T16:40:49+07:00

This study aims to apply the K-Means algorithm to cluster students based on their mathematics grades at Madrasah Tsanawiyah Islamiyyah Yami Waled. By categorizing students into clusters of low, medium, and high academic achievement, the institution can develop more effective and targeted learning strategies. The data consisted of semester mathematics grades from 112 students, analyzed using the K-Means clustering algorithm. Clusters were evaluated using the Davies-Bouldin Index (DBI), with results showing three distinct clusters: Cluster 0 (low achievers, 54 students), Cluster 1 (medium achievers, 37 students), and Cluster 2 (high achievers, 21 students). The DBI score of 0.893 indicates good clustering quality, providing valuable insights for personalized learning approaches.

Optimization of Kebaya Product Grouping Using K-Means Algorithm for Marketing Strategy of Rental Services at Gifaattire Store

2024-12-19T15:32:16+07:00

This study aims to implement the K-Means algorithm to improve the kebaya clustering model to support the rental marketing strategy at Gifaattire Store. The K-Means algorithm was used to analyze eight months of historical kebaya rental data, focusing on the attributes of kebaya type and color. Using the Knowledge Discovery in Database (KDD) approach, the research conducted data selection, preprocessing, transformation, data mining, and evaluation of clustering results. Davies-Bouldin Index (DBI) was utilized to assess the quality of clustering, resulting in an optimal value of 6 clusters with a DBI of 0.580. The results showed that each cluster has unique characteristics that reflect customer demand patterns. Cluster 0, the largest cluster, indicates kebayas with high demand but limited color variations. In contrast, Cluster 1 indicates kebayas with a wide variety of colors but specific demand. This information enables Gifaattire Store to design more targeted data-driven marketing strategies and improve stock management efficiency. The research contributes to the development of literature on the application of K-Means in the fashion rental sector and offers practical insights into understanding customer preferences.

The Lack of Safety Facilities on Pintu Angin Biak Road Results in Less Users Negating Driving Safety

2025-02-26T22:57:31+07:00

The purpose of this study is to identify the risk of road accidents in order to provide solutions or recommendations in improving road safety facilities as a preventive measure with the PKJI (Indonesian Road Safety Guidelines) method on Pintu Angin road, Biak Regency. Jalan Pintu Angin is an arterial road that connects the Provincial Road (Biak-Adibai-Marauw Section) and the National Section (Biak-Moker), the Provincial Section (Biak-Bosnik). However, this is not balanced by the complete safety facilities, especially street lighting, markings, reflectors, and traffic signs. The road has several danger points, including uphill and curved roads, besides that there is also no availability of warning signs and road monitoring ahead which makes this Japanese Cave road often an accident-prone point. This accident risk analysis obtained results, which showed that these hazards have varying levels of risk ranging from moderate to extreme. This can be urgent to fulfill the need for warning signs in areas with a high risk of accidents, as well as the installation of guardill repairs, lighting lights, reflectors, and markings. The implementation of appropriate risk control measures is expected to reduce the risk of accidents, and the severity of accidents, and it is expected to increase safety and welfare for road users in this area.

Online SMART-KIR Application with Waterfall Model

2025-02-27T17:09:56+07:00

The Testing or inspection towards a certain motor vehicle are often referred to as a KIR testing. KIR testing is commonly performed by Dinas Perhubungan, a government agency in carrying out its duties there are many difficulties, especially in processing data such as applicant data, vehicle data, test result data, reports and it takes quite a long time to process. testing process. This study aims to design and build a Motor Vehicle Testing Application in order to facilitate the testing process, data processing and reports. The system development method used is Waterfall. The programming language used is Hypertext Preprocessor (PHP), and the database uses MySQL. The test method uses Blackbox testing. It is hoped that the system built can assist and facilitate vehicle testing activities.

Geographic Information System for Shortest Route Search of Inseminator Locations Using A* Algorithm

2025-03-02T17:08:13+07:00

This research develops a web-based Geographic Information System (GIS) to help farmers in Ketapang Regency locate the nearest inseminator efficiently using the A* algorithm. Livestock plays a crucial role in food security, and artificial insemination (IB) enhances cattle quality and quantity. However, farmers face challenges in finding inseminator locations quickly. The system is implemented using the Laravel framework for the backend and Google Maps API for visualization. It also evaluates the A* algorithm’s effectiveness in determining optimal routes by comparing it with the Google Maps API route feature. The expected outcome is a more efficient insemination process, supporting modern and productive livestock development in Ketapang Regency.

Application of K-Nearest Neighbor Method for Prediction of Best-Selling Fruit Sales at Ziel Kiosk

2025-03-12T14:13:47+07:00

Ziel kiosk sells various types of high-quality fresh fruits. Unfortunately, there is currently no system that manages fruit sales prediction, so there is often a buildup of goods, damaged and rotten goods, or even a shortage of goods, resulting in losses for the kiosk. The data collected is less accurate and effective because the current system is operated manually. This research conducts a data mining process on fruit sales data from Ziel Kiosk from January - December 2023. In sales prediction, Fruit Kiosks can use data mining techniques to be more proactive in managing stock items. This not only avoids the accumulation of fruit stock that can cause spoilage and damage, but also reduces the risk of stock shortages that can affect customer satisfaction. The purpose of this research is to ensure that Ziel Kiosk can see the sales rate for each product sold, so that they can avoid the accumulation of goods and concentrate on the most sold products. With an 80:20 data split, the K-Nearest Neighbor model has high accuracy. This algorithm can also predict fruit sales with an accuracy rate of 97.22% by determining the categories of fruit sales that are in demand or not in demand.

Improving the Regional Grouping Model for Students of SMK Muthia Harapan Using K-Means Clustering Algorithm

2025-03-14T11:16:46+07:00

Education is an important aspect in human life to improve and develop self-potential. The rapid development of technology has increased the need for fast, accurate, and efficients information, including in the world of education. One of the challenges faced by SMK Muthia Harapan Cicalengka is the accumulation of student data every year. This makes it difficult to identify student data based on region of origin. This research aims to apply data mining using the K-Means Clustering method to group student data with similar characteristics. The method used in this research is Knowledge Discovery in Database (KDD) which includes the stages of data cleaning, data transformation, data mining, and evaluation. The implementation og K-Means Clustering is done using RapidMiner with attributes such as Name, Village, Department, and school of origin. The purpose of this research is to provide a targeted and strategic overview of areas that can have a significant impact on the supply of students each year. The result show that student data can be grouped into two clusters. Cluster 0 consists of 254 items and cluster 1 consists of 254 items, with a Davies-Bouldin Index (DBI) value of 0.549.

Sales Association Analysis at the Donatkoe Factory Store Which is Upgraded using the Fp-Growth Algorithm

2025-03-17T19:51:42+07:00

In the retail industry, especially food and beverage, understanding customer buying patterns is crucial for effective stock management and marketing strategies. Donatkoe Factory stores faced challenges in identifying items that were frequently purchased at the same time, which often led to operational inefficiencies and lowered profitability. Association analysis is needed to uncover purchasing patterns to support data-driven decision-making. This study uses the FP-Growth algorithm to analyze transaction data at Donatkoe Factory stores. The parameters used are support, confidence, and elevator to evaluate the strength of the relationship between items. Transaction datasets are analyzed to find combinations of products that are frequently purchased together. The results of the analysis showed several product combinations with strong associations, such as Donuts with Pizza (confidence 0.814; elevator 1.031) and Donuts with Fruit Salad (confidence 0.821; elevator 1,039). The combination with the highest confidence was Donuts with Pizza, Fruit Salad, and Buko Pandan (confidence 0.842; elevator 1,066). These findings indicate that the FP-Growth algorithm is effective in identifying relationships between items, so it can support marketing strategies such as adjacent product placements, bundling, or special promotions. The results of this study also provide insights for Donatkoe Factory stores to improve operational efficiency and customer satisfaction through data-driven decisions.

K-Means Clustering to Improve Interest Grouping Model For High School Students

2025-03-21T18:04:26+07:00

Informatics Engineering has a significant appeal to high school students in the digital era. However, differences in students' understanding of career prospects in this field affect their level of interest. This study aims to identify students' interest patterns using the K-Means Clustering algorithm as a basis for developing data-based strategies to increase the attractiveness of the major. This study used quantitative methods with primary data collected through questionnaires from 202 high school students. The variables analyzed include students' understanding of Informatics Engineering, interest in technology subjects, and aspirations to continue their studies in the field. The data was processed using RapidMiner software, through the stages of pre-processing, data transformation, and model evaluation. Davies-Bouldin Index (DBI) was used to determine the best number of clusters, with cluster trials (k) from 2 to 10. The results showed the best DBI value at k=2 with a score of 0.527. Two clusters were formed: Cluster 0 (uninterested students) with 96 students and Cluster 1 (interested students) with 106 students. Interested students generally have a better understanding of career prospects in technology, while less interested students need additional education to increase their interest. This research shows the importance of a data-driven approach in understanding student needs. For students with low interest, an upstream program is needed.

Grouping of Social Assistance Recipients Using K-Means Algorithm (Case Study: Gegunung Village Office)

2025-03-21T22:15:34+07:00

The aim of this research is to use the K-Means algorithm to classify social assistance recipients in Gegunung Village based on location and nominal data. Inaccuracy and inefficiency are the main problems in the distribution of social assistance, so a technique is needed that can target grouping of recipient data. The Knowledge Discovery in Database (KDD) stage was used to process 672 data entries, including nominal information, location, occupation and type of assistance. Clusters were created using the K-Means method based on location and nominal value, and the Davies Bouldin Index (DBI) was used to assess quality. The findings show that six clusters with different data distributions were produced by optimal clustering with K=6 and DBI 0.971. Relevant parties can identify more effective distribution strategies with the help of these clusters, which provide insight into more structured social assistance distribution patterns. In short, the K-Means algorithm can be a useful tool for classifying social assistance data, facilitating more informed and effective decision making. This study significantly advances the domain of social assistance management and data collection.

Sentiment Analysis of GoPay Application is Improved Using Natural Language Processing Method to Optimize Services

2025-03-22T21:59:59+07:00

Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna aplikasi Gopay menggunakan pendekatan Natural Language Processing (NLP) berbasis algoritma Naïve Bayes Multinomial. Ulasan pengguna diambil dari kumpulan data publik yang tersedia di platform Kaggle, yang berisi teks ulasan dan skor penilaian dalam bahasa Indonesia. Tahapan penelitian ini meliputi pengumpulan data, praproses data, transformasi data, pemodelan sentimen, dan evaluasi model. Pada tahap pemilihan data, hanya dua kolom yang relevan, yaitu teks ulasan dan skor penilaian, yang dipertahankan untuk memastikan analisis yang terfokus. Tahap praproses meliputi pembersihan teks, penghilangan tanda baca, tokenisasi, penghilangan kata henti, dan stemming untuk menghasilkan data yang bersih dan terstruktur. Data yang diolah kemudian diubah menjadi representasi numerik menggunakan teknik TF-IDF (Term Frequency-Inverse Document Frequency). Proses klasifikasi dilakukan menggunakan algoritma Naïve Bayes Multinomial, di mana ulasan dikategorikan menjadi tiga sentimen: positif, netral, dan negatif, berdasarkan skor penilaian pengguna. Evaluasi model dilakukan dengan menggunakan metrik akurasi, presisi, recall, dan skor F1. Hasil penelitian menunjukkan bahwa algoritma Multinomial Naïve Bayes mampu mengklasifikasikan sentimen dengan akurasi 90%, dengan kinerja terbaik pada sentimen positif. Namun, model menunjukkan kelemahan pada klasifikasi sentimen netral, dengan skor F1 yang sangat rendah, yang disebabkan oleh ketidakseimbangan jumlah data antar kategori. Penelitian ini berkontribusi dengan menghasilkan wawasan tentang persepsi pengguna terhadap aplikasi Gopay. Hasil analisis menunjukkan bahwa sebagian besar ulasan bersifat positif, mencerminkan kepuasan pengguna terhadap kemudahan dan keamanan layanan. Sementara itu, ulasan negatif menunjukkan masalah teknis dan layanan pelanggan yang memerlukan perhatian lebih lanjut. Penelitian ini merekomendasikan untuk meningkatkan kualitas layanan berdasarkan keluhan dalam ulasan negatif dan mempertahankan keunggulan fitur yang diapresiasi pengguna. Dengan demikian, hasil penelitian ini dapat digunakan untuk mendukung pengambilan keputusan strategis dalam pengembangan layanan GoPay.

Implementation and Security Testing of Mikrotik Router Againts Cyber Attacks Using Firewall and Penetration Testing

2025-03-22T22:00:53+07:00

Network security is a crucial aspect that must be considered, because without adequate security, the network becomes vulnerable to cyber attacks that can cause losses. Routers are one of the most vulnerable and easily attacked targets because of their very important role in computer network systems. One of the most common types of routers used in developing countries is Mikrotik. Mikrotik routers have several security holes, such as CVE-2018-14847 (Winbox Exploitation), Brute-Force Attacks, and Denial of Service (DoS), which can be exploited by attackers to cause disruption or loss. Therefore, efforts to prevent cyber attacks are very important. Preventive steps that can be taken are by implementing a strong security system on Mikrotik routers through firewall configuration and conducting penetration testing to ensure that the configuration applied is optimal. This study uses the SDLC (Security Development Life Cycle) model, using the waterfall model stages.

Analysis of the Application of Machine Learning Algorithm in Spam Detection System: Literature Review

2025-03-23T21:45:39+07:00

Spam detection is an evolving issue in line with the increasing volume of data and the evolution of spam techniques. In recent years, the application of machine learning (ML) algorithms has become an effective solution to enhance the accuracy and efficiency of spam detection systems. This study aims to analyze various machine learning algorithms applied in spam detection systems through a literature review. Several popular algorithms used in spam detection include Naive Bayes, Support Vector Machine (SVM), Neural Network, Recurrent Neural Network (RNN), and Transformer-based models. Each algorithm has its strengths and weaknesses that affect its performance in handling spam detection issues, depending on the characteristics of the data and the application requirements. Based on the data obtained, the Naive Bayes algorithm achieved 88% accuracy, 85% precision, 90% recall, and 87% F1-score. In contrast, SVM showed higher results with 93% accuracy, 92% precision, 94% recall, and 93% F1-score. Neural Network reached 96% accuracy, 95% precision, 97% recall, and 96% F1-score, while Recurrent Neural Network (RNN) achieved 95% accuracy, 94% precision, 96% recall, and 95% F1-score. Transformer-based models provided the best results with 97% accuracy, 96% precision, 98% recall, and 97% F1-score. This study adopts a literature analysis method by reviewing various articles and research that discuss the application of these algorithms in spam detection. In conclusion, the selection of the appropriate algorithm should be adjusted to the characteristics of the dataset, the complexity of the problem, and the availability of computational resources, as each algorithm has its own strengths and weaknesses in the context of spam detection.

Application of K-Means for Clustering Analysis of Moring Sales in Stores Meowring

2025-03-24T08:17:56+07:00

The complexity of stock management and marketing strategy at Toko Meowring requires a systematic analytical approach. This study implements the K-Means algorithm with a Knowledge Discovery in Databases (KDD) approach to optimize product segmentation. The analysis was conducted on 246 sales data over a year, considering product type, spiciness level, and sales volume. Evaluation using Davies-Bouldin Index (DBI) resulted in 7 optimal clusters with a DBI value of 0.402. The formed clusters identified bestseller product groups dominated by original flavors, low-demand products, moderate popularity products, stable sales products, and unique products with limited demand. This clustering enables optimization of inventory management, development of targeted promotional strategies, and improvement of product layout. The results validate the effectiveness of the K-Means algorithm in enhancing product segmentation accuracy for strategic decision-making.

Sentiment Analysis of Scar Removal Product Reviews Using the Naïve Bayes Algorithm

2025-03-31T22:40:14+07:00

Produk penghilang bekas luka banyak dicari konsumen untuk mengatasi masalah kulit akibat luka atau cedera. Di Shopee, ulasan pengguna mencerminkan pengalaman konsumen dan memberikan wawasan berharga untuk meningkatkan kualitas produk. Studi ini bertujuan untuk menganalisis sentimen pengguna menggunakan algoritma Naïve Bayes. Penelitian diawali dengan pengumpulan dataset dan praproses teks. Ulasan diberi label menggunakan Inset Lexicon, yang menghitung skor polaritas untuk mengklasifikasikan sentimen sebagai positif atau negatif. Dataset dibagi menjadi set pelatihan dan pengujian (rasio 80%:20%) dan direpresentasikan menggunakan TF-IDF. Algoritma Naïve Bayes kemudian diterapkan untuk klasifikasi sentimen. Evaluasi model menunjukkan akurasi 92%, dengan kinerja yang sangat baik dalam mengidentifikasi sentimen positif (Skor F1: 0,96). Namun, model tersebut berkinerja buruk dalam mengklasifikasikan sentimen negatif (Skor F1: 0,31). Visualisasi matriks kebingungan dan Word Cloud digunakan untuk evaluasi lebih lanjut. Studi ini berkontribusi bagi manajer toko dengan meningkatkan kualitas produk, mengoptimalkan strategi pemasaran berbasis data, dan meningkatkan daya saing produk di pasar.

Application For Managing and Reporting Financial data Case Study: Imanuel Lalao Chruch

2025-03-31T22:42:22+07:00

Rapid technological developments provide opportunities for every organization to increase efficiency in managing and reporting financial data in a structured manner. However, until now, the Imanuel Lalao Church still manages finances conventionally, using books and Microsoft Excel, which are prone to recording errors, data inaccuracies, and the risk of losing information. The lack of transparency in financial reports is also a major problem, because it causes the congregation to distrust the management of church finances. Therefore, a more transparent, structured, and accountable system is needed to facilitate the process of managing and reporting finances. This study uses the waterfall method with the aim of building an application that can replace conventional methods in managing and reporting church financial data. The results of the study are an application that is able to increase transparency and accountability in financial management, as well as produce faster, more accurate, and more efficient financial reports.

Internship Monitoring System at State Vocational High School 7 Kupang

2025-03-31T22:41:27+07:00

The internship program at State Vocational High School 7 Kupang aims to provide students with work experience and industry-relevant skills. Challenges such as difficulties in monitoring students at distant locations, fraud in attendance reporting, and dishonesty in activity journals hinder its effectiveness. To address these issues, a web-based internship monitoring system was developed using the waterfall method. This system enables supervising teachers to monitor student activities, while students can take attendance and fill out activity journals online. It facilitates real-time monitoring, improves transparency, and ensures accurate reporting. The system also helps schools in placing students at internship locations, tracking their activities, and maintaining digital records of attendance and journals. Key features include monthly monitoring by teachers, presence validation, and activity journal verification by field supervisors and supervising teachers at the end of the internship. By implementing this system, schools can enhance internship supervision, minimize fraud, and improve the reliability of student reports.

A Web-Based Application to Determine Nutritional Status in Toddlers using the Z-Score Calculation Method at the Kambaniru Health Center

2025-04-07T21:00:54+07:00

Gizi sangat penting bagi masa pertumbuhan balita agar dapat tumbuh dan berkembang secara optimal, kurangnya pengetahuan orang tua dalam masalah gizi pada balita membuat anak mengonsumsi makanan yang tidak sesuai dengan kebutuhan sistem tubuhnya. Gizi juga menjadi salah satu penentu utama kualitas sumber daya manusia khususnya pada balita. Gizi dan kandungan makanan yang dikonsumsi manusia memiliki pengaruh terhadap perkembangan otak dan tubuh manusia khususnya pada balita. Kebutuhan gizi dan gizi balita tentunya akan berbeda dengan kebutuhan orang dewasa karena mereka berada pada masa pertumbuhan dan perkembangan. Berdasarkan hasil wawancara dengan salah satu ahli gizi di Puskesmas Kambaniru diketahui bahwa ahli gizi menggunakan manual perhitungan dengan melihat nilai z-score setiap balita kemudian menentukan status gizi masing-masing balita. Oleh karena itu untuk membantu kinerja ahli gizi diperlukan suatu aplikasi yang membantu ahli gizi dalam menentukan status gizi balita. Gizi yang tidak memiliki jumlah gizi yang tepat dapat menyebabkan munculnya gangguan gizi. Status gizi yang dialami balita terbagi menjadi 4 kategori yaitu gizi baik, gizi buruk, gizi kurang, dan gizi lebih. Pada penelitian ini dibuat sistem dengan menggunakan xampp. Perancangan aplikasi status gizi balita berbasis web ini menggunakan metode perhitungan z-score di Puskesmas Kambaniru untuk memudahkan ahli gizi dalam menentukan status gizi balita. Berdasarkan hasil pengujian black box test menunjukkan bahwa semua fitur aplikasi berjalan dengan fungsionalitas. Sedangkan dari hasil pengujian skala usability sistem diperoleh kesimpulan bahwa hasil pengujian terhadap 10 responden memperoleh skor dasar sebesar 84,25, hasil tersebut menunjukkan bahwa sistem memiliki tingkat rentang akseptabilitas “acceptable” atau layak digunakan, sedangkan pada tingkat skala grade atau skala penilaian memperoleh nilai “B”, dan penilaian kata sifat termasuk dalam kategori luar biasa sehingga dengan adanya sistem ini dapat membantu Puskesmas Kambaniru dalam menentukan status gizi balita.

Eligibility Analysis of Non-Cash Food Assistance Recipients in Rajadesa Village Using the K-Means Clustering Method

2025-04-09T07:59:10+07:00

The distribution of Non-Cash Food Assistance (BPNT) in Rajadesa Village often encounters challenges in accurately determining recipient eligibility. The selection process lacks objectivity due to limited data and suboptimal verification, leading to uneven distribution. To address this issue, the study employs the K-Means Clustering algorithm to enhance the efficiency of BPNT recipient selection. The assessment is based on attributes such as ID number (NIK), name, address, occupation, and the amount of assistance received.The methodology adopts the Knowledge Discovery in Databases (KDD) approach, involving stages such as data selection, preprocessing, transformation, data mining, and evaluation. Data processing is carried out using RapidMiner version 10.5. The clustering results are evaluated using the Davies Bouldin Index (DBI), yielding the best model with three clusters and a DBI value of 0.346.

This approach successfully identifies recipient groups more accurately, enabling a more targeted distribution of food assistance. Consequently, the study provides significant contributions to ensuring the eligibility of BPNT recipients in Rajadesa Village through the application of K-Means Clustering-based analytical technology.

Improved Spam Email Detection Performance Based on Naïve Bayes Approach TF-IDF Vectorizer with Multi-Metric Optimization

2025-04-09T08:00:04+07:00

Email spam has become a serious threat to user productivity and security in digital communication, particularly regarding malware and phishing risks. This study aims to develop and evaluate a more effective email spam detection system model using the Naïve Bayes algorithm optimized with TF-IDF Vectorizer, focusing on improving detection accuracy and handling language variations.The research methodology uses a Knowledge Discovery in Databases (KDD) approach with email message datasets collected from STMIK IKMI Cirebon students during the 2020-2024 period via Google Takeout. The data processing involves comprehensive preprocessing stages, including text cleaning, tokenization, stemming using Sastrawi for Indonesian, and data transformation using TF-IDF Vectorization. The model was evaluated using various data split ratios (90:10, 80:20, 70:30, and 60:40) to test system consistency and reliability. Experimental results show very satisfactory performance, with the 80:20 data split ratio achieving the highest accuracy of 92%. The model demonstrates a good balance between precision (0.94) for spam and (0.91) for non-spam, as well as recall values (0.91) for spam and (0.94) for non-spam. ROC Curve analysis yielded consistently high AUC values (0.96-0.97) across all data split ratios, indicating strong discriminative capability in distinguishing spam and legitimate emails. This research provides a significant contribution to developing more effective and efficient email filtering systems to protect users from various cyber threats.

Implementation of Finite State Machine on NPCs to Improve Game Productivity

2025-04-09T08:01:20+07:00

This research aims to design an artificial intelligence system based on Finite State Machine (FSM) to enhance Non-Player Character (NPC) responsiveness in RPG Maker MZ games. The study employs an experimental Research and Development approach to develop FSM for two characters with distinct states, incorporating conditional dialogues and self-switch mechanisms. Testing involved 10 respondents through unit testing and integration testing methodologies. Results revealed significant performance improvements with response times under 100ms, dialogue delays under 50ms, CPU usage below 30%, and memory consumption between 50-60 MB. Qualitative analysis demonstrated that NPC behavior became more natural and interactions more engaging. The implementation provides developers with an efficient framework for creating more responsive and realistic game AI while maintaining optimal resource utilization. This approach contributes to the advancement of game development techniques by offering a structured method for implementing intelligent NPC behavior systems.

Design and Development of Air Mouse Using ESP32 and MPU6050 Sensor

2025-04-09T08:02:01+07:00

In the era of modern technology, innovations in digital input devices are growing, one of which is an air mouse based on ESP32 and MPU6050 sensors. The air mouse allows users to control the cursor on the computer screen with just a hand movement, which provides more comfort and flexibility compared to a conventional mouse. This research aims to design and develop an air mouse device using the ESP32 microcontroller and MPU6050 sensor, and test its performance in transforming hand movements into responsive cursor movements. The methods used include hardware design, installation of sensors and modules connected to the ESP32, and testing to ensure the system functions according to specifications

The results of this study show that the ESP32 and MPU6050-based air mouse is able to detect hand movements and move the cursor on the computer screen accurately. The MPU6050 sensor, which functions to detect acceleration and rotation, provides good performance in cursor control, although it needs to be calibrated against noise and latency. The use of Bluetooth Low Energy (BLE) technology enables stable and efficient communication between the device and the computer. Tests show that the device works well, although there is still room for improvement in terms of responsiveness and accuracy.

Enhancing Mujawwad Qur'anic Recitation Rhythm Classification Using Optimized LSTM Algorithm

2025-04-11T09:19:22+07:00

This research develops an automated classification system for Qur'anic recitation rhythms using the Long Short-Term Memory (LSTM) deep learning approach. The study aims to enhance rhythm identification accuracy by applying hyperparameter optimization techniques. Audio data was collected from mujawwad recitation recordings at Al-Falah 2 Nagreg Islamic Boarding School. Mel-frequency Cepstral Coefficients (MFCC) was extracted as acoustic features, and a systematic GridSearch approach was used to optimize the LSTM model. The proposed model achieved 88.07% classification accuracy, significantly outperforming the Naïve Bayes Classifier (38.97%). Confusion matrix analysis revealed superior performance in classifying complex rhythms, particularly bayati (95%), jiharkah (92%), and rast (90%) styles. This research demonstrates the potential of deep learning in understanding intricate Qur'anic recitation patterns and provides a foundation for developing advanced learning and assessment tools.

Development of Data Processing and Contribution Receivables Monitoring Services Based on Website at BPJS of Employment East Nusa Tenggara

2025-04-11T10:45:48+07:00

BPJS of Employment East Nusa Tenggara faces challenges in managing contribution receivable data due to a manual system that is slow and prone to errors. This study developed a web-based system to streamline, accelerate, and improve the accuracy of receivable management using the Waterfall method. The system includes features such as data management across various receivable categories, Excel file uploads, graphical monitoring, tiered verification, and multi-user access. Implementation results show the system functions effectively, providing real-time information and enhancing work efficiency. Noted limitations include the absence of automated notifications and central system integration. This system is expected to support the digital transformation of public services in the social security sector.

Palm Fruit Ripeness Detection System Using Convolutional Neural Network (CNN) Algorithm

2025-04-15T18:19:11+07:00

Oil Palm Fruit is a valuable natural resource crop in the plantation sector in Indonesia, with promising future growth prospects. To produce the best oil palm fruit, good sorting is needed. With good oil palm fruit, adequate technology is needed to assist in sorting oil palm fruit. Therefore, this study aims to help companies sort oil palm fruit bunches. In this study, CNN was used with the MobileNetV2 algorithm and the training accuracy results reached a peak of 98.20%, while the validation accuracy remained high at 95.00%. This proves that this model is very good and very feasible for further research. This method has proven to be the best choice for achieving high accuracy and low loss, but also minimizing errors in prediction.

Classification of Youtube User sentiment on 5G Technology Videos with Naïve Bayes

2025-04-17T08:04:42+07:00

The rapid development of 5G technology has triggered various reactions from the public on social media platforms such as YouTube. User sentiment towards videos discussing 5G technology varies, from positive to negative. This research aims to improve the sentiment classification model of YouTube user reviews of videos about 5G technology with the Naïve Bayes algorithm, which is known to be able to handle large text data and sentiment variations. This research goes through the stages of collecting review data from YouTube, data preprocessing including tokenization, stop word removal, and stemming, and sentiment classification into positive, neutral, and negative categories using Naïve Bayes. The bag-of-words (BOW) technique is used to improve the algorithm's performance. The results showed a sentiment distribution of 1,581 neutral, 1,165 positive, and 517 negative. The proposed model achieved 98% accuracy, with macro average precision 0.99, recall 0.98, and F1-score 0.98. Weighted average resulted in precision 0.98, recall 0.98, and F1-score 0.98. These results show the model performs very well in sentiment classification. This research is expected to make a significant contribution in understanding public perception of 5G technology.

Prediction Model Optimization on Odd-Even License Plates Using YoloV8 Algorithm

2025-04-17T21:31:21+07:00

Traffic congestion in urban areas encourages the implementation of vehicle restriction policies based on license plate numbers, such as the odd-even system. Therefore, to support this policy, an accurate vehicle license plate detection system is needed and can work in real-time. The main challenge faced is how to develop an accurate and efficient detection model in recognizing license plates in various environmental conditions. The research method used is Knowledge Discovery in Databases (KDD) with five main stages, namely: data selection, preprocessing, transformation, data mining, and evaluation. This research method aims to develop and evaluate a vehicle license plate detection model based on the YOLOv8 algorithm, focusing on the classification of license plates into the "Odd" and "Even" categories. However, the dataset used was only obtained from the Roboflow platform and primary data in the parking environment, which was then processed through the cropping, resizing, and labeling stages using a format that was in accordance with YOLOv8's needs. The model was trained for 100 epoches with performance evaluation using precision, recall, F1-score, and Average Precision (mAP) metrics. The training results showed that the model achieved a precision of 0.879, a recall of 0.888, an mAP50 of 0.954, and an mAP50–95 of 0.830, with a fitness value of 0.843. In addition, the image resolution of 640x480 pixels results in the highest detection accuracy, which is 92% for odd plates and 85% for even plates. Tests were carried out on both images and videos, showing that the model was able to work in real-time with stable results. Based on these results, it can be concluded that YOLOv8 is effectively used to detect odd-even license plates with high accuracy. This research contributes to the development of intelligent systems based on computer vision to support efficient traffic management, especially in the implementation of odd-even policies in urban areas.

Utilization of YoloV8 Algorithm for in-Vehicle Video-Based Driver Monitoring System

2025-04-18T09:23:38+07:00

Driving safety is a critical factor in reducing the risk of traffic accidents, which are often caused by unsafe driver behavior such as drowsiness, phone usage, or neglecting to wear seat belts. To address this, a real-time driver monitoring system is needed to detect and identify risky behaviors using the YOLOv8 algorithm. This study utilizes a secondary dataset titled “DMS Driver Monitoring System” from Kaggle, comprising 9,440 images of various driver behaviors. The dataset underwent preprocessing, including resizing 640x640 pixels and data augmentation to increase image diversity. The YOLOv8 model was trained for 100 epochs with a data split of 70% training, 20% validation, and 10% testing. Performance was evaluated using precision, recall, F1-score, and mean Average Precision (mAP). Results showed that the model achieved 89.6% precision, 87.2% recall, 88.0% F1-score, and 92.0% mAP50. The mAP50–95 score of 69.1% indicates room for improvement in more complex detection scenarios. Real-time video testing revealed the model could detect open eyes with 85% confidence and seat belt use with 35% confidence. The study concludes that YOLOv8 is effective for standard behavior detection but requires further optimization to handle varying lighting and camera angles for broader real-world deployment.

Sentiment Analysis of MobileJKN Application Reviews Using Neural Network Algorithm

2025-04-18T12:21:59+07:00

The advancement of information technology has encouraged the use of user data to improve digital services, particularly in health-related applications such as MobileJKN, developed by BPJS Kesehatan Indonesia. This research conducts sentiment analysis on user reviews of MobileJKN from the Google Play Store, aiming to identify key areas for improvement based on user perceptions. A Deep Learning approach is utilized, with Neural Networks as the primary model and Altair AI Studio as the main data processing tool. Following the Knowledge Discovery in Databases (KDD) methodology, the study involves various preprocessing stages including case folding, tokenization, filtering, stopword removal, and stemming, using the Kamus Besar Bahasa Indonesia (KBBI) to standardize local language terms. After preprocessing, clustering and classification are performed to extract sentiment patterns. The most frequently mentioned keywords “register,” “app,” “number,” “sign in,” and “verify” highlight common user concerns. The sentiment classification model achieved a 100% accuracy rate, with the Shuffled Sampling technique and a 90:10 training-testing ratio yielding optimal results. These findings demonstrate the effectiveness of Neural Networks in analyzing sentiment within health applications, providing valuable insights for developers seeking to enhance MobileJKN’s performance and user satisfaction. The study also offers a practical reference for future sentiment analysis research in the Indonesian digital health context.

Improving the Classification Model of Smart Indonesia Program Recipients in Koorwilbidikcam Sumber Using the C4.5 Algorithm

2025-04-18T17:34:43+07:00

This study aims to implement the C4.5 classification algorithm in determining the recipients of the Smart Indonesia Program (PIP) in the Koorwilbidikcam Sumber area. The main problem faced is the inaccuracy in identifying recipients of assistance which causes suboptimal distribution. This study uses a quantitative approach with data mining techniques, analyzing students' social and economic data. The dataset used consists of 550 student data with variables such as parental occupation, income, means of transportation, and ownership of KIP or SKTM. The classification process is carried out using the C4.5 algorithm with the Knowledge Discovery in Databases (KDD) stages which include data selection, preprocessing, data transformation, and data mining using RapidMiner. The results of the study show that the C4.5 algorithm is able to identify significant patterns in the data and produce decision trees that can be used to support decision making. The implementation of this algorithm improves the accuracy and efficiency of the PIP recipient selection process, as well as reducing subjective bias in the determination. Thus, this study contributes to the development of a fairer and more targeted educational assistance distribution system. The use of data mining-based technology such as the C4.5 algorithm also opens up opportunities for technology integration in decision making in the education sector, so that it can be a model for other areas with similar problems. In this study, it produced an accuracy rate of 85.45% from 550 data and from 110 testing data that had been tested.

Implementation of Knowledge Sharing Website at State Vocational High School 4 Kupang City

2025-04-19T06:41:38+07:00

In the digital era, the effectiveness of the knowledge-sharing process is one of the main challenges, especially in education. This research aims to design and build a website as a knowledge-sharing support platform for State Vocational High School 4 Kupang City. This system is designed to make it easier for teachers, students, and staff to share materials, especially seminar materials, training, ideas, and important information efficiently without being limited by time and place while encouraging more collaboration in the school environment. This research uses the waterfall software development method, which includes the phases of requirements analysis, system design, implementation, testing, and maintenance. Implementing this system is expected to improve the efficiency of the knowledge-sharing process at State Vocational High School 4 Kupang City, support the development of human resource competencies, and contribute to improving the overall quality of education. The result of this study is a website that functions as a knowledge-sharing medium in the State Vocational High School 4 Kupang City environment, which can be accessed by all school residents to support collaboration and exchange of information effectively.

Development of News Management Information System PT. PLN Persero NTT Regional Main Unit Based on Website

2025-04-21T05:59:29+07:00

This research focuses on developing a web-based news management system for PT. State Electricity Company (Persero) Main Unit for East Nusa Tenggara Region to improve the efficiency and accuracy of the news creation and validation process. Previously, news management was carried out manually using WhatsApp, leading to inefficiencies, especially in multi-party validation. The new system integrates structured user management and tiered news validation, eliminating manual processes and ensuring that only validated news is published internally. Developed using the Waterfall model, the system includes features like multi-level login, news tracking, user data management, and progress monitoring. The implementation of this system has resulted in faster, more organized communication, improved collaboration among stakeholders, and a more secure and efficient management of news. This solution is expected to optimize internal communication and news governance within PT. State Electricity Company (Persero) Main Unit for East Nusa Tenggara Region.

Sentiment Analysis Using Fuzzy Logic on Medan Culinary Tourism Based on Google Maps User Reviews About Lontong Kak Lin

2025-04-21T22:34:50+07:00

In the digital era, user reviews on platforms like Google Maps play a crucial role in assessing the quality of culinary destinations. Lontong Kak Lin, a well-known culinary spot in Medan, has received numerous customer reviews. This study aims to analyze user sentiment towards Lontong Kak Lin using the fuzzy logic method. The research methodology includes collecting user reviews from Google Maps, preprocessing the text by cleaning data, tokenization, and removing stopwords, followed by applying fuzzy logic to classify sentiments into positive, neutral, and negative categories. Sentiment analysis is conducted using the Fuzzy Inference System (FIS), integrating the VADER and TextBlob algorithms to handle subjectivity in reviews. The study results show that out of 994 collected reviews, 697 reviews (70%) were classified as positive, 130 (13%) as negative, and 167 (16%) as neutral. The developed model achieved an accuracy rate of 66%, with precision of 80% for the positive class, 49% for the negative class, and 21% for the neutral class. These findings suggest that combining FIS with TextBlob and VADER can effectively analyze sentiment in textual data. This research aims to provide valuable insights for culinary business owners to improve service quality based on customer feedback.

Development of a Web-Based Entrance Examination System to Increase the Efficiency and Accuracy of New Student Selection at the STMIK Kaputama Campus

2025-04-24T14:30:22+07:00

This research aims to develop a web-based entrance examination system so that the new student selection process at STMIK Kaputama becomes more efficient and accurate. This system is designed to replace traditional methods that often require a lot of time, paper and are prone to human error. System development involves literature analysis, creating interface mockups, drawing business process userflow, and creating entity-relationship diagrams (ERD) for optimal database management. This system allows prospective students to take exams online with results that can be processed and displayed in real-time. The results of this research include design documents, user guides, comprehensive final research reports, as well as the publication of scientific articles in journals discussing the development of information systems and educational technology. With this system, it is hoped that the campus can manage the new student selection process more efficiently, accurately and transparently.

Development of an Integrated Information System for Regional Revenue and Asset Management in East Nusa Tenggara Province

2025-04-25T23:12:29+07:00

Badan Pendapatan dan Aset Daerah (BPAD) Provinsi Nusa Tenggara Timur (NTT) menghadapi berbagai tantangan dalam pengelolaan aset, seperti keterlambatan pemutakhiran data akibat proses manual yang mengakibatkan rendahnya efisiensi, transparansi, dan akuntabilitas. Untuk mengatasi permasalahan tersebut, penelitian ini mengembangkan SiTepadNTT, yaitu Sistem Informasi Terpadu berbasis web yang dirancang untuk memusatkan data aset dan meningkatkan efektivitas pengelolaan aset. Sistem ini dikembangkan dengan menggunakan metodologi Waterfall (SDLC) dan dilengkapi dengan fitur kontrol akses berbasis peran, yaitu administrator (user signer) dan staf operasional (user maker), untuk mendukung pengelolaan aset yang efektif seperti tanah, bangunan, peralatan dan mesin, jalan dan jaringan, aset dalam pembangunan, dan aset lainnya. Pengujian efektivitas yang dilakukan kepada 15 responden menunjukkan bahwa penggunaan aplikasi berbasis web (SiTepadNTT) mencapai tingkat efektivitas sebesar 97%, jauh lebih tinggi dibandingkan dengan aplikasi Excel yang mencapai 83,8%. Dengan demikian, dapat disimpulkan bahwa SiTepadNTT memberikan peningkatan efektivitas pengelolaan aset sebesar 13,2%. Temuan ini tidak hanya menunjukkan keberhasilan implementasi teknologi dalam meningkatkan tata kelola aset tetapi juga berkontribusi pada pengembangan teori tata kelola digital dan menawarkan solusi yang dapat direplikasi untuk wilayah lain di Indonesia yang menghadapi tantangan serupa.

Integration of the Internet of Things in Smart Home Information Systems to Improve Security and Convenience

2025-05-01T08:03:01+07:00

The integration of the Internet of Things (IoT) in smart homes improves security and convenience with device automation. The system receives input from motion sensors (PIR), CCTV cameras, and temperature sensors (DHT22), and then processes data using the Machine Learning-based anomaly detection method that runs on the ESP32 module as the main controller. The data is sent to the cloud for further analysis and can be accessed via a mobile or web app. The results obtained in this study are in the form of device automation, real-time notifications, and security alerts when suspicious activity occurs. Testing shows detection accuracy of 92% and system responsiveness of 95%, proving its effectiveness in improving security efficiency and household comfort through smarter monitoring and control.

Prediction of Electricity kWh Sales in Pontianak City Using Linear Regression Method

2025-05-02T13:21:06+07:00

This study presents the development of a web-based system to predict monthly electricity sales (in kWh) in the city of Pontianak using the Simple Linear Regression method. The main objective is to build a system capable of estimating electricity demand for the latest period and projecting the required kWh for the following month. The system uses 24 months of historical electricity sales data as the basis for prediction, allowing it to identify trends and patterns over time. After applying the regression calculation, the system predicted the next month's electricity sales to be 93,394,700 kWh. This result indicates that the system's prediction aligns with historical trends, demonstrating the model's reliability and potential accuracy. The relationship between the independent and dependent variables used in the model is linear and causal, making this method suitable for forecasting electricity consumption. Additionally, the system includes data visualization features on the website to enhance user understanding and simplify analysis. These visual tools help stakeholders to interpret predictions more effectively. Overall, the system serves as a practical and efficient solution to support electricity demand planning, resource management, and decision-making processes for local authorities and energy providers in Pontianak.

The Application Of The Decomposition Method In Predicting The Sale Of Building Materials On CV. Laris Baja

2025-05-06T17:06:28+07:00

CV. Laris Baja is a retail store that sells various construction needs and home supplies such as iron, boards, paint, pipes, and cement. The stock recording process is still done manually, which often leads to inaccuracies in inventory control, resulting in overstock or out-of-stock situations. These conditions can cause significant financial losses if not addressed promptly. This study aims to implement the decomposition method to predict the sales of building materials and to design a web-based sales prediction system to support decision-making at CV. Laris Baja. The research applies the decomposition method, with data collected through observation, interviews, and literature studies. The results show that the decomposition method is effective in identifying sales patterns by combining seasonal and trend components to produce reliable sales estimates. The developed prediction system helps the company optimize inventory management, reduce the risk of overstocking or stockouts, and improve operational efficiency. This study emphasizes the importance of systematically utilizing historical data to support data-driven decision-making, while also considering unpredictable external factors. Overall, the study provides a significant contribution to business planning in the building materials industry and can serve as a reference for future research in different scales and contexts

Implementation of a Geographic Information System for Mapping and Promoting Tourist Attractions in Kupang City

2025-05-10T05:49:11+07:00

Tourism is one of the key sectors with significant potential to support regional economic development. Kupang City, located in East Nusa Tenggara, offers various attractive tourist destinations. However, the lack of integrated information and effective promotion remains a major obstacle in maximizing this potential. This study aims to implement a Geographic Information System (GIS) to map and promote tourist attractions in Kupang City. The K-Nearest Neighbor (K-NN) method is applied to classify and recommend destinations based on specific criteria such as location. The resulting system provides accurate, interactive, and easily accessible information for both the public and tourists. Moreover, the system is expected to assist local governments in managing and promoting tourism more effectively. The implementation of this GIS-based system is projected to increase tourist visits to Kupang City, support local economic development, and showcase the natural and cultural beauty of East Nusa Tenggara to a broader audience.

Optimization of Supervised Learning Algorithms for Early Prediction of Heart Attack Risk

2025-05-10T05:50:24+07:00

Cardiovascular disease, particularly heart attacks, persists as a primary global cause of mortality. Heart attacks arise from an abrupt obstruction of oxygenated blood flow to a segment of the cardiac muscle, resulting in inadequate oxygen supply to the heart. This obstruction may stem from modifiable risk factors, including suboptimal dietary habits, physical inactivity, obesity, and tobacco consumption, alongside non-modifiable factors such as age, sex, and familial predisposition. Contemporary research increasingly focuses on preemptive strategies against heart attacks to mitigate associated mortality rates. One such strategy involves the application of artificial intelligence for predictive modeling of heart attack risk. These models may utilize machine learning algorithms, such as logistic regression, support vector machine, k-nearest neighbors, and random forest, all categorized under supervised learning paradigms. This study undertakes a thorough examination and optimization of diverse supervised learning algorithms for the prospective prediction of heart attack risk. Findings suggest that machine learning algorithms possess utility in predicting heart attack risk, with the random forest model demonstrating a peak accuracy of 64%. Nevertheless, the model's efficacy is constrained by high feature dimensionality, suggesting avenues for refinement via feature dimension reduction techniques and meticulous hyperparameter optimization across the employed machine learning algorithms.

Design of a Web-Based Book Collection Management Information System at Universitas Sains Indonesia

2025-05-10T09:14:16+07:00

The increasing demand for efficient library resource management has prompted Universitas Sains Indonesia to improve the way book collections are organized and documented. Accurate data on book availability and quantity is not only essential for day-to-day library operations but also plays a significant role in supporting academic departments during accreditation processes, where detailed reports on available study resources are often required. This study aims to design a web-based book collection management information system for the university library. The system is intended to simplify the management of book data, including recording, categorizing, and tracking the quantity of collections by program or department. Additionally, it provides structured and centralized access to collection data, enabling academic programs to retrieve the information needed for accreditation reports quickly and accurately. Data for this study were gathered through interviews with library staff and academic administrators, as well as through a literature review on library information systems and web-based technology development. The resulting system design includes core features such as book data management, classification by academic program, and reporting tools tailored for institutional needs. It is expected that the implementation of this system will enhance the library’s operational efficiency and provide strategic support to the university’s accreditation process.

Decision Support System for Determining Recipients of Fishing Boat Assistance using the Topsis Method

2025-05-12T18:52:46+07:00

East Flores Regency is one of the regions in Indonesia that has great potential in the marine and fisheries sector. With most of its people relying on fishing activities, the provision of fishing boat assistance is one of the local government's priority programs to improve the welfare of coastal communities. The purpose of this research is to design and develop a Decision Support System (SPK) that can help the Fisheries and Maritime Affairs Office in determining prospective recipients of fishing boat assistance objectively and on target. The method used in this research is Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), which is able to process multicriteria data such as income, age, number of dependents, and boat condition. This method was chosen for its superiority in ranking alternatives based on their proximity to positive and negative ideal solutions. The results show that the developed system is able to generate a ranking of beneficiaries based on the level of eligibility, thus accelerating the decision-making process and increasing transparency and accuracy in the selection of beneficiaries. The implementation of this system is expected to not only support operational efficiency, but also contribute to improving the welfare of traditional fishermen in the region.

Comparative Analysis of Network Security: Firewall, IDS, and AI-Based Defense Against DDoS Attacks

2025-05-12T18:54:14+07:00

Distributed Denial of Service (DDoS) attacks have become one of the most significant threats in today’s network security landscape. By overwhelming a network with excessive traffic, these attacks can disrupt service availability and render digital systems inaccessible. Various defense mechanisms have been developed to counter this threat, including firewalls for initial traffic filtering, Intrusion Detection Systems (IDS) for real-time anomaly detection, and Artificial Intelligence (AI)-based systems that can adaptively recognize new attack patterns. This study aims to analyze and compare the effectiveness of these three approaches in mitigating DDoS attacks. The method used is a literature review of selected scientific journals published between 2019 and 2024. The findings show that firewalls are effective for standard traffic filtering, IDS excels in early threat detection, and AI-based systems offer high accuracy with lower false positive rates. A combined implementation of these three methods is recommended to build a comprehensive and adaptive network defense system capable of withstanding increasingly complex DDoS threats.

Implementation of Multihomed Firewall Based on IDS and DMZ Technology Using PfSense

2025-05-15T21:23:34+07:00

As cyberattacks increase, it is necessary to strengthen the mechanism of network defense. Ancae, it is necessary to improve cos This research aims to design and implement a multihomed firewall system using pfSense enhanced with Demilitarized Zone (DMZ) and Intrusion Detection System (IDS) Suricata to strengthen network security. This research uses a simulation-based experimental method in a virtualized environment, using VMware with three main network segments: WAN, LAN, and DMZ. Firewall rules are configured to segment traffic and enforce strict access control, while Suricata is integrated with the Emerging Threats Open (ET Open) ruleset to detect known attack patterns in real-time. Various attack pattern scenarios, including DoS, port scanning, and common brute force, were used to test the system. Log analysis showed that the firewall successfully blocked unauthorized access attempts and effectively segmented the network, while the IDS generated accurate alerts with minimal false positives. These results confirm that integrating pfSense, DMZ, and Suricata IDS provides a complex and responsive network defense strategy suitable for academic and medium-sized enterprise environments.

Web Security Vulnerability Analysis and Mitigation Based on OWASP TOP 10

2025-05-15T21:24:34+07:00

Information security is present as one of the main pillars in the challenges of the current era of technological development, especially on websites used by XYZ institutions. This study aims to test system security using penetration testing techniques with the latest standards, namely using OWASP TOP 10 in evaluating its security. The methods used in this research include scope, information gathering, vulnerability analysis, exploit, report and remediation, and testing is carried out based on the vulnerabilities obtained during vulnerability analysis according to the list of 10 types of vulnerabilities found in the OWASP Top 10 2021. The results showed that the system still has several security gaps consisting of security misconfiguration, vulnerable and outdated components, and identification and authentication failures. With appropriate improvements, the system can be more secure in the face of cyberattacks and maintain the confidentiality of mustahik data (zakat distributors). This research is expected to be a reference for system developers in improving the security of web-based applications, especially in the context of data protection.

Information System for the Recruitment of Facilitator Personnel for the Provision of Drinking Water and Sanitation Program

2025-05-16T07:59:51+07:00

Community Based Drinking Water and Sanitation Provision (PAMSIMAS) is one the national prgrams to improve rural community access to clean drinking water facilities. The purpose of this study is to create a recruitment information system form community facilitators for the PAMSIMAS program in West Papua Province. Thes system development stages of this study use the Waterfall method, the stages stars from system needs analysis, design, coding, testing and improvement. So that the system implementation process can be impelemented according to the needs of system users. The result of this study produce an information system that is able to assist related parties in recruiting prospective PAMSIMAS facilitators in West Papua Province.

Selection of the Best Margarine Brand in UMKM Roti Pandan Using the AHP and TOPSIS Methods

2025-05-16T19:36:37+07:00

The selection of the best margarine brand is essential for the MSME Roti Pandan, as margarine is a key ingredient in bread production that influences both quality and taste consistency. This study aims to recommend the most suitable margarine brand based on predetermined criteria: price, quality, fat content, taste consistency, and availability. The Analytical Hierarchy Process (AHP) method is used to determine the weight of importance for each criterion, while the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method is applied to rank the alternatives. The three margarine brands considered in this study are Mother Choice, Simas, and Menara. The analysis results indicate that Mother Choice ranks highest based on the TOPSIS approach, as it has the shortest distance to the positive ideal solution and the farthest distance from the negative ideal solution. The conclusion of this research is that Mother Choice is the most suitable margarine brand for Roti Pandan, as it best meets the established criteria. These findings are expected to assist Roti Pandan in improving product quality through the optimal selection of raw materials.

Comparison of Median Filter and Gaussian Filter Performance in Removing Salt and Pepper Noise

2025-05-18T08:40:00+07:00

Image processing plays a critical role in various applications, from medical diagnostics to surveillance systems. However, one of the major challenges in digital image processing is the presence of noise, particularly salt and pepper noise, which significantly degrades image quality. This study aims to compare the effectiveness of two popular filtering techniques—Median Filter and Gaussian Filter—in removing salt and pepper noise from digital images. The evaluation is conducted both quantitatively, using Peak Signal-to-Noise Ratio (PSNR) and Mean Squared Error (MSE) metrics, and qualitatively, through visual analysis.

The experimental results show that the Median Filter consistently outperforms the Gaussian Filter in terms of noise reduction performance. Median filtering yields higher PSNR and lower MSE values across various levels of noise intensity (5%, 10%, and 15%). Moreover, the visual assessment indicates that Median Filter preserves image edges and fine details more effectively, whereas Gaussian Filter tends to introduce blurring artifacts due to its smoothing nature.

These findings suggest that for impulsive noise such as salt and pepper, Median Filter is a more appropriate and robust method, offering better restoration quality without compromising important image features.

Intrusion Detection System Analysis to Improve Computer Network Security

2025-05-18T12:02:34+07:00

This study analyzes intrusion detection systems (IDS) as a vital component in the security of modern computer networks that face increasingly complex cyber threats. Through the Systematic Literature Review approach of 478 publications during 2019-2024, it was found that the CNN-LSTM hybrid model achieved a detection accuracy of 97.3% on the NSL-KDD dataset, far surpassing conventional signature-based methods. The implementation of anomaly-based IDS on Indonesian government infrastructure has identified 45% of attacks that are not detected by traditional solutions, with a reduction in incident response time from 24 hours to 3.5 hours. Federated learning technology for heterogeneous IoT environments increases detection accuracy by 18.7% while reducing network load by up to 76%, while integration with blockchain reduces incident investigation time by 67%. Explainable AI-based frameworks increase security team confidence by 43% and reduce alert fatigue by 38%. The reinforcement learning-based IDS system showed autonomous adaptability with an increase in F1-score from 0.87 to 0.96 without manual intervention. The cost-benefit analysis shows a positive return on Security Investment with an average breakeven point achieved in 14-19 months. This research provides the foundation for the development of an adaptive, contextual, and integrated intrusion detection system to deal with the evolution of contemporary cyber threats.

Keywords: Intrusion detection systems, network security, artificial intellige

Web-Based Ticket Purchase Information System in Bena Village

2025-05-18T19:25:50+07:00

Bena Village is one of the cultural tourism destinations located in Tiworiwu Village, Jerebu'u District, Ngada Regency, East Nusa Tenggara. As a traditional village rich in historical and megalithic cultural values, Bena Village attracts many domestic and foreign tourists. However, the manual ticket purchase system that has been used so far has caused various obstacles, such as long queues, potential ticket loss, and difficulties in financial reporting. This study aims to design and build a web-based ticket purchase information system that can be accessed by visitors online. The method used in developing this system is the waterfall method. The result of this development is a website that supports the ticket purchase process efficiently and transparently

Potential Regional Forecasting System for New Students at STIKOM UYELINDO Kupang

2025-05-19T08:28:00+07:00

Universities in Indonesia, especially in the East Nusa Tenggara region, face great challenges in attracting new prospective students amid increasingly fierce competition. For this reason, effective and innovative marketing strategies are needed to increase attractiveness and strengthen the competitive position of universities. One approach that can be implemented is the utilization of information technology in a digital-based new student admission system. A data-driven approach that relies on historical data analysis has also proven to be very effective in identifying targeted marketing potential. In this context, STIKOM Uyelindo Kupang can utilize data-driven forecasting methods, such as Simple Moving Average and Weighted Moving Average, to project areas with a focus on high schools and vocational schools that have the potential to generate new students at STIKOM Uyelindo Kupang. This method allows the college to focus resources on more potential areas and optimize its promotional activities. This research aims to develop a forecasting system for potential new student areas using the Simple Moving Average and Weighted Moving Average methods, which can provide more accurate information in designing data-based marketing strategies. Thus, it is that STIKOM Uyelindo Kupang can increase the number of new students, strengthen its position in the higher education market, and adapt to technological developments in supporting a more effective and efficient recruitment strategy.

Somnambulism Classification Model Using Decision Tree Algorithm

2025-05-19T20:49:32+07:00

Somnambulism, commonly known as sleepwalking, is a sleep disorder classified under parasomnias and poses potential dangers to both the individual affected and those nearby. This condition often goes unnoticed by the person experiencing it, making early detection and intervention challenging. This study aims to develop a classification model for somnambulism using the C4.5 decision tree algorithm, focusing on identifying key risk factors and supporting early diagnosis and treatment strategies. The research adopts the CRISP-DM (Cross Industry Standard Process for Data Mining) methodology, which comprises six stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. A dataset of 400 records was used, containing attributes such as age, sleep quality, stress level, and BMI category. Analysis results revealed that the "Age" attribute serves as the root node due to its highest information gain value, indicating its significant role in classification. The constructed model achieved an accuracy rate of 71.25% and a classification error rate of 28.75%. While the overall performance of the model is fairly satisfactory, it shows limitations in accurately identifying minority classes like Insomnia and Sleep Apnea. In conclusion, the model offers potential as a decision-support tool for analyzing sleep disorders, although further enhancement is necessary to improve its accuracy and generalizability, particularly for more diverse and imbalanced datasets

Design and Construction of Goods Inventory Information System Using First in First Out Method

2025-05-20T11:04:58+07:00

PT SEA in managing incoming goods and outgoing goods data is currently done manually. So that several problems were found including the possibility of missing data, damage to data recording. From this matter, it is necessary to have a Goods Inventory Information System using the First In First Out method. This system was made referring to the SDLC (System Development Life Cycle) method with the waterfall model. An information system is produced that can store data, manage data easily. Tests are carried out with blackbox and UAT types aimed at determining the success of the system. Blackbox testing obtained 100% success. The UAT test obtained an average score of 98% which stated that the system was feasible to use. The final result of this final project is the design and implementation of an inventory information system that is able to assist the parties concerned in managing the inventory of goods.

Usability Analysis of Kupang City's New Students Admission System

2025-05-20T14:38:30+07:00

This study examines the usability issues of Kupang City's New Student Admission system, which still faces challenges in functionality, such as technical support features (email and phone numbers) that often do not function properly, as well as non-intuitive menu placement, making it difficult for users to find important information. Additionally, the website does not provide clear guidance or tutorials, especially for users who are less familiar with technology. These issues hinder the efficiency of the registration process, which should be quick and straightforward. This research employs the USE Questionnaire method to evaluate aspects of usefulness, ease of use, ease of learning, and user satisfaction. Data is collected through questionnaires distributed to parents and students who have used the PPDB system. The results of the study are expected to identify issues related to system navigation, feature effectiveness, and technical problems experienced by users. These findings will serve as the basis for recommendations to improve the user interface, enhance system features, and improve the overall user experience. Thus, the Kupang City PPDB system is expected to function more effectively and meet the needs of the community in the student admission process in a transparent and efficient manner

Conversational Agent for Medical Question-Answering Using RAG and LLM

2025-05-30T19:28:47+07:00

This study analyzes the application of the RAG concept alongside an LLM in the context of PubMed QA data to augment question-answering capabilities in the medical context. For answering questions relevant to private healthcare institutions, the Mistral 7B model was utilized. To limit hallucinations, an embedding model was used for document indexing, ensuring that the LLM answers based on the provided context information. The analysis was conducted using five embedding models, two of which are specialized medical models, PubMedBERT-base and BioLORD-2023, as well as three general models, GIST-large-Embedding-v0, blade-embed-kd, and all-MiniLM-L6-v2. As the results showed, general models performed better than domain specific models, especially GIST-large-Embedding-v0 and b1ade-embed-kd, which underscores the dominance of general-purpose training datasets in terms of fundamental semantic retrieval, even in medical domains. The outcome of this research study demonstrates that applying RAG and LLM locally can safeguard privacy while still responding to medical queries with appropriate precision, thus establishing a foundation for a dependable medical question-answering system.

SVM Optimization for Autism Spectrum Disorder Classification: A Comparison of PCA, PSO, and Grid Search

2025-05-20T14:37:38+07:00

Autism Spectrum Disorder (ASD) is a developmental condition impacting communication and socialization, often manifesting in distinct behaviors. Early detection and timely intervention are crucial for improving the quality of life for individuals with ASD. This research aims to develop an ASD risk classification model using the Support Vector Machine (SVM) algorithm across three age groups: children, adolescents, and adults. To optimize model performance, Principal Component Analysis (PCA) was used for dimensionality reduction, while Particle Swarm Optimization (PSO) and Grid Search were employed for parameter tuning. The study sought to identify the most effective combination of these techniques for autism prediction. Evaluation results indicated that SVM with Grid Search optimization, without PCA, yielded the best performance, achieving 98.2% accuracy and an AUC of 0.997 at an 80:20 data split. Furthermore, Grid Search demonstrated greater computational efficiency compared to PSO. The findings suggest that the integration of SVM and Grid Search offers a promising, accurate, and efficient approach for the early detection of autism.

Development of A Web-Based Gym Information System at Nahaga Sabu Seba

2025-05-30T19:30:42+07:00

In the digital era, the need for efficient and accurate data management in fitness centers is increasing. Nahaga Gym Sabu Seba previously relied on manual systems that hindered administrative processes such as member registration, payment verification, and membership tracking. This study aims to develop a web-based information system to automate and streamline these processes. Using the Agile development method, the system was designed with key features including online member registration, package selection, digital payments, downloadable membership cards, and real-time administrative dashboards for monitoring members and revenue. The implementation of this system, built with React.js, Node.js, and MySQL, enhances user experience and operational efficiency, enabling remote access and improving overall service quality at Nahaga Gym.

Integration of IoT Sensors in Early Warning Systems for Mass Fish Deaths in Fish Farms

2025-05-20T22:43:17+07:00

Mass fish kill in aquaculture is a serious issue that can result in significant economic losses for farmers. One of the main causes of this occurrence is the changes in water quality parameters that are not detected early, such as a decrease in dissolved oxygen levels, an increase in ammonia, and extreme temperature fluctuations. This study aims to design and develop an Internet of Things (IoT) based early warning system that can monitor water quality parameters in real-time and provide automatic notifications when parameter values approach hazardous limits for fish. The system integrates various sensors such as temperature, pH, dissolved oxygen (DO), and ammonia sensors connected to a microcontroller and wireless communication module. The collected data is sent to a cloud platform for analysis and visualization through a web-based user interface or mobile application. The results of the system trials in the aquaculture environment show that this device is capable of detecting changes in water conditions quickly and accurately, and providing early notifications to breeders via text messages or app notifications. With this system, it is hoped that breeders can take rapid mitigation actions to prevent mass fish deaths, while also enhancing the efficiency and sustainability of aquaculture operations

Utilization Of TF-IDF Weighting In Song Search System Based On Spotify Lyrics

2025-05-30T19:29:47+07:00

In the rapidly developing digital era, the need for an efficient information retrieval system is increasing. Spotify, as one of the largest music streaming platforms, faces challenges in providing a fast and accurate song search system. Improving user experience in searching for song titles based on lyrics is the main focus in developing a search system on the music streaming platform. like Spotify. Study This explore use method weighting using TF-IDF (Term Frequency- Inverse Document Frequency) to optimize the search for song titles through lyrics. By applying TF-IDF, system can assess and weighting words in lyrics based on the frequency in One song and its uniqueness in gathering song data in overall. As for the data that used in this study totaling 30 entries. The methods used include system design, preprocessing (data cleaning, tokenization, filtering, and stemming), and TF-IDF weighting. The test results show that this approach significantly improves the relevance and accuracy of search results, making it easier for users to find the appropriate song title. with lyrics Which they remember. System Which proposed This expected can repair quality search services on Spotify and provide a more satisfying experience for users.

House Price Prediction Analysis Using Linear Regression and Random Forest Algorithms

2025-05-21T07:53:09+07:00

This study aims to analyze house price prediction using two machine learning algorithms: Linear Regression and Random Forest. Quantitative evaluation is conducted using four main metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), R² Score, and Mean Absolute Percentage Error (MAPE). The experimental results show that the Random Forest model outperforms Linear Regression in all four evaluation metrics. The MAE and RMSE of the Random Forest model are lower, indicating that this model is more effective in minimizing prediction errors. Additionally, the higher R² Score demonstrates the model's better ability to explain house price variance, while the smaller MAPE indicates more accurate prediction errors in the context of real estate. These findings suggest that choosing the right algorithm is crucial for modeling complex house price data, and although Random Forest is more accurate, its black-box nature limits interpretability. Therefore, for future research, more interpretable methods such as XGBoost with SHAP analysis could be considered.

Decision Support System For Selecting The Best Lecturer Using The Simple Additive Weighting (Saw) Method

2025-05-31T11:13:12+07:00

The selection of the best lecturer at Politeknik LP3I Medan Marelan has traditionally been conducted manually, lacking clear evaluation criteria. This results in subjective judgments and reduced transparency. This research proposes a decision support system (DSS) based on the Simple Additive Weighting (SAW) method to enhance the objectivity and fairness of the selection process. The system evaluates lecturers using multiple criteria: teaching quality, discipline, and peer assessment. Each criterion is weighted according to its institutional importance, and a final ranking is produced based on aggregated normalized scores. The implementation of the SAW-based DSS demonstrates improved decision accuracy, transparency, and fairness in lecturer evaluation. The system offers an effective solution to support academic decision-making and could serve as a reference model for other higher education institutions.

Optimizing Google Classroom for Student Fulfillment

2025-05-31T19:36:22+07:00

In recent years, Google Classroom has become one of the most widely used learning platforms, especially since online learning began to be widely implemented. This study attempts to explore how Google Classroom can be maximized to support students' learning process more effectively. Through direct observation, interviews with teachers and students, and a review of the use of its features, it was found that this platform actually has great potential. When used appropriately. For example, to share materials, give assignments, and open discussion spaces. Google Classroom can help students learn in a more structured and independent way. Even so, challenges remain, especially regarding uneven internet access and lack of technical understanding among teachers. From this it can be concluded that optimizing Google Classroom is not just about technology, but also about readiness and comprehensive support from various parties.

Information Technology Governance Audit at STIKOM Artha Buana Kupang Using ITIL Version 4

2025-05-22T08:45:29+07:00

In the ever-evolving digital era, advances in information and communication technology affect various aspects of life, including education. STIKOM Artha Buana, as a higher education institution, has an important role in preparing competent human resources. However, there are problems in information technology governance management, especially in the administration department, which results in inefficiency and slow response to user needs. This research aims to evaluate information technology services at STIKOM Artha Buana by applying Availability Management, Problem Management, Capability Management, and Change Control work practices from the Information Technology Infrastructure Library V4. The methodology used includes qualitative and quantitative data analysis with data collection through surveys, interviews and questionnaires to identify non-compliance and non-conformity of processes that hinder service performance. As a result of this research, the author provides strategic recommendations for improving information technology governance at STIKOM Artha Buana to improve incident management, operational efficiency, and IT risk management, thereby supporting the achievement of the vision and mission of STIKOM Artha Buana as a superior higher education institution in the field of information technology.

Comparative Analysis of Memory Performance and Processing Time of Five Sorting Algorithms Using C++ Programming Language

2025-05-22T08:46:38+07:00

This study aims to analyze and compare the performance of five different data sorting algorithms, namely Shell Sort, Heap Sort, Counting Sort, Merge Sort, and Quick Sort, which are implemented using the C++ programming language. The main problem behind this research is the need for algorithms that can sequence data efficiently, both in terms of computing time and memory usage, especially when handling large datasets. The research method was carried out by testing each algorithm on three categories of datasets, namely small (100 data), medium (1,000 data), and large (10,000 data), which contained random numbers with a value range of 1–100. The test is carried out by recording the execution time and memory used during sequencing. The results show that Quick Sort is the algorithm with the fastest execution time on small and medium datasets, while Shell Sort is superior for large datasets. Meanwhile, Merge Sort tends to have the slowest runtime and highest memory consumption across all data categories. Implementing the right algorithm at the scale of the dataset has proven to be important to improve the system's efficiency in data processing. Therefore, the selection of appropriate sequencing algorithms can be a strategic solution in the development of optimal data-based systems.

Multi Attribute Utility Theory (MAUT) Method in Determining Cinemas with the Best Facilities in Balikpapan City

2025-05-23T11:38:33+07:00

Cinema is one of the entertainment destinations that are often visited. In Balikpapan city, there are five cinemas that can be chosen by people as a source of entertainment or just to enjoy the weekend. However, each person can only watch in one of the available cinemas. The number of cinemas makes people confused in choosing a place to watch, everyone certainly chooses a cinema with the best facilities, in determining the cinema with the best facilities people need to consider several criteria such as ticket prices, number of films, availability of audience seats, and supporting facilities (offline ticket purchase counters, online ticket pick-up counters, waiting rooms, waiting room seats, trash cans, toilets, etc.). These criteria can be used in the Decision-making system. This study uses Multi Attribute Utility Theory (MAUT) to make it easier to choose a cinema with the best facilities. In the process of using the MAUT method, it is to determine the criteria that are beneficial (benefit) and detrimental (cost), determine the weight of the criteria, determine alternatives, collect data, conduct assessments, normalize, and sort alternatives based on the final results to find out the highest value. From the process that has been carried out, the final result of using the MAUT method in making decisions to choose a cinema with the best facilities in Balikpapan city is that CGV Plaza Balikpapan is in first place with the highest score.

Design of Inventory Information System at CV. Graha Raya Consultant Company

2025-05-23T22:18:36+07:00

Efficient inventory management is crucial for companies to enhance operational effectiveness. CV. Graha Raya Consultant faces challenges in recording and managing inventory, which is still done manually, leading to risks of recording errors, asset loss, and delays in item availability. This study aims to design and develop a web-based inventory information system to improve the efficiency and accuracy of inventory management within the company. The software development method used is the Waterfall model, consisting of analysis, design, implementation, and testing stages. The system is developed using PHP and MySQL as the database. The results of the study show that the system can support more accurate inventory recording, reduce the risk of data loss, and accelerate the monitoring and reporting process. With the implementation of this system, the company is expected to enhance operational efficiency and asset management effectiveness.

Enhancing Heart Disease Prediction through SMOTE-ENN Balancing and RFECV Feature Selection

2025-05-24T13:29:39+07:00

Heart disease is the leading cause of mortality worldwide, exerting a significant influence on the national economic burden and productivity. The identification of heart disease is imperative for the prevention of more severe conditions, as it facilitates the detection of risks and symptoms at an early stage. The development of disease prediction models using machine learning has been extensively researched; however, the field continues to encounter challenges, including uneven data distribution and the presence of large, complex datasets. The proposed solution to these issues is the optimization of the Random Forest algorithm through the integration of the Synthetic Minority Over-sampling Technique and Edited Nearest Neighbor (SMOTE-ENN) with Recursive Feature Elimination and Cross-Validation (RFECV). The objective of these methods is to address the issue of data imbalance and to reduce irrelevant features, thereby enhancing the performance of the prediction model. The combination of SMOTE-ENN and RFECV consistently produces higher recall up to 0.984 and an optimal F1 score of 0.938. These results suggest that combining SMOTE-ENN data balancing and RFECV feature selection methods improves the performance of Random Forest, making it a promising approach for enhancing prediction models.

Implementation of the Rapid Game Prototyping Method in the Educational Game E-Rush Using Unity 2D Engine

2025-05-24T23:37:23+07:00

Technological development has progressed rapidly, including in the field of education. One result is educational games, which are practical and engaging tools for delivering content, such as environmental awareness training. Games today offer more than entertainment; they can foster interactive learning. This study developed an Android-based educational game, E-Rush, to increase youth awareness about waste sorting. The game employs a drag-and-drop interface, allowing players to classify waste into three categories: organic, inorganic, and hazardous (B3). It features gamification elements, such as scoring, time challenges, and enemy robots, to boost engagement. The development method used was Rapid Game Prototyping, which enabled quick iterations in design and testing. Requirement analysis identified user and system needs, followed by the design of storyboards, 2D models, and UML diagrams (Use Case and Activity). Blackbox Testing evaluated functionality from the user's perspective. The results show that E-Rush was successfully implemented with functional features such as scoring, levels, NPC enemies, and time limits. All components met the defined requirements. In conclusion, E-Rush can be an effective alternative learning medium for promoting early waste segregation habits and supporting environmental education programs.

Predictive Analysis Heart Disease Based on Machine Learning Using the Random Forest Algorithm

2025-05-25T10:38:41+07:00

Heart disease is one of the leading causes of death worldwide, requiring accurate and early detection systems. This study aims to build a predictive model for heart disease using the Random Forest algorithm based on patient medical records. The dataset used contains 1,190 patient records with 11 medical attributes. The data were preprocessed and divided into training and testing sets with an 80:20 ratio. The model was trained and evaluated using accuracy, confusion matrix, and classification report metrics. The results show that the model achieved 100% accuracy on the training data and 82.35% on the testing data. Important contributing features include max heart rate, chest pain type, old peak, and ST slope. In addition, predictions for individual patients were presented to improve interpretability. This approach demonstrates that machine learning, particularly Random Forest, can be a reliable method for early detection of heart disease and has potential for clinical decision support systems.

Performance Analysis of SMOTE and SMOTEN Techniques for Daily Rainfall Classification using XGBoost

2025-05-26T23:05:55+07:00

The vital function that rainfall patterns fulfill in diverse sectors of life, including agriculture, water management, and disaster mitigation, has engendered the necessity for an accurate rainfall classification system to facilitate early warning and decision-making. However, the development of a classification system is often encumbered by various obstacles, with data imbalance being a prominent one. The objective of this study is to analyze two data resampling techniques, namely SMOTE and SMOTEN, with the aim of improving the performance of the XGBoost classification model. The dataset utilized is accessible on the BMKG website and is classified into five categories. Subsequent to the preprocessing stage, the data is divided by two schemes: 70:30 and 80:20. The determination of the sensitivity of each dataset is achieved through variations in the number of folds in cross validation and the use of learning rates. The experimental results indicate that the SMOTE configuration, with a data division proportion of 80:20 using 10 folds and a learning rate of 0.15, attains the maximum accuracy value of 92.92%. This represents a substantial enhancement from the original dataset accuracy result of 75.36% and surpasses the SMOTE experimental results with an accuracy of 90.58%. Consequently, SMOTEN was found to be superior and effective in managing the imbalance of numerical and categorical datasets, thereby enhancing the performance of the XGBoost model in daily rainfall classification.

Design and Validation of a Web-Based E-CRM System for Baby Fashion Business: A Case Study of PT Rhinno Makmur Jaya Using Black Box and UAT Testing

2025-05-29T14:43:02+07:00

This study aims to design and validate a web-based Electronic Customer Relationship Management (E-CRM) system tailored for the baby fashion business sector. The system was developed in response to operational limitations experienced by companies that rely on third-party marketplaces, particularly issues related to restricted access to customer data and the inability to implement loyalty programs. The development approach followed the Waterfall model, encompassing stages such as requirements analysis, system design, implementation, and testing. The system incorporates key features including user registration, product catalog management, coupon integration, payment confirmation, and reward point redemption. Validation was performed using Black Box Testing to assess functional accuracy and User Acceptance Testing (UAT) to evaluate usability and user satisfaction. The test results confirmed that all functions operated as intended, with UAT yielding a strong approval rating. The implementation of the E-CRM system is expected to enhance operational efficiency, provide better control over customer interactions, and support long-term engagement strategies. These improvements position the business for sustainable growth in the digital market landscape.

Literature Review of Earthquake Clustering Algorithms in Indonesia

2025-05-30T00:46:28+07:00

This study presents a structured literature review, often referred to as a Systematic Literature Review (SLR), based on 18 articles discussing clustering methods. The primary aim of this study is to explore how clustering techniques have been applied to earthquake data in Indonesia. To achieve this, the study addresses four key research questions. First, it examines which algorithms are most commonly used for earthquake clustering in Indonesia. Second, it evaluates which algorithms demonstrate the best performance. Third, it investigates which regions within Indonesia are most frequently studied in this context. Finally, it analyzes the types of datasets that are most often utilized for earthquake clustering in the country. The findings indicate that the K-Means algorithm is not only the most frequently used but also consistently shows strong performance. In addition, earthquake clustering studies most commonly focus on Indonesia as a whole, using publicly available datasets. These insights offer valuable guidance for researchers seeking to apply or further develop clustering methods for earthquake-related studies in Indonesia.

3D Animation Video about The Impact of Fear Of Missing Out (FOMO) Using Pose-to-Pose Method

2025-05-27T17:52:21+07:00

FOMO is a behavior characterized by anxiety and the fear of missing out, which drives someone to always stay connected with others and participate in something new and trending. Although not entirely bad, excessive FOMO can lead to a decrease in life satisfaction, anxiety, and disrupt a person's mental and financial condition. Nowadays, many people might hear of FOMO, but not many clearly understand what FOMO is, the impacts, and how to respond to it. One way to present information in a more easily understandable manner is through animation. By using pose-to-pose method, which is an animation technique that involves determining the main poses at key points in a sequence, then filling in additional movements between these main poses to smooth out the animation so that it looks natural and not stiff. In a satisfaction survey shared with 103 respondents, 90.3% reported becoming more aware of the impact of FOMO, and 86.4% stated that the 3D animation video was quite effective in conveying information, indicating that 3D animation is an effective medium for delivering information about FOMO in an engaging and easily understandable manner.

Analysis of Public Satisfaction in Using QRIS as a Digital Payment Tool with The End User Computing Satisfaction (EUCS) Method

2025-05-31T22:46:54+07:00

QRIS is a server-based QR code that enables transaction processes through e-wallets, e-money, and mobile banking. Although the number of users continues to increase, the success of QRIS implementation does not only depend on the number of users but also on the level of public satisfaction as end users. Therefore, it is important to know the extent to which the public is satisfied with the use of QRIS. To measure the level of public satisfaction objectively and systematically, the End User Computing Satisfaction (EUCS) method will be used. The EUCS method is a method for measuring user satisfaction with an information system or application through 5 variables: format, content, ease of use, accuracy, and timeliness. The results of the analysis show the variables that significantly affecting the level of public satisfaction are the Ease of Use and Timelines which indicate that the public prioritizes ease of use and transaction speed over other factors. The research results also show that QRIS is easier to use compared to other digital payment methods, and based on the F-test, the effectiveness of QRIS in conducting digital payment transactions is also considered good.

Analysis of the Quality of the Personnel Management Information System at the Civil Service Police Unit of East Nusa Tenggara Province

2025-06-01T09:08:50+07:00

Human Resource Management is the science or method of managing the relationship and role of the workforce efficiently and effectively to achieve organizational goals. This study discusses the issue of implementing the Personnel Management Information System (SIMPEG) and its influence on employee career development at the Civil Service Police Unit of Pematangsiantar City. The absence of SIMPEG may disrupt information stability, risk the loss of archives due to manual methods, and reduce employee performance efficiency and effectiveness. Observations revealed delays in promotions and a lack of clarity regarding career advancement opportunities, negatively impacting employee development. Therefore, it is necessary to analyze whether the implemented SIMPEG website meets user satisfaction and fulfills its intended purpose. This study employs the Webqual 4.0 method, using variables such as usability, information quality, service interaction quality, and user satisfaction. The purpose of this study is to evaluate the quality of the SIMPEG website based on user perceptions. The final result of this study provides a deeper understanding of the quality of SIMPEG implementation and offers input for system development or improvement, aiming to enhance the user experience and support more optimal career development for employees.

Implementation of Teacher and Staff Attendance Information System Android-based with Appsheets and Spreadsheets for SMP Al-Imam Islamic School Cileungsi

2025-06-01T09:10:31+07:00

It was found that teachers of Al-Imam Islamic School Cileungsi Junior High School still use the manual attendance method to record the presence of teachers and staff at the school. It is considered ineffective to find out the timeliness of attendance, return and lateness. This study aims to apply an android-based attendance system with appsheets and spreadsheets in order to increase the effectiveness of the punctuality of attendance, homecoming, and lateness of teachers and staff. The results of functional testing of the application of an android-based presence system with appsheets and spreadsheets as application media experts are well assessed according to their function. Based on the results of the test of 23 teachers and staff, it is known that the results of punctuality of attendance, homecoming, and tardiness can be known and more effective than before. It is hoped that this system will be able to increase the effectiveness and accuracy of the attendance of teachers and staff and improve the quality of educational services in schools.

Development of Integrated E-Voting System to Increase the Effectiveness and Transparency of General Elections Muria Kudus University

2025-06-01T12:19:02+07:00

The rapid advancement of technology has enabled the development of electronic voting systems to support democratic processes, particularly in educational institutions. This study presents the design and implementation of an e-voting system for the General Elections at Muria Kudus University. The waterfall methodology developed the system through stages including requirements analysis, system design, implementation, testing, and maintenance. Data were collected through interviews, observations, and literature review to ensure the relevance and accuracy of the system requirements. The system was designed using Unified Modeling Language (UML) diagrams and implemented using PHP and MySQL. Functionality testing was conducted using the black box method, and results showed that all system features performed according to specifications. The implemented e-voting system enhances transparency, reduces manual errors, minimizes potential manipulation, and improves student participation by offering a user-friendly and accessible voting platform. This solution supports an efficient and accountable electoral process within academic environments.

Analysis of Wi-Fi Network Usage with Cellular Data Packages on Video Call Service Quality

2025-06-01T15:07:28+07:00

Abstract

Video calls have now become an important part of daily activities, from personal communication to work meetings and online learning. However, the quality of video calls is highly dependent on the internet network used. This study aims to analyze the comparison of the quality of video call services when using Wi-Fi networks and cellular data packet networks. Testing was carried out by utilizing several main parameters of network quality, such as data transfer speed (throughput), data packet loss, delay, and signal interference (jitter). In addition, signal quality was also analyzed using the SINPO (Signal, Interference, Noise, Propagation, Overall) parameters, and signal strength was measured using the GNetTrack application. Testing was carried out using the Telegram video call application at three different times—morning, afternoon, and evening—for three consecutive days. The results of the study showed that the quality of video call services with Wi-Fi networks tends to be more stable and consistent compared to cellular data packets, especially during times of heavy internet usage. However, in conditions of a strong cellular signal, the quality of video call services can match or even approach the quality of Wi-Fi. This study concludes that network type and usage time have a significant impact on video call quality, and it is important for users to choose a network that suits environmental conditions and communication needs.

Keywords: Video call, Wi-Fi, Mobile data, Network quality, SINPO, QoS

Comparative Evaluation of YOLOv5 and YOLOv8 Models in Detecting Smoking Behavior

2025-06-01T18:02:24+07:00

Smoking behavior in public spaces has become a serious concern in public health efforts, as it poses health risks not only to active smokers but also to passive smokers. This study presents a comparative evaluation of two state-of-the-art object detection models, YOLOv5 and YOLOv8, for the automatic detection of smoking behavior. The models were trained on a labeled image dataset containing cigarettes, faces, and smoking activities. Evaluation metrics used in this study include precision, recall, F1-score, and mean Average Precision (mAP). The experimental results show that both models achieved strong detection performance, with precision, recall, and F1-scores above 0.95. YOLOv5 obtained slightly higher precision (0.98064), recall (0.96388), and F1-score (0.97), while YOLOv8 achieved a marginally higher mAP (0.97782), indicating better generalization across varying IoU thresholds. YOLOv8 also showed improved classification performance in detecting faces (0.69) and smoking behavior (0.54), benefiting from its anchor-free architecture and advanced loss functions. These findings demonstrate that while both models are highly effective, YOLOv8 offers greater robustness and accuracy for real-time smoking detection in complex public environments, supporting efforts to minimize cigarette exposure and improve public health awareness.

Implementation of a Prototype-Based Logistics Information System at the Blood Transfusion Unit of Indonesian Red Cross, Karawang Regency

2025-06-02T16:03:09+07:00

This study addresses critical operational inefficiencies within the logistics unit of the Blood Transfusion Unit (UTD) of the Indonesian Red Cross (PMI) in Karawang Regency, which currently relies on manual processes. The existing system presents significant challenges in data recording, retrieval, and reporting, leading to substantial delays and an inefficient workload for the dedicated staff. To mitigate these challenges, a prototype software development methodology was adopted, emphasizing an iterative development cycle and direct user involvement. The proposed system is designed to computerize inventory management, streamline operational workflows, and facilitate faster, more accurate data handling across various logistical functions, including goods requests, distribution, receipt, and purchasing. The implementation of this system is anticipated to yield substantial benefits, including a significant reduction in data errors, accelerated item search and transaction processing, and enhanced reporting capabilities. These improvements are expected to alleviate the heavy workload on logistics personnel, making the management of essential supplies more efficient and reliable for UTD PMI. This research not only contributes to the technical advancement of information systems but also demonstrates a practical application of these principles to solve critical operational challenges within a vital humanitarian organization, thereby improving the efficiency and reliability of a crucial public service. The emphasis on minimizing errors and accelerating data search directly addresses the core pain points, indicating a tangible improvement in service delivery and strategic capabilities.

Analysis of eFootball Game User Sentiment Using the Support Vector Machine (SVM) Method

2025-06-03T18:09:08+07:00

This study examines the analysis of user review sentiment for eFootball games on the Google Play Store using the Support Vector Machine (SVM) method. A total of 900 reviews written in Indonesian were taken and collected, and divided based on user ratings. The research process includes data exploration, text cleanup (preprocessing), sentiment labeling based on rankings, modeling using SVM, and model evaluation with confusion matrix and accuracy metrics. The results of the analysis showed that the majority of reviews conveyed positive sentiment (48.7%) followed by negative sentiment (44.9%) and neutral sentiment (6.4%). The SVM-based model built in this study achieved an accuracy of 76%, with adequate precision, memory, and F1 scores, especially in the positive and negative sentiment categories. These findings suggest that SVM is effective in classifying digital game review sentiment, but performance in the neutral category requires significant improvement. The study contributes to the use of machine learning to analyze user perceptions of eFootball games and provides recommendations for developers to improve product quality through automated sentiment analysis.

Integrated Licensing Application Online Service at the Industry and Trade Service Kupang City

2025-06-03T21:34:19+07:00

A clean and transparent system of governance remains a major challenge in the modern era, particularly in public service sectors such as licensing processes. In many regions, integrated online licensing services have been adopted to improve efficiency and transparency. However, the Department of Industry and Trade (Disperindag) of Kupang City still relies heavily on manual procedures for most licensing services, leading to wasted time, effort, and resources. This study aims to develop an integrated online licensing system for Disperindag Kupang to enable the public to submit licensing applications without having to visit the office in person. The system is expected to reduce queues, save time and energy, and enhance resource efficiency within the office. The research applies the waterfall model as the software development methodology, encompassing the stages of requirement analysis, system design, implementation, testing, and maintenance. The results of the study show that the developed online licensing service system significantly improves the efficiency and transparency of the licensing administration process at Disperindag Kupang. The implementation of this system has had a positive impact on both the public and the institution, particularly in terms of easier access, faster service, and reduced administrative workload

Case Study: How T&S Survived a Ransomware Attack

2025-06-04T19:14:58+07:00

This case study explores the experience of Tools and Solutions (T&S), a small business that encountered a devastating ransomware attack and successfully restored its operations through strategic resilience. Initially exposed due to inadequate cybersecurity measures, T&S became a target for attackers who encrypted critical data and disrupted business continuity. Through prompt crisis management and long-term reforms, including cloud-based backup solutions, the implementation of the Odoo ERP system, employee cybersecurity training, and the application of the NIST Cybersecurity Framework, T&S enhanced its cybersecurity stance. This case underscores the vital preventive strategies necessary to mitigate ransomware threats, particularly for small and medium-sized enterprises, by integrating technology, policy development, and employee education. T&S’s transition from vulnerability to resilience serves as a beneficial model for organisations aiming to strengthen defences against increasingly sophisticated cyber threats. The findings highlight that cybersecurity is not just a technological issue but an organisation-wide discipline that requires ongoing investment and diligence.

Sentiment Analysis of Twitter Data Related to the Ratification of the TNI Bill Using Orange Data Mining

2025-06-04T22:29:59+07:00

Twitter is one of the social media platforms where users can post photos, videos and talk about current issues. One of the current issues is the issue of the ratification of the TNI Bill. The method used is naïve bayes with the help of the orange data mining application. Researchers managed to group 400 tweets from Twitter based on the sentiments and emotions contained in them. The results showed that responses were Negative with a total of 166 tweets, neutral sentiment reaching 140 tweets, and 94 tweets showing positive sentiment. If the percentage of polarity analysis is calculated, the results are as large, negative (41.5%), neutral (35%), and positive (23.5%). The Naïve Bayes model used is able to classify data with fairly good accuracy, which is 82%. Although there is still an imbalance in the amount of data between positive, negative, and neutral sentiments, in general this method is quite reliable for describing public opinion on social media. In addition, this study shows that Orange Data Mining can be a practical and effective tool in analyzing texts or opinions in cyberspace.

IoT Based Goldfish Aquarium Water Quality Monitoring System Using SDLC Method

2025-06-05T06:45:04+07:00

Maintaining aquarium water quality is an important factor in the care of goldfish and their aquariums, at the Gema Ornamental Fish And Aquarium store, maintenance of water quality in aquariums is still done conventionally, This study aims to implement a water quality monitoring system in goldfish aquariums based on the internet of things with automation of water changes using google assistant voice commands with integration of if this then that (IFTTT) and webhook. The method in this study uses the software development live cycle (SDLC) method with an agile development approach. This monitoring system has several functions including maintaining water quality at temperature, pH, and turbidity parameters and automating water changes. Using ESP32 Devkit as the main microcontroller and several hardware including water pumps, it is designed to monitor aquariums including the integration of the Blynk and If This Then That (IFTTT) platforms in controlling automatic water pumps via voice via google assistant. The results of this study, the monitoring system that has been created can show the water quality parameters in the goldfish aquarium which are displayed on the LCD and the blynk application, the automatic water change system with voice commands has also been successfully run to drain the aquarium water with a water height of 15cm to 10cm and refill the aquarium water.

Prediction of the Air Quality Index in DKI Jakarta Province Using the CatBoost Method

2025-06-05T15:20:11+07:00

Air pollution in major cities like Jakarta continues to worsen due to various contributing factors, including unregulated industrial emissions, open waste burning, and the increasing number of private vehicles. This study aims to classify air quality levels based on the Air Pollution Standard Index (ISPU) using the CatBoost Classifier algorithm. The dataset comprises ISPU data from 2021 to 2024 sourced from Jakarta's public data portal, including parameters such as PM10, PM2.5, SO2, CO, O3, and NO2. After preprocessing and feature selection, the model was trained and evaluated using standard classification metrics. The CatBoost Classifier achieved high performance in major categories like “BAIK”, “SEDANG”, and “TIDAK SEHAT” with F1-scores exceeding 0.94. However, the “SANGAT TIDAK SEHAT” category could not be predicted accurately due to class imbalance. To address this, a hybrid model incorporating rule-based logic was employed, enabling accurate classification in the case of extreme pollution. The model also offers station-level predictions, supporting spatial analysis and early warning systems. The results demonstrate that the proposed approach provides a robust framework for air quality classification and real-time environmental monitoring.

The Impact of AI on Education: A Dual Approach of Systematic Review and Bibliometric Mapping

2025-06-07T09:22:23+07:00

This study aims to analyze the development of literature on Artificial Intelligence Education through a systematic review and bibliometric mapping approach. The method used involves screening articles from the Scopus database with the keywords "artificial intelligence AND education", resulting in 111 selected articles. The analysis was carried out using the PRISMA protocol and VOSviewer visualization to identify publication trends, geographical distribution, institutional affiliation, and keyword relevance. The results showed a significant increase in the number of publications over the past decade, with contributions from China, South Korea, and the United States dominating. Higher education institutions in Finland and Hong Kong were also recorded as active in publications. Frequently emerging topics include AI literacy, curriculum design, the role of teachers and students, and computational thinking. This study found that Artificial Intelligence Education not only includes learning about AI, but also the use of AI as a learning tool. The conclusion of this study emphasizes that the integration of AI in education is a systemic transformation that requires a multidisciplinary approach, competency-based learning, and strong ethical policies to support the development of inclusive and adaptive 21st century education.

User Acceptance Analysis of AI GROK on Platform X

2025-06-08T09:42:09+07:00

Significant changes have been brought about by advancements in artificial intelligence (AI) to digital platforms, including social media. One of the latest innovations is the integration of GROK AI into Platform X, designed to enhance user interaction, productivity, and the overall user experience. This study uses the Technology Acceptance Model (TAM) to examine user acceptance of AI GROK, focusing on four main factors: perceived ease of use, perceived usefulness, user attitude and intention to continue using the feature. Data were collected via a questionnaire distributed to active Platform X users who had interacted with GROK AI. The findings aim to provide insights into user perceptions and behaviour to support the development of more effective and user-centric AI features. This research is expected to benefit developers, digital service providers and other stakeholders involved in improving AI integration.

Acceptance Analysis of Bareksa Digital Investment with UTAUT Model (Generation Z Case Study)

2025-06-08T21:26:51+07:00

Generation Z's increasing interest in digital investment drives the need to understand the factors that influence their acceptance of investment applications such as Bareksa. This study aims to analyze the acceptance of Bareksa using the Unified Theory of Acceptance and Use of Technology (UTAUT) model which consists of four main constructs namely Performance Expectancy (PE), Effort Expectancy (EE), Social Influence (SI), and Facilitating Conditions (FC), as well as two additional constructs namely Behavioral Intention (BI) and Use Behavior (UB). The research method used is a quantitative approach with Partial Least Squares Structural Equation Modeling (PLS-SEM) data analysis technique processed through the WarpPLS 8.0 application. Data were collected from 390 Gen Z respondents who are active users of Bareksa using the Lameshow formula. The results showed that EE, SI, and BI have a significant positive effect on app usage intention and behavior, while PE has a significant negative effect on BI, and FC has a marginal effect on UB. The findings suggest that ease of use and social influence are key in driving Gen Z's adoption of digital investments. These results are important for designing app development strategies that are more adaptive to the digital native characteristics of the younger generation.

Analysis of Firewall Policy Effectiveness in Filtering Network Traffic Using Elastic Stack

2025-06-09T22:53:28+07:00

This research is motivated by the increasing importance of network security in the digital age, particularly for organizations like Company X, given the rise in cyber threats that compromise data and system integrity. The study aims to analyze the effectiveness of the firewall policy in filtering network traffic using the Elastic Stack and to provide recommendations for improvement. The research methodology involves processing and analyzing firewall log data over one month using the Elastic Stack. The results demonstrate that the Elastic Stack successfully identified normal and suspicious traffic patterns, as well as the effectiveness of the firewall in blocking threats. The research also found connections with an "incomplete" status, indicating potential network communication issues. It is concluded that the firewall policy at Company X is generally effective, but there is room for improvement. This research recommends adjusting filtering rules, improving network segmentation, and implementing an intrusion detection system.

Data Security Analysis in Information Management in Digital Food Sovereignty Systems

2025-06-10T06:18:32+07:00

The digital food sovereignty system represents an innovation in food information management, enhancing efficiency, transparency, and food security across various sectors. However, during its implementation, data security remains one of the most significant challenges that must be addressed to ensure the system’s continuity and reliability. This study aims to analyze data security aspects within the digital food sovereignty system, focusing on potential risks, vulnerabilities, and applicable mitigation strategies. A descriptive qualitative approach was employed, involving data collection through direct observation, stakeholder interviews, and literature reviews from relevant sources. The findings indicate that key challenges in data security include threats from cyberattacks, data breaches, and insufficient user awareness regarding the importance of information protection. To address these issues, strict security measures such as data encryption, multi-layered authentication, and regular system monitoring are essential. The analysis highlights that strengthening data security in digital food sovereignty systems requires a comprehensive approach that integrates technical solutions, policy development, and user education. This research is expected to contribute to the formulation of more effective security strategies that support the advancement of digital-based food sovereignty.

Implementation of Bayes’ Theorem Method for Diagnosing Diseases in Plants Daucus Carota L (Carrot)

2025-06-10T07:51:14+07:00

Carrot is a biennial plant known for its ability to store large amounts of carbohydrates and flower in the second year. In addition to being a food ingredient, carrots offer various health benefits, especially for vision. Rich in nutrients, carrots are known as a source of pro-vitamin A (beta-carotene) and various other essential nutrients. Common diseases that affect carrots include leaf spots, alternaria rot, and root-knot nematodes. To address the issues related to carrot plant diseases, a system is needed that can assist in diagnosing the symptoms of these diseases on the plants. The design of an expert system for diagnosing diseases in carrots is very important. This system can match symptoms with existing rules and generate clinical diagnoses based on the developed knowledge base, using Bayes' Theorem. The result of this research is that farmers can better understand how to manage diseases in carrot plants to prevent losses. Not only farmers, but also novice gardeners interested in horticulture can utilize this expert system application to make the planting process more effective and produce high- quality carrots.

Simple Additive Weighting Method to Assess the Impact of Social Media Usage on High School Students' Learning Concentration

2025-06-10T09:41:26+07:00

This study aims to evaluate the impact of social media usage on the concentration levels of high school students by utilizing the Simple Additive Weighting (SAW) method as a decision-making tool. In this research, several important criteria are considered, including the duration of social media use, the frequency of accessing social media during study hours, the types of platforms most frequently used, and the academic performance of the students. These criteria are quantitatively measured and analyzed to assess how social media habits influence students’ ability to maintain focus while studying. The SAW method is applied to process and weigh each criterion, allowing for a comprehensive assessment of the students’ concentration levels. The findings of this study reveal that higher intensity in social media usage is associated with a noticeable decrease in students’ concentration during learning activities. This suggests that excessive or poorly timed social media use may hinder academic focus and performance.By implementing the SAW method, this research provides an objective and data-driven basis for understanding the relationship between social media use and student concentration. The results can assist educators and policymakers in developing more effective teaching strategies and guidelines to help students manage their social media usage and improve their learning outcomes.

Web-Based Inventory System Design Using Rapid Application Development Method at PT. ALFA SCORPII

2025-06-10T14:46:20+07:00

This study designs a web-based inventory system for PT. Alfa Scorpii using the Rapid Application Development (RAD) method. The previous manual system led to data errors and slow processes. The new system features real-time recording, multi-level approval, and role-based access management. Implementation results show improved accuracy and efficiency. This paper discusses the RAD stages, system design, and suggestions for future development. The web-based inventory system at PT. Alfa Scorpii using the RAD method improves the efficiency and accuracy of inventory management.

Optimization of Digital Image Processing Through Gaussian Filtering for Noise Reduction

2025-06-10T12:21:03+07:00

Pemrosesan citra digital memainkan peran penting dalam berbagai bidang seperti pencitraan medis, penginderaan jarak jauh, pengawasan, dan multimedia. Salah satu tantangan paling umum dalam pemrosesan citra adalah adanya noise, yang dapat menurunkan kualitas citra dan memengaruhi keakuratan analisis selanjutnya. Studi ini berfokus pada pengoptimalan teknik pemrosesan citra digital menggunakan penyaringan Gaussian untuk mengurangi noise. Penyaringan Gaussian adalah filter penghalusan linier yang banyak digunakan berdasarkan fungsi Gaussian, efektif dalam mengurangi noise Gaussian sambil mempertahankan fitur citra penting seperti tepi. Pengoptimalan melibatkan penyesuaian ukuran kernel dan parameter deviasi standar untuk mencapai keseimbangan terbaik antara pengurangan noise dan pelestarian detail. Hasil eksperimen pada berbagai jenis citra noise menunjukkan bahwa penyaringan Gaussian yang dioptimalkan secara signifikan meningkatkan kejernihan dan kualitas citra, menjadikannya metode yang andal untuk pra-pemrosesan dalam berbagai aplikasi analisis citra. Penelitian ini menekankan pentingnya penyetelan parameter dalam teknik penyaringan dan menyoroti potensi filter Gaussian dalam meningkatkan sistem pemrosesan citra digital.

Analysis of Motivation for Continued Use of Meta AI on WhatsApp: Uses and Gratification Theory Approach

2025-06-10T14:59:53+07:00

Advances in AI technology have brought innovations such as the Meta AI chatbot integrated on WhatsApp that are changing the way users interact digitally. However, there is little understanding of the factors that motivate the continued use of AI chatbot technology on messaging platforms. Adapting McLean & Osei-Frimpong's (2019) model, this study examines the motivations for using Meta AI on WhatsApp by analyzing the influence of utilitarian, hedonic, symbolic, social (social presence & social attractiveness) benefits, as well as the moderating role of perceived privacy risks. A quantitative survey was conducted on 100 respondents aged 20-29 years, Meta AI WhatsApp users, and domiciled in Surabaya, and then the data was analyzed using PLS-SEM. The results showed that hedonic benefits and social attractiveness significantly influenced the use of Meta AI, while utilitarian benefits, symbolic, social presence, and privacy risk moderation were not significant.

Performance Analysis and Implementation of A Real-Time Based Robotic System in Clean Water Filtration

2025-06-06T08:07:04+07:00

The increasing crisis of clean water availability and pollution in urban drainage systems has become a pressing concern. This study aims to analyze the performance and optimize a real-time-based robotic system for clean water filtration in drainage channels. The proposed robotic system integrates smart sensors for automated waste detection and collection, and is operated remotely via the Internet of Things (IoT) platform. The methodology includes system testing under various drainage conditions, with an emphasis on evaluating waste processing capacity and identifying key performance-influencing factors such as sensor stability and robotic design. Preliminary findings indicate that the robot can enhance filtration efficiency by up to 30%. However, certain limitations were observed, including disruptions in ultrasonic sensor functionality due to loose jumper wires, and operational constraints under adverse weather conditions caused by the robot's non-waterproof design. Real-time simulation results demonstrate that the system is capable of effective operation under specific scenarios, although further improvements are needed to enhance sensor reliability and weather resistance. This research is expected to contribute to the advancement of robotic technologies for more efficient and environmentally sustainable clean water management

Predicting CO levels using LSTM and Rolling-Features

2025-06-10T21:28:01+07:00

Accurately predicting carbon monoxide (CO) levels is essential for effective environmental monitoring and safeguarding public health. This research investigates the use of Long Short-Term Memory (LSTM) networks for forecasting CO concentrations specifically evaluating how different learning rates influence model performance. The study aimed to assess the effects of adjusting the learning rate to 0.001, 0.0001, and 0.0005 on the model's accuracy and rate of convergence. A dataset of CO measurements was utilized with feature engineering applied to include lag-based and rolling window features. Results indicated that a learning rate of 0.001 produced the most accurate predictions, achieving the lowest error metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). Conversely, smaller learning rates resulted in higher error rates, reflecting slower convergence and less accurate predictions. These findings underscore the importance of selecting the correct learning rate for optimal model performance and suggest that future studies could further investigate learning rate optimization and integrate additional data to improve prediction outcomes.

Application of Bounded Collusion for Identity-Based Encryption Using the Identity Based Encryption Algorithm

2025-06-11T11:54:35+07:00

This research aims to design and develop an identity encryption application using the bounded collusion method with the implementation of the Identity Based Encryption (IBE) algorithm. The method combines IBE, bounded collusion, and key generation based on the user's email. The application was developed using Visual Basic. In its implementation, the application can perform text encryption and decryption while limiting the number of decryptions to a maximum of two times per identity, in accordance with the bounded collusion principle. The testing results show that the application effectively protects user identities by generating unique keys based on email and restricting potential collusion attacks between users. Therefore, the implementation of bounded collusion and IBE is proven to enhance the security of identity-based encryption processes

Development of a 3D Short Animated Film on Traffic Compliance Utilizing Offline Rendering Techniques

2025-06-11T19:25:36+07:00

Traffic violations such as running red lights are one of the main causes of accidents in Indonesia. The lack of public awareness, especially among drivers, worsens this issue. This study aims to design a short 3D animated film using the offline render method as an educational medium to raise awareness about the importance of obeying traffic signals. This method was chosen for its ability to produce realistic visual quality and support strong message delivery. The design process includes problem identification, data collection through surveys and literature review, story idea development, storyboard creation, and animation production. The production stages involve modelling, texturing, rigging, lighting, animation, camera work, and rendering, while post-production includes visual editing, audio arrangement, and final video output. The software used in this research includes Blender and CapCut. The final product is a 1-minute-47-second MP4 video animation that visually depicts the consequences of traffic violations. This video is expected to raise public awareness of the importance of following traffic rules in an engaging and easily understandable way.

Analysis and Design of Attendance Information System and Payroll at PT. Carsurindo Siperkasa

2025-06-11T23:52:02+07:00

The development of information technology that is growing rapidly has now affected various fields, technology and information are two things that cannot be separated. To process attendance data and employee salaries, it is still done manually by using notes in the attendance book which is carried out by HRD. Proof of absence for employees is still given in the form of physical documents stored in the cupboard, this can affect the salary that will be received by employees if the document is lost and damaged or an error occurs when making an attendance report. in order to keep up with competition in the market with other companies. This design aims to design a simple and integrated website-based information system, if implemented computerized, it is expected to make it easier for employees to find out attendance and payroll reports in a structured way. The methodology used is System Development Life Cycle (SDLC). The tools used are Fishbone Diagram, Data Flow Diagram, PIECES, and Data Dictionary. This research produces a website design for the company which, if continued to the system development stage, can make it easier for companies to manage attendance data and manage payroll data. Accurate and automatic recording of employee attendance, reducing errors that affect salary calculations.

Internet of Things-Based Automated Honey Harvesting: A Smartphone-Integrated Solution for Efficient Beekeeping

2025-06-12T08:40:32+07:00

Background: The low level of technological adoption in honeybee farming in Indonesia has directly impacted productivity, despite the country's vast potential as a leading global honey producer due to its rich tropical rainforests. Since 2013, Indonesia has imported approximately 70% of its national honey demand. Therefore, technological innovation in beekeeping has become an urgent necessity. Objective: This study aims to design and develop an automated honey harvesting system based on the Internet of Things (IoT), integrated with a smartphone application. Research Method: This research is an experimental design and development study that integrates traditional beehives with mechanical and electronic technologies, including a DC motor, load cell sensor to measure honey weight, DHT11 sensor to monitor environmental temperature and humidity, Arduino Uno as the main controller, and a Wi-Fi module to interface with the smartphone application. The system is powered by solar energy to support operation in remote areas. Research Results: The result of this design is a prototype of an automatic honey harvesting device that enables real-time monitoring and control of the harvesting process via a smartphone application. Conclusion and Recommendations: This innovation is expected to improve the efficiency and productivity of honeybee farming, while also promoting digital transformation within Indonesia’s beekeeping sector.

Keyword: Honey, Harvest, Automatic, Internet of Things

Telegram BOT Application Development Integration with Google Sheets for Sending Service Reporting

2025-06-12T15:49:58+07:00

The development of digital communication technology has changed the way businesses operate, including in the delivery service sector. This research aims to develop a Telegram bot application that is integrated with Google Sheets to facilitate reporting and data management of sending services. Telegram bots were chosen because of their ease of access and wide use in Indonesia. The development method uses an agile approach with the stages of needs analysis, system design, implementation, and testing. Integration with the Google Sheets API allows for real-time storage and management of data. The test results show that the app can handle order reporting, shipment tracking, and generate automated reports with an accuracy rate of 98.5%. The system successfully reduced the report processing time from 2 hours to 5 minutes and increased operational efficiency by 75%. The bot can handle up to 1000 transactions per day with an average response time of 2.3 seconds. The implementation of this system provides a cost-effective and user-friendly solution for MSMEs in the field of delivery services.

Prediction of Red Chili Prices at Musi Market Using Android-Based Linear Regression Algorithm

2025-06-12T20:07:19+07:00

The prices of nine essential goods (sembako) often experience fluctuations, which can affect people's purchasing power and economic stability. One commodity that frequently undergoes price changes is red bird's eye chili. One of the factors causing the instability of red chili pepper prices is extreme weather changes, such as heavy rainfall or droughts, which directly impact harvest yields and the availability of supplies in the market. This research aims to predict the price of red bird's eye chili in Musi Market using the Linear Regression algorithm. Furthermore, the study also develops an Android-based application to provide users with real-time and predictive price information for red bird's eye chili. This predictive information will be displayed through the Android-based application, making it easily accessible to users and helping them obtain price data quickly and accurately. This system integrates price data, weather, and seasonal events to predict price fluctuations. Evaluation results show that Linear Regression is the best model, with an MAE of 14,380.53 and an R² of 0.686, indicating the model's ability to explain 68.6% of the data variation, providing an efficient solution for price monitoring at Pasar Musi.

Public Sentiment Analysis on Police Service Satisfaction Using Twitter Dataset Based on NLP and SVM

2025-06-12T21:53:25+07:00

The Indonesian National Police plays an important role in maintaining security and providing services to the public. However, there is still public doubt about the quality of its services. This study aims to analyze public sentiment towards police services using Twitter data with a Natural Language Processing (NLP) approach. A total of 14,718 tweets were collected, and after preprocessing, 13,941 tweets were produced that were worthy of analysis. The data was automatically labeled using the Indonesian lexicon method, resulting in 3,737 positive tweets and 6,869 negative tweets. Text representation was carried out using the Term Frequency–Inverse Document Frequency (TF-IDF) method, then classified with the Support Vector Machine (SVM) algorithm using linear, RBF, and polynomial kernels. The Grid Search results showed that the RBF kernel with parameters C=1000 and gamma=0.1 gave the best performance with an accuracy, precision, and recall of 91.36%. Model evaluation on training and test data ratios (70:30, 80:20, and 90:10) showed the highest accuracy of 91.83% at the 90:10 ratio. 10-fold cross-validation produced an average accuracy of 92.31%, precision of 92.29%, and recall of 92.31%. These results indicate that SVM with RBF kernel is effective in classifying text-based sentiment in Indonesian.

Development of an Interactive 3D Animation as a Visual Medium for Depicting Student Life Using Frame by Frame Technique

2025-06-12T21:52:35+07:00

This study aims to design and produce a short 3D animated film that represents the dynamics of student life, with a focus on reinforcing ethical values, social norms, and courtesy within the academic environment. In the context of today's digital technology development, 3D animation is considered a highly effective interactive visual learning medium that can capture the attention of younger generations, especially when addressing topics related to character and morality. Traditional methods of delivering such content are often perceived as monotonous and less engaging, prompting the adoption of frame-by-frame animation techniques as an innovative alternative. This technique allows for the creation of smooth and dynamic motion expressions, supporting the emotional and in-depth delivery of messages. The development process includes story planning, character design, animation production, and the evaluation of its effectiveness. The visual production was carried out using Blender version 3.6 for 3D animation creation, and CapCut was used as a post-production editing tool. Evaluation was conducted through surveys, interviews, and observations involving students aged 18–25, analyzed using a mixed-method approach combining quantitative and qualitative data. The results indicate that this animation medium enhances students’ understanding and awareness of the importance of applying ethical values and norms in campus life. Moreover, it is perceived as more attractive and easier to comprehend than traditional learning methods. This study is expected to contribute to the development of educational media based on animation and serve as a reference for the application of visual technologies in higher education

Analysis of User Comment Sentiment on the Siwaslu Application Using the Naive Bayes Method

2025-06-11T19:24:17+07:00

This study aims to identify sentiment in user comments on the Siwaslu application by utilizing the Naive Bayes model. The Siwaslu application itself is a digital platform developed to support election supervision, with the aim that the public can provide input that can be used to improve the quality of the application's services. The data analyzed consisted of 2,926 comments that had gone through the pre-processing stage, such as converting text to lowercase, removing punctuation and stopwords, and implementing stemming using the Literary algorithm. After that, the text features are extracted using the method (TF-IDF) and then fed into the Naive Bayes classification model. The results of the evaluation showed that from the overall data, as many as 1,642 comments were classified as negative and another 1,284 as positive. The Naive Bayes classification model used succeeded in providing an accuracy of 88%, with a precision of 0.84 in the negative class and 0.94 in the positive class. The resulting F1-score is 0.90 for the negative class and 0.85 for the positive class, respectively. Overall, these results show that the Naive Bayes model is quite effective in analyzing sentiment and can make a real contribution to efforts to improve the quality of Siwaslu application services in the future.

Analysis of Microsoft Copilot Acceptance as Artificial Intelligence-Generated Content (AIGC) Using the TAM/TPB Model

2025-06-13T19:43:00+07:00

The development of Artificial Intelligence-Generated Content (AIGC) technology has brought significant changes to creative work processes, particularly in design. Microsoft Copilot is one implementation of AIGC aimed at enhancing user productivity and efficiency. However, its adoption among designers remains limited due to various psychological, functional, and social considerations. This study aims to analyze the factors influencing user acceptance of Copilot by integrating the Technology Acceptance Model (TAM) and the Theory of Planned Behavior (TPB), along with external constructs such as trust, functional risk, and emotional risk. Data were collected through a survey of 100 respondents, including design students and professionals, using a 5-point Likert scale questionnaire. The analysis was conducted using the Structural Equation Modeling Partial Least Squares (SEM-PLS) approach. The results indicate that perceived usefulness, perceived ease of use, and subjective norms significantly influence trust, which in turn positively affects the behavioral intention to use Copilot. These findings highlight the critical role of trust as a mediating factor linking perceptions of usefulness and social pressure to the intention to adopt AIGC technologies. This study provides a foundation for developing AI implementation strategies in the creative industry that consider users' psychological aspects.

Cluster Modeling with K-Means on Provincial Data in Indonesia Based on Environmental Indicators

2025-06-14T12:05:20+07:00

Population growth and economic activity in Indonesia significantly affect the quality of the environment. The government uses the Environmental Quality Index as a comprehensive measurement tool, which considers aspects of water, soil, and air pollution, as well as demographic variables such as population size and land area. This study aims to identify groups of 33 provinces in Indonesia based on pollution and demographic characteristics by applying the K-Means algorithm. The data, sourced from the Central Statistics Agency (BPS), underwent a series of stages: pre-processing, standardization, and evaluation using the Elbow, Silhouette Score, and Dunn Index methods. The clustering results identified two main groups. The first cluster consists of three provinces on the island of Java, which exhibit high population density and pollution levels. Meanwhile, the second cluster includes the remaining 30 provinces with more diverse characteristics. These findings are expected to support the formulation of more specific and evidence-based environmental policies.

A Systematic Review of Physical Artificial Intelligence (Physical AI): Concepts, Applications, Challenges, and Future Directions

2025-06-05T12:16:26+07:00

Physical AI represents a significant evolution from digital AI , interacting directly with the physical world and mimicking human functions to a greater extent. PAI is a multidisciplinary field divided into Integrated PAI (IPAI) and Distributed Physical AI (DPAI). This systematic literature review analyzes the concept of PAIs, their implementation in various domains such as IoT, automotive, agriculture, healthcare, and logistics, and highlights their transformative potential. Nonetheless, PAIs face significant challenges such as general AI concerns (privacy, bias) and specific challenges (presence in unregulated spaces, information organization, social acceptance, Cannikin law). The integration of PAIs into Cyber-Physical Systems (CPS) also presents challenges related to uncertainty, limited resources, and adversarial attacks. PAIs are supported by advanced technologies from materials science, mechanical engineering, computer science, chemistry, and biology, including deep learning, multimodal processing, domain randomization, zero-shot learning, and large language objects (LLOs). This research provides comprehensive insights to drive the development of reliable and transformative PAIs in the future.

A Transformative PAR (Participatory Action Research) Paradigm in AI Engineering: Towards Adaptive and Humanistic Vocational Learning

2025-06-14T17:45:16+07:00

Artificial Intelligence (AI) presents significant prospects for personalizing learning experiences. However, technology-oriented engineering paradigms cannot often adapt comprehensively and support fundamental human aspects, thus risking the creation of systems perceived as rigid. This paper aims to articulate a transformative paradigm for AI engineering within the context of vocational education by integrating Participatory Action Research (PAR) principles. Using a systematic literature synthesis approach, this paper examines the challenges in human-centered AI engineering and analyzes the potential of PAR as a methodological framework. The result is an integrated conceptual model that aligns the PAR cycle with the AI system development lifecycle, positioning learners and educators as co-design partners. The PAR paradigm offers substantial potential to direct the evolution of AI engineering toward learning systems that are technically adaptive, contextually relevant, and substantively humanistic.

Utilization of Telegram Bot for Integrated Data Visualization with Google Sheets at PT Telkom Cibitung

2025-06-14T19:24:52+07:00

In today’s digital age, organizations demand real-time, accurate, and efficient access to data in order to support decision-making and enhance operational workflows. This research focuses on the development and implementation of a Telegram Bot integrated with Google Sheets to improve data visualization and internal coordination at PT Telkom Cibitung. Prior to this innovation, the process of retrieving data from Google Sheets and sharing it via Telegram was conducted manually, leading to frequent errors, delays in communication, and inefficiencies in data-driven tasks—particularly within the sales division.The study adopts a descriptive-analytical method to examine existing workflows and to design a solution that automates data retrieval using a bot. The Telegram Bot was programmed to fetch and present key data points directly from Google Sheets based on user input, reducing the dependency on manual operations. The system was tested within the sales division and demonstrated significant improvements in speed, accuracy, and usability.Based on the analysis and findings, it can be concluded that the integration of Telegram Bot with Google Sheets provides a viable and scalable solution to the problems previously encountered at PT Telkom Cibitung. This approach not only eliminates the risk of data misinterpretation and human error but also enhances interdepartmental coordination. The implementation of such automation technology reflects a strategic move towards digital transformation and highlights the value of low-code solutions in business environments with limited IT resources.

Implementation of Website Quality Management for Tourist Villages Using Webqual 4.0 A Case Study of Sidajaya Tourist Village

2025-06-15T17:25:16+07:00

Tourist village websites are pivotal in promoting local destinations and enhancing visitor engagement in the digital era. This study evaluates the quality of the Sidajaya Tourist Village website using the Webqual 4.0 method. The research identifies issues regarding the website's effectiveness in meeting visitor expectations and a lack of comprehensive insights into its usability, information accuracy, and service interaction quality. A survey with 70 respondents from the Sidajaya community was conducted, focusing on three key dimensions: Usability Quality (UQ), Information Quality (IQ), and Service Information Quality (SIQ). The results indicate that the website performs well in terms of usability and quality. However, significant concerns remain in service interaction quality, particularly in community engagement, transaction security, and customization features. These findings provide actionable recommendations for enhancing the website and contribute to developing digital services in Indonesian tourist villages, ultimately improving visitor satisfaction.

Design and Creation of Application Estimation of Wood Packing Service Cost for Web-Based Goods Delivery With Prototype Model (Case Study: PT. Cahaya Lintang Lestari)

2025-06-16T07:11:04+07:00

The development of information technology has driven the need for information systems that can improve efficiency and accuracy in business operations. PT Cahaya Lintang Lestari, a company engaged in logistics packaging services, still uses traditional methods such as manual recording and Excel in calculating estimated wooden packing costs. This method often causes errors and is less efficient. To overcome this, a web-based application was developed with a prototyping method, which aims to calculate estimated packing costs automatically. The system development process is carried out in stages in six stages, starting from gathering needs to the implementation stage. This application makes it easy for customers to obtain price estimates independently without having to contact the service provider, and facilitates integrated data management. Based on the implementation results, this system has been proven to improve calculation accuracy, speed up the service process, and provide price transparency to customers. Overall, the use of this system can improve the quality of service and the company's operational efficiency.

The Use of Support Vector Machine in Classifying Scrap Metal Goods Based on Physical Characteristics

2025-06-16T07:12:51+07:00

The problem of metal waste management, especially scrap metal, is increasingly complex with the increase in industrial and construction activities that produce various types of waste materials. Scrap metal is one type of waste that still has high economic value if it can be sorted and classified appropriately based on its type and quality. However, manual classification methods are still predominantly used, subjectivity and human error. To overcome these challenges, this study proposes an artificial intelligence-based approach by implementing Support Vector Machine (SVM) as an automatic classification method that is able to identify types of scrap metal items based on their physical characteristics.

The characteristics used as input features in this model include surface color, rust rate, material hardness, density, magnetic attraction, and texture. The data is collected directly from UD's scrap metal waste collectors. Cahaya Surya in Karawang, which is one of the largest scrap metal processing centers in the region. This research process includes the stages of data collection, pre-processing, selection of model parameters, training and testing using linear kernels and Radial Base Function (RBF), as well as evaluation of model performance through accuracy, precision, recall, F1-score, and confusion matrix metrics.

The results of the tests showed that the SVM algorithm, particularly with the RBF kernel, was able to provide excellent classification performance with an accuracy rate of over 90%, as well as a relatively balanced distribution of predictions between metal classes. This indicates that the physical features used are quite representative in distinguishing different types of scrap metal consistently. Thus, this approach is not only able to improve the efficiency and accuracy of classification, but also contributes to a reduction in reliance on non-objective manual methods. In the future, the effectiveness of these models can be further enhanced through the integration of additional features, such as mild chemical analysis or computer vision-based image processing technology, to support more sophisticated metal classification systems that are adaptive to field conditions.

The Efforts to Improve The Sales of Villagers Business Using Online Marketing (Cases Study: Bawomataluo Village)

2025-06-16T10:24:34+07:00

Most people who live in village especially in remote area make their living income based on farming or fishing. However, the income that coming from those activities not always can meet the ends. Bawamataluwo village is one of tourism villages in Nias island. The people in the tourism village take opportunities to sell souvenirs, like handicrafts, t-shirt to the tourists. Unfortunately, not all tourim villages are easily to be accessed by the tourist. Some villages are located in remote area, and one of the villages is Bawamataluwo. People in that village make handicraft to increase their income. They make wood crafts, woven hat made of nipah, bags and many more. Since the location of the village quite difficult to be accessed, the income of selling souvenirs is very low. The author made the research of the situation and gives solution for the marketing of their products. Using online marketing is the solution for the products. The method of developing the system is using waterfall method. The system information developed by using PHP and the database was built by using SQL. By building the online marketing, hopefully the villagers can raise their sales and also their income.

Development of a Campus Project Management System to Enhance Collaboration Using the Agile Method

2025-06-16T21:32:08+07:00

The advancement of information technology encourages educational institutions to improve the effectiveness of internal project management, such as research activities, student organization programs, and system development. However, collaboration among project team members is often suboptimal due to the lack of integrated project management tools. This study aims to develop a webbased project management system specifically designed for campus environments to enhance collaboration among users, including lecturers, students, and administrative staff. The system was developed using the Agile methodology, particularly the Scrum framework, which allows for incremental development and adaptability to changing user requirements. The system provides key features such as task planning, progress tracking, team management, and integrated team communication. Testing results indicate that the developed system significantly improves team coordination, project progress transparency, and task accountability. With the implementation of this system, campus project management is expected to become more efficient, adaptive, and productive.

Acceptance of ChatGPT by Students in Academic Assessment

2025-06-16T23:29:01+07:00

The development of artificial intelligence technology, particularly ChatGPT, has changed the way students complete academic assignments. This study aims to analyze the factors that influence students' intention to use ChatGPT for academic assessment using the extended Unified Theory of Acceptance and Use of Technology (UTAUT) model approach. This study uses a quantitative approach with a cross-sectional design and Structural Equation Modeling (SEM-PLS) method. The model was developed by adding three external variables, namely Moral Obligation (MO), Trust (TR), and Perceived Risk (PR). The results of the analysis show that Trust, Performance Expectancy, and Effort Expectancy have a significant effect on students' Behavioral Intention in using ChatGPT. Meanwhile, the influence of Moral Obligation, Perceived Risk, and Social Influence tends to be weak and marginal. This model successfully explains 67.5% of the variance in students' behavioral intentions, with Trust as the most dominant factor. This research provides important insights for the development of policies on the ethical use of AI in higher education settings as well as for technology developers in increasing user trust and comfort with ChatGPT.

Website -Based Congregation Data Information System at the GKS Kaliuda Church

2025-06-18T08:39:52+07:00

The congregational data collection at GKS Kaliuda is still carried out using the church master book, which causes various problems. Data inaccuracy often occurs because changes in the status of the congregation, such as births, deaths, relocations, and sacred events, are not always recorded correctly. The data recapitulation process takes a long time, around 3 months, and makes it difficult for church administrators to access information quickly. In addition, recording with different handwriting adds to the complexity of reading and understanding information. Data inaccuracy also causes problems in managing church services, such as scheduling weddings, baptisms, and other sacramental activities that do not match the congregation's real data. To overcome this problem, this study aims to develop a web-based congregational data information system to improve data efficiency and accuracy. System development is carried out using the waterfall method,

The test results using the black box method show that this system can run according to its function without any errors. Meanwhile, from the results of the SUS test that has been carried out on the level of user satisfaction with the church financial recording information system, the assessment given to 10 respondents produced a score of 77%. acceptance range " Acceptable " and " High". The value scale is in the class category "C". and in " Good " Adjective assessment These results indicate that the Web- based data recording information system at GKS Kaliuda can be accepted by its users.

Keywords : Information system, congregation data collection, GKS Kaliuda, website, waterfall

Design of A Web-Based Teacher and Staff Attendance Information System at SD Negeri Laituta

2025-06-16T15:04:47+07:00

In the current era of globalization, computers play a vital role in meeting the need for accurate, precise, and fast information. Computers actively contribute to various fields and simplify human tasks. Technological advancements, especially in the field of informatics, have led to the development of various software tools designed to address a range of problems, including information management. One essential need in the education sector is an attendance information system that facilitates the recording of staff attendance. At SDN Laituta, the attendance of teachers and staff is still recorded manually using an annual logbook, which is prone to damage and data loss. This study aims to design and implement a web-based attendance information system to improve the efficiency and accuracy of attendance records. The development method used is the waterfall model, consisting of five main phases: requirements analysis, system design, coding, testing, and maintenance. This system allows teachers and staff to record their attendance online and automatically generates attendance reports. The implementation of this web-based attendance system is expected to replace the existing manual method, making the attendance process faster, more efficient, and free from the common issues associated with physical records. Based on the results of testing using the black box method, all system features function as specified. Thus, the system has proven effective in enhancing attendance management for teachers and staff at SDN Laituta.

Implementation of the Waterfall Method in Development of Geographic Information Systems Primary School (Case Study: Kambera District)

2025-06-17T09:33:18+07:00

Geographic information systems (GIS) are very important, especially for elementary schools in Kacamatan Kambera, East Sumba Regency. Based on data from the East Sumba Regency Youth and Sports Education Office, Kambera District has 20 elementary schools. The Youth and Sports Education Office in East Sumba Regency is the lack of integrated data on the location and data of schools spread across the region, one of which is data on schools in Kambera District. This causes difficulties in planning and equitable distribution of educational infrastructure development. In addition, limited access to information about school facilities and infrastructure hinders efforts to improve the quality of education. Not only that, the uneven distribution of schools is also an obstacle, where some regions experience a shortage of schools and a lack of educational facilities. This condition is exacerbated by limited accessibility, especially for schools in remote areas. The lack of a digital-based mapping system makes it difficult for the Office of Education, Youth and Sports to accurately monitor and evaluate school conditions. As a result, budget allocation and education policies are often not on target. The method used in this study is the Waterfall method. The purpose of this study is to determine the limitations of educational facilities in an area based on location mapping in Kambera District. The resulting system shows that it functions as expected to determine the limitations of educational facilities in an area based on location mapping in Kambera District. Based on the results of testing using the Black Box Testing method, all features in the system built were successfully tested with a 100% success percentage result.

Influence of Input Image Size Variations and Data Balancing on VGG-16 and VGG-16-ELM Models for Pneumonia Classification

2025-06-18T22:12:36+07:00

Pneumonia is a lung disease that can be identified through chest X-ray images. This study aims to evaluate the performance of two deep learning models, namely VGG-16 and a combination of VGG-16 with Extreme Learning Machine (ELM), in automatically classifying pneumonia. The approach used includes an analysis of variations in input image sizes (150×150, 200×200, 224×224, 256×256, and 300×300 pixels) as well as the application of data balancing techniques using Random Over Sampling (ROS). The dataset used contains 5,856 X-ray images classified into two classes: NORMAL and PNEUMONIA. The preprocessing stages include resizing, normalization, data splitting, and augmentation. Performance evaluation is conducted using metrics of accuracy, precision, recall, and F1-score. The experimental results show that the input size of 200×200 consistently yields the best performance. The VGG-16 model without the application of ROS achieved the highest accuracy of 96.59% and an F1-score of 97.69%. Meanwhile, the VGG-16-ELM combination showed significant performance improvement when ROS was applied. These findings indicate that the selection of model architecture, data balancing techniques, and input image size significantly influence classification accuracy, and contribute to the development of AI-based automated diagnostic systems.

Keywords: Pneumonia, Deep Learning, VGG-16, Extreme Learning Machine, Data Balancing.

Decision Support System for Teacher Performance Assessment at State Vocational High School 7 Kupang City Using the MOORA Method

2025-05-18T08:31:23+07:00

SMK Negeri 7 Kupang City is an educational institution that has four leading departments and aims to improve the quality of education and produce competent graduates. One important aspect that influences the success of education is teacher performance. However, teacher performance assessments in this school are still carried out conventionally, which rely on manual recording and data analysis that are prone to human error. This process takes a long time, high accuracy, and has the potential to result in unfairness in the assessment. Therefore, this study aims to develop a decision support system for teacher performance assessment using the MOORA Method (Multi-Objective Optimization on the basis of Ratio Analysis). The results of the study are a website-based support system that can simplify the process of teacher performance assessment, reduce errors in calculations, and provide a stronger basis for principals in making decisions related to human resource development.

Application of K-Means Clustering Algorithm for E-Commerce Data Analysis

2025-06-20T04:31:26+07:00

The development of information technology has driven significant changes in consumer behavior, especially in online shopping transactions through e-commerce platforms. Increasingly fierce business competition requires companies to not only focus on the product, but also understand the characteristics and needs of customers in order to maintain their loyalty. This research aims to identify customer behavior patterns so that segmentation can be carried out that is useful for a more personalized, effective, and efficient marketing strategy. The results of the analysis show that there is a segmentation of customers into several groups based on different transaction intensity and value. This segmentation can be used as a basis for strategic decision-making, especially in marketing planning and customer relationship management. By understanding customer behavior patterns through the clustering process, companies can develop a more personalized and effective service strategy to increase loyalty and business profitability.

Analysis of the Use of Backtracking Algorithm in Course Scheduling

2025-06-17T11:36:24+07:00

In a university study program, course scheduling is an essential procedure to guarantee the effective use of resources, including lecturers and classrooms. The goal of this study is to examine how the Constraint Satisfaction Problem (CSP) Method and the Backtracking Algorithm are used in the scheduling of courses in the State Islamic University of North Sumatra's Computer Science Study Program. Through the assignment of courses to the appropriate time slots, classrooms, and lecturers, this study seeks to maximize the timetable while meeting predefined limits. such include the length of the course, the availability of lecturers, and the size of the classroom.The NetworkX library is used to show the graph-based approach that is being used. utilizing the NetworkX library, in which classrooms, lecturers, and courses are represented by vertices, and the connections between them are represented by edges. The technique By removing incompatible scheduling configurations, this technique effectively lowers the quantity of erroneous configurations. The findings of the study demonstrate that a workable and ideal schedule that minimizes conflicts and satisfies all requirements may be created by employing CSP and backtracking. disputes. This study offers a possible model and advances knowledge of the practical applications of computing techniques like CSP and backtracking in scheduling issues.

Implementation of Fuzzy Logic Algorithm to Improve NPC Decision-Making in 2D Adventure Games Using Unity

2025-06-21T11:35:26+07:00

In 2D adventure games, Non-Playable Characters (NPCs) play a crucial role in creating a more immersive and interactive experience. However, static and non-adaptive NPC behavior may reduce the game quality. This study aims to enhance NPC artificial intelligence by implementing the Fuzzy Logic algorithm in decision-making processes. The input parameters include the distance between the NPC and the player, the player's health level, and the player's level, with four possible outputs: chase, evade, defend, and wait. A fuzzy rule base consisting of 27 rules was developed and implemented in a Unity-based game. Testing was conducted on various input combinations to evaluate the NPC’s responses. Results indicate that NPCs respond more adaptively, such as evading when the player has high health and level at a close range, or waiting when the situation is unfavorable. This implementation improves interaction dynamics between NPCs and players, and adds strategic depth to the gameplay.

Application of the COBIT 5 Framework in the Information Technology Governance Audit at Public Regional Hospital S.K. Lerik

2025-05-21T16:41:07+07:00

Information technology (IT) management in hospitals is very important. Most hospitals in Indonesia still experience difficulties in managing information technology (IT) effectively. This was also experienced by Public Regional Hospital S.K. Lerik, this is caused by a lack of understanding of good information technology governance, as well as a lack of human resources trained in the field of information technology. Human resources in the field of information technology, including experts, technicians and information technology managers, are an important component in information technology operations. The COBIT 5 framework was chosen because it is able to provide a structured approach to managing information technology strategy, risk and performance that supports organizational goals. This research aims to analyze the application of the COBIT 5 framework to information technology (IT) governance at Public Regional Hospital S.K. Lerik. The method used, namely COBIT 5, is focused on the EDM04 (Ensure Resource Optimization) and APO01 (Manage the IT Management Framework) subdomains. The results of this study are increased operational efficiency of information technology, more effective investment management, and better quality of health services at Public Regional Hospital S.K. Lerik.

Promotional Media Design for Dua Rasa River Tourism Negeri Gugung Village Using the Rapid Method Application Development

2025-06-21T23:28:57+07:00

Desa Negeri Gugung, Kecamatan Sibolangit, Kabupaten Deli Serdang, memiliki potensi wisata alam yang unik berupa Sungai Dua Rasa yang dikenal dengan fenomena dua aliran sungai dengan suhu yang berbeda, yaitu dingin dan panas. Promosi yang dilakukan selama ini seperti memasang banner dan memanfaatkan media sosial seperti Instagram dan TikTok dinilai kurang efektif dalam menarik perhatian wisatawan secara luas. Untuk mengatasi keterbatasan tersebut, penelitian ini bertujuan untuk merancang media promosi berbasis website guna memperluas jangkauan informasi dan meningkatkan daya tarik wisatawan terhadap objek wisata Sungai Dua Rasa. Pengembangan sistem dilakukan dengan metode Rapid Application Development (RAD) yang meliputi tahapan Requirement Planning, User Design, Construction, dan Cutover. Website yang dirancang menampilkan fitur-fitur utama, meliputi halaman beranda, galeri, fasilitas, lokasi, kontak, dan about. Sistem juga dilengkapi dengan fitur login khusus bagi admin untuk memudahkan pengelolaan konten. Hasil pengujian dengan metode Black Box menunjukkan bahwa seluruh fungsi dalam sistem beroperasi dengan benar. Website ini merupakan media promosi yang informatif, interaktif, dan mudah diakses, serta berpotensi mendukung publikasi potensi pariwisata Sungai Dua Rasa secara lebih efektif dan luas.

Analysis of Acceptance and User Experience of the Bibit Application as a Digital Investment Platform for the Surabaya City Community

2025-06-21T23:27:37+07:00

Given the number of platforms that are not registered with OJK and have the potential to harm users, legality is very important when using investment apps. Bibit App is a technology-based mutual fund investment platform that is very simple and safe to use. A modified Technology Acceptance Model (TAM) is used to measure the extent to which this application is accepted by people in Surabaya City. Financial Literacy, Trust, Social Influence, User Interface, Perceived Ease of Use, Perceived Usefulness, and Intention to Use are some of the variables analyzed. Partial Least Square-based Structural Equation Model (SEM-PLS) was used to analyze data from 390 respondents. Results showed that out of nine hypotheses, eight were accepted. The relationship between Financial Literacy, User Interface, and Social Influence on Perceived Ease of Use and Perceived Usefulness is highly significant. Perceived Ease of Use also affects Intention to Use and Perceived Usefulness. In contrast, Trust does not affect Perceived Usefulness. This research shows that benefits and ease of use attract users more than trust in security. Applications that have an easy-to-use interface, provide tangible benefits, and support the social environment tend to be preferred by users.

Measurement of User Acceptance of BRImo Application with Technology Acceptence Model (TAM) Approach

2025-06-22T13:58:04+07:00

This study investigates the factors influencing user acceptance of the BRImo mobile banking application using the Technology Acceptance Model (TAM). As the adoption of fintech in Indonesia rapidly increases, understanding user behavior towards digital banking platforms becomes critical. The research analyzes six key variables: perceived usefulness, perceived ease of use, perceived trust, subjective norm, user attitude, and intention to use. Data were collected through a questionnaire distributed to 398 active BRImo users and analyzed using Structural Equation Modeling-Partial Least Squares (SEM-PLS). The results show that perceived trust is the most significant factor influencing user attitude, which subsequently impacts the intention to continue using the application. Perceived usefulness also has a positive influence, while perceived ease of use and subjective norm were found to have no significant effect. The study concludes that trust in the application's security and reliability plays a critical role in shaping user attitudes and behavioral intentions. These findings suggest that developers should prioritize features that enhance credibility and user trust to improve acceptance and usage of digital banking services like BRImo.

Acceptance of ChatGPT as an AI Chatbot at Among Students: An Analysis Using the UTAUT Model

2025-06-23T08:42:46+07:00

This study explores the degree to which university students in Surabaya accept ChatGPT, an AI-powered chatbot, by utilizing the Unified Theory of Acceptance and Use of Technology (UTAUT) model. Adopting a quantitative methodology, data were collected through questionnaires distributed to respondents. The data analysis was carried out using the Structural Equation Modeling (SEM) method with the aid of SmartPLS software. The results demonstrate that the fundamental elements of UTAUT namely performance expectancy, effort expectancy, social influence, and facilitating conditions exert a significant influence on students' intentions and predicted behaviors concerning ChatGPT usage. These findings imply that simplicity, perceived usefulness, social support, and adequate technological infrastructure serve as key drivers in the adoption of ChatGPT. Hence, with proper educational facilitation and a supportive learning environment, ChatGPT is likely to offer substantial long-term value in academic settings.

Analysis of Technology Acceptance Using the UTAUT Model: A Case Study of the Use of Blu By BCA Digital

2025-06-23T09:29:46+07:00

This study investigates user acceptance of the Blu by BCA Digital application using the UTAUT framework, extended with the Perceived Risk construct. The objective is to analyze key factors influencing behavioral intention to adopt digital banking services. A descriptive quantitative approach was employed through an online questionnaire distributed to Blu users. The instrument was developed from established indicators and refined through validity and reliability testing. Data were analyzed using Jamovi and WarpPLS, covering both measurement and structural model assessments. The results show that Performance Expectancy, Social Influence, Facilitating Conditions, and Perceived Risk significantly affect behavioral intention, while Effort Expectancy does not. These findings reflect users’ emphasis on benefits, support systems, and security over ease of use, indicating increasing digital familiarity. This research contributes to understanding technology acceptance in the digital finance sector and provides insights for developers and institutions in enhancing user adoption.

Analysis of Acceptance and Usage of Blu by BCA Digital Using UTAUT Model

2025-06-24T08:56:11+07:00

The increasing adoption of digital banking services in Indonesia encourages the importance of understanding the factors that influence the acceptance of financial technology by the public. This study aims to analyze the intention and behavior of using the Blu by BCA Digital application using the Unified Theory of Acceptance and Use of Technology (UTAUT) approach. The method used is a quantitative approach through the distribution of online questionnaires to 400 respondents who use Blu by BCA Digital, as well as data analysis using Partial Least Square Structural Equation Modeling (PLS-SEM) through the SmartPLS 4.0 application. The results of the study indicate that the Facilitating Conditions variable has a significant effect on Use Behavior, while Performance Expectancy, Effort Expectancy, Facilitating Conditions and Social Influence do not show a significant effect on Intention to Use. In addition, Intention to Use is not always followed by Use Behavior in using Blu by BCA Digital. These findings indicate that the availability of technical infrastructure and service support are crucial factors in increasing user acceptance of digital banking services. Therefore, the application development strategy should prioritize the availability of facilities that support optimal user experience.

User Satisfaction Analysis of Ajaib Alpha Application Using EUCS Method

2025-06-24T11:20:39+07:00

The development of financial technology has driven the increasing use of digital investment applications such as Ajaib Alpha. This study aims to analyze user satisfaction with the Ajaib Alpha application using the End-User Computing Satisfaction (EUCS) model, which includes five dimensions: content, accuracy, format, ease of use, and timeliness. This research uses a descriptive quantitative approach by distributing questionnaires to 400 active users of the application. Data were analyzed using descriptive statistics and structural model testing through the Partial Least Squares Structural Equation Modeling (PLS-SEM) approach, with the assistance of Jamovi and WarpPLS software. The results show that the dimensions of content, accuracy, and format significantly influence user satisfaction, while the dimensions of timeliness and ease of use do not have a significant effect. These findings indicate that information quality and interface presentation are the main factors affecting user satisfaction levels with the Ajaib Alpha application. This research is expected to serve as a foundation for developers in improving the quality of digital investment application services.

Mobile Based Animal Health Consultation Service Information System Using the Agile Feature-Driven Development Method

2025-06-24T08:55:21+07:00

Digital transformation in the field of animal health has become urgent along with the increasing need for fast, easily accessible, and efficient services. This study aims to develop a mobile-based animal health consultation service system to facilitate interaction between animal owners and veterinary medical personnel online. This system is designed to be able to answer the limitations of conventional services that are often constrained by distance, time, and limited information. The development was carried out using the Feature Driven Development (FDD) method, which focuses on designing and implementing key features based on user functional needs. The FDD method allows for an iterative and structured development process, with an emphasis on team collaboration and feature sustainability. The final result of this study is a mobile application that supports real-time consultation features, recording animal health history, integrating doctor and user data, and managing service queues. System trials were conducted through a heuristic approach and direct testing by prospective users, which showed a high level of functionality and usability. With this approach, the developed system not only improves service efficiency but also contributes to the acceleration of the digitalization of the animal health sector in Indonesia.

Implementation of Internet of Things in Making Smart Trash Bins Case Study Paud Elevate Mbatakapidu

2025-06-24T20:30:45+07:00

Problem Garbage in Waingapu City, East Sumba, is increasing Serious consequence stacking and mixing trash that is not classified based on types in some locations, such as the Inpres Market, and several place tourism around Waingapu City. Lack of awareness public For throw away trash in its place and facilities limited transportation give impact negative on the environment including pollution land, water and air. Research This aiming For test accuracy IoT technology in classify rubbish organic and inorganic as well as detecting waste volume on prototype place the trash that will created. PAUD Elevate Mbatakapidu made into as location research and testing accuracy place waste. This research has been successfully designed place rubbish clever IoT based which can sorting rubbish organic and inorganic using capacitive proximity sensors and inductive proximity sensors which are then separated using servo motor. Place rubbish this can also monitor the volume of waste at the site rubbish use application blynk . In an experiment conducted by researchers happen error in sorting rubbish organic by 20%, sorting rubbish inorganic by 40%. For monitoring of waste volume at the site rubbish organic 100% successful while place rubbish inorganic No succeed.

Critical Factors Determining Information Security Maturity in AI Utilization: A Systematic Literature Review

2025-06-24T21:01:41+07:00

This study aims to identify and synthesize critical factors influencing information security maturity within the context of Artificial Intelligence (AI) utilization in organizations. As AI adoption rapidly escalates across various sectors, it introduces unique and complex information security challenges, necessitating a structured approach to their management. Through a Systematic Literature Review (SLR), we will analyze relevant scientific and professional literature to extract and categorize key information security dimensions and best practices integrated into existing AI maturity models. Particular emphasis will be placed on how these critical factors encompassing technical, organizational, and human aspects directly impact an organization's ability to achieve and sustain higher levels of AI security maturity. The findings of this research are expected to provide a comprehensive understanding of the essential elements required to establish a robust information security posture in AI-driven environments. A primary contribution of this study is to delineate a clear research agenda for future investigations, alongside offering practical guidance for practitioners and decision-makers to assess and proactively enhance their AI security based on these identified determinants.

Design of Reservation System in Timor Travel Kupang

2025-06-23T22:58:27+07:00

Various challenges, such as data recording errors, confirmation delays, and lack of information transparency, are still commonly found in manual reservation systems within the transportation industry. Timor Travel Kupang, as a transportation service provider in East Nusa Tenggara, requires a digital reservation system to enhance operational efficiency and customer satisfaction. This study aims to design and develop a digital reservation system using the Agile methodology, specifically Scrum. This method is chosen for its flexibility in iterative system development and its ability to adapt features according to customer needs. The development process includes user requirements analysis, interface design, and the implementation of key features such as ticket booking, automated confirmation, and digital payments. By implementing this system, the reservation process is expected to become faster, more accurate, and capable of providing real-time access to departure information and seat availability. The results of this study are expected to enhance Timor Travel’s competitiveness in the technology-based transportation industry.

Critical Sentiment Analysis of Tokopedia Electronic Products Using SVM-Logistic & TF-IDF Ensemble Methods

2025-06-25T16:54:15+07:00

This research aims to analyze customer review sentiment for electronic products on Tokopedia using a Support Vector Machine (SVM) classification method with Term Frequency-Inverse Document Frequency (TF-IDF) based features, enhanced by an ensemble approach with logistic regression. Utilizing a Tokopedia review dataset from 2023, this study seeks to identify critical sentiments embedded in customer reviews, which can provide valuable insights for sellers and the platform. The methodology involves comprehensive textual data preprocessing, feature extraction using TF-IDF for vector representation, and the implementation of an SVM-Logistic ensemble model via a stacking strategy. The results indicate that the SVM-Logistic ensemble model can classify review sentiments with high accuracy and superior performance metrics, effectively distinguishing between positive, negative, and neutral sentiments. These findings highlight the significant potential of machine learning methods in automatically understanding customer feedback, which is crucial for continuous improvement in product and service quality on e-commerce platforms, and for supporting more strategic business decisions.

Application of Modified Vigenere Cipher Cryptography Technique in Text Data Encryption in Web Based Applications

2025-06-25T16:56:30+07:00

The development of information technology in today's digital era has brought rapid progress, especially in terms of data security which is a major concern in various sectors. In securing data or information, the application of cryptographic techniques is becoming increasingly important. The vigenere cipher algorithm is one of the classic cryptographic methods widely used for text encryption. However, the standard form of encryption algorithm has weaknesses, especially in terms of its vulnerability to frequency analysis attacks that can be used to break the encryption pattern if the key used is repeated.

This research aims to design and implement a modified Vigenere cipher on a web-based application to improve encryption security. The designed web-based application is a password manager that is used as a test to show what the application of the vigenere cipher modification looks like in an application. The password manager application designed has the features of registering, logging in, storing, managing, and securing various passwords and login information for websites, applications, or online services. sensitive data in this application such as login information is encrypted before being stored in the database and decrypted when displayed to the user.This implementation is expected to show the application of the Vigenere Cipher modification in securing data in web-based applications.

The Implementation of a Web-Based Library Management Information System Using Barcodes at Al-Islam Vocational High School Surakarta: A Research and Development (R&D) Approach

2025-06-25T23:16:59+07:00

This study discusses the implementation of a web-based Library Management Information System utilizing barcode technology at Al-Islam Vocational High School in Surakarta. The system was developed to enhance efficiency in managing book data as well as borrowing and returning transactions in a digital environment. Built using the Laravel framework, the system ensures structured and secure web application development. The Research and Development (R&D) method was applied through stages of needs analysis, system design, development, validation, and evaluation. The implementation results indicate that the system accelerates library services, minimizes data entry errors, and facilitates user access to collection information and transaction history. Testing was conducted by involving librarians as the primary users, and evaluation results revealed a high level of satisfaction regarding the system’s ease of use and functionality. In conclusion, the system functions effectively and can serve as an efficient and user-friendly solution for digital library management in educational institutions.

Interactive Learning Media for Introduction to English for Early Childhood Education (Paud) Web-Based

2025-06-27T13:11:18+07:00

The development of information technology has opened new opportunities in education, particularly in the creation of interactive learning media. This study aims to design web-based interactive learning media for introducing English to early childhood education (PAUD). Using a R&D (Research and Development) approach with the ADDIE development model (Analysis, Design, Development, Implementation, Evaluation), this study produces a web-based learning platform that integrates learning materials, quizzes, and progress monitoring features for children. This learning media is designed to enhance students' learning interest through interactive content incorporating text, audio, images, and animations. Additionally, the system allows teachers and parents to monitor children's learning progress in real-time. By utilizing web-based technology, the application is accessible to a broad audience, including remote areas with limited educational resources.

Village Evaluation System in Kem Kem using the Weighted Product Method

2025-06-27T13:16:04+07:00

Village staff performance appraisal is an important part of knowing how well an organization is running, including in the village government. In Kem-Kem Village, the staff performance appraisal process has been done manually and subjectively. This can lead to unfairness and lack of transparency in decision-making. To overcome these problems, the purpose of this research is to create a computerized system to evaluate staff performance using the Weighted Product (WP) method. The WP method was chosen because it can process data based on several criteria. This is done by considering the importance of each criterion proportionally to other criteria. This system was developed using PHP programming language and MySQL database. The assessment criteria include responsibility, discipline, cooperation, initiative, and attendance. The results of applying the WP method show that it can produce objective and consistent staff performance ratings based on overall staff preferences. The system also helps the village government conduct regular and thorough performance checks. The system also makes it easier for Kem-Kem Village staff to be accountable for their work and encourages them to do their best.

Expert System for Dental Disease Diagnosis with Forward Chaining Method at Sidoarjo Dental Clinic

2025-06-27T19:03:02+07:00

A Dental health is very important. For most Indonesians, the recommendation to have their teeth checked every six months is generally considered less important because they prioritize the health of other organs of the body. In fact, diseases that attack the teeth can have a very pronounced impact, such as cosmetic problems. Applied computer science research in the field of medicine, especially dental disease problems at the clinic sidoarjo, uses the concept of an expert system. An expert system is a system in the form of computer software in which the computer is created to think like an expert system. The search method used is forward chaining with a decision tree, namely tracing known facts that support the conclusions drawn. This expert system facilitates patient consultations to manage symptom data along with diseases and patient data can be seen from the results of a very useful diagnosis, which can be used as an initial diagnosis by a doctor.

Design of an Administrative Information System at the First GBI Medan Web-Based using the Agile Method

2025-06-27T22:22:07+07:00

The development of information and technology, making information a very important thing to support work in institutions and organizations, many organizations use web-based information systems to improve the efficiency and accuracy of their administrative and management performance, for example administration in church organizations. However, the application of web-based administrative information systems in religious environments, especially churches, is still very limited. Many churches, in reporting every week, use desktop applications in recording the number of offerings and congregations that attend divine services every week. Then for reporting every other activity there is no report at all. One of them is GBI Pertama Medan which in managing its administrative system which still relies on manual methods, namely through word processing applications such as Excel and Word which are still less effective, which results in various problems and obstacles such as recording errors, delays in submitting information, and difficulties in accessing data quickly and accurately. This study aims to and build a web-based administrative information system that will help make it easier for congregations and admins to search and manage administrative data for the First Indonesian Baptist Church Medan. The method used in the development and design of the First GBI Medan administrative information system is the Agile method. Which, this Agile method is widely used in the Software Development Life Cycle (SDLC). Each stage of this method, such as planning, analysis, design, development, testing, and maintenance can help design administrative web systems and various other administrative features at the First Indonesian Baptist Church of Medan, such as managing congregational data, offerings, ministerial schedules, announcements, and FT devotional reading lists. Based on the description above, the authors are interested in conducting research and taking the title of designing an administrative information system at the First GBI Medan web-based using the Agile method

Acceptance of the Use of KAIPay Digital Wallets Using the UTAUT Model

2025-06-27T13:15:00+07:00

The rapid development of digital technology has driven the adoption of application-based payment services such as KAIPAY; however, its usage among students remains suboptimal. This study aims to analyze the factors influencing the intention and behavior of students to use the KAIPAY application, referring to the Unified Theory of Acceptance and Use of Technology (UTAUT) model, which is modified by adding the variable of Trust. Using a quantitative approach and survey method, data will be collected through a questionnaire designed to explore users' perspectives and experiences. Data analysis is planned to utilize Structural Equation Modeling (SEM) to examine the influence of the variables Performance Expectancy, Effort Expectancy, Social Influence, Facilitating Conditions, and Trust on Behavioral Intention and Use. By understanding these factors, this research is expected to provide deeper insights into how trust and social influence can contribute to the adoption of digital payment applications among students.

Designing Ministry Profile Video Glow Community Church Medan Using Color Grading Technique

2025-06-28T17:31:16+07:00

The development of informatics media technology supported by hardware and software systems has improved the quality and speed of information presented. This encourages various organizations, including churches, to be able to present information quickly and on target. Glow Community Medan (GCM) Church utilizes multimedia technology to support promotional activities and the preaching of the word of God digitally. One of the techniques used in improving visual quality is color grading. This research aims to design a ministry profile video at the GCM church with the application of color grading techniques and can improve the visual quality of the video and audience appeal. The resulting video is expected to be an effective promotional tool for the church.

Application of K-Means on Human Rights, Demographic, Economic, and Crypto Investment Data

2025-06-28T22:40:04+07:00

Abstract

This study combines the K-Means Clustering and Decision Tree methods to analyze multidomain data covering economic and social human rights, demographics, poverty, crypto investment, and sustainable financing in Indonesia's financial services sector. Data was obtained from various credible sources such as the National Commission on Human Rights (Komnas HAM), the Central Statistics Agency (BPS), the Financial Services Authority (OJK), and scientific publications (2019–2023), then processed through missing value handling, outlier detection, and normalization using Min-Max Scaling and Z-score. K-Means was used to group regions based on the similarity of socio-economic and financial indicators, while Decision Tree was used to classify financial entities based on ESG (Environmental, Social, and Governance) scores. Model evaluation was conducted using WCSS, Silhouette Score, Davies-Bouldin Index, and classification accuracy. The results show the formation of clusters representing different levels of inequality and sustainability in Indonesia. This approach contributes to understanding the dynamics of multidimensional development and provides a basis for more adaptive and sustainable policies in the socio-economic and financial sectors.

Utilization of Data Mining in Finding Household Electricity Consumption Patterns in Indonesia

2025-06-27T16:30:57+07:00

Penelitian ini bertujuan untuk mengidentifikasi pola konsumsi listrik rumah tangga di Indonesia berdasarkan waktu penggunaan, yaitu siang dan malam, menggunakan teknik data mining, terutama metode clustering K-Means. Data yang digunakan terdiri dari konsumsi listrik harian dalam satuan kWh pada siang dan malam hari. Proses analisis dimulai dengan pra-pemrosesan data untuk memastikan kualitas dan keseragaman skala data, kemudian dilanjutkan dengan pengelompokan data ke dalam tiga kelompok yang mewakili karakteristik konsumsi listrik yang berbeda. Hasil clustering menunjukkan tiga pola utama: bahkan konsumsi antara siang dan malam, konsumsi tinggi di malam hari, dan konsumsi tinggi di siang hari. Temuan ini mengungkapkan keragaman perilaku penggunaan listrik yang dipengaruhi oleh faktor sosial-ekonomi dan kebiasaan sehari-hari. Dengan memahami pola-pola ini, pemerintah dan penyedia listrik dapat merancang kebijakan efisiensi energi yang lebih bertarget, termasuk pengembangan tarif listrik berbasis waktu dan program pendidikan hemat energi. Pendekatan ini mendukung pengelolaan energi yang lebih efektif dan berkelanjutan di sektor rumah tangga di Indonesia.

Decision Analysis on the Feasibility of Granting People's Business Credit at PT. Bank Negara Indonesia Using the Multi-Objective Optimization On The Basis of Ratio Analysis (MOORA) Method

2025-06-28T11:22:28+07:00

In selecting credit recipients, it is necessary to have a recipient selection system that can overcome the problem of bad credit that often occurs (loans that are not repaid by the debtor). Based on this problem, a decision support system is needed that helps identify the wrong recipient. The method used in this study is the Moora method, namely the method for determining priorities. A decision support system

is a computer-based system consisting of interacting components: a language system component, a knowledge system component, and a problem-handling system component, and uses data and decisionmaking models to create semistructured problems. It solves structured problems and semi-structured problems and assist in decision making. Structured and unstructured problems, this system helps you get information about your customers, the results are more accurate and on target.

Decision Support System to Determine KIP Scholarship Recipients at STIKOM Uyelindo Kupang

2025-06-20T15:30:57+07:00

Increasing access to higher education for the underprivileged is a priority through the Smart Indonesia Card (KIP) College program. However, the selection process for scholarship recipients often faces challenges in the form of many criteria that must be considered manually, such as academic achievement, economic conditions, and the number of family dependents, which can affect the efficiency and accuracy of decision making. This study aims to develop a Decision Support System (DSS) based on the Naive Bayes method that is able to automate the selection process by considering various criteria objectively. This study is a web-based system that is expected by STIKOM Uyelindo Kupang to conduct the selection of KIP scholarship recipients more quickly, transparently, and accurately. This system is expected to be able to increase the effectiveness and efficiency of the selection process and minimize the potential for bias, thus ensuring that prospective recipients are truly worthy.

Socio-Economic Status Classification of Neighborhood Residents Using the Decision Tree Algorithm

2025-06-30T17:52:10+07:00

This study aims to analyze the socioeconomic classification of RT residents using the Decision Tree algorithm. The analysis was carried out using data that includes attributes such as the number of family members, education, and occupation. The results of the study show that the Decision Tree algorithm is capable of producing a clear and structured classification model, with the number of family members being the dominant factor in class distribution. Most residents were classified into the Middle socioeconomic category (68.3%), followed by the Low category (26.8%), and the High category (4.9%). These results reflect that the majority of residents have relatively stable socioeconomic conditions, although there are still groups that require special attention. This classification model provides important insights for policymakers to design more focused assistance and economic empowerment programs. This study also recommends further development by adding more diverse attributes and comparing the Decision Tree algorithm with other classification methods to improve the model’s accuracy and validity.