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

Saiful Arifin Ipin; Tukino; Elfina Novalia

doi:10.59934/jaiea.v4i3.1154

Authors

Saiful Arifin Ipin Universitas Buana Perjuangan Karawang
Tukino Universitas Buana Perjuangan Karawang
Elfina Novalia Universitas Buana Perjuangan Karawang

DOI:

https://doi.org/10.59934/jaiea.v4i3.1154

Keywords:

Support Vector Machine (SVM), automatic classification, scrap metal, physical characteristics of metals, waste metal management, machine learning.

Abstract

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.

Downloads

Download data is not yet available.

References

Sari, M., & Ramadhan, R. (2020). Classification of waste types using the Support Vector Machine (SVM) algorithm. Journal of Informatics Engineering, 13(1), 12–19.

Pramudia, R., & Nurhayati, D. (2021). Application of Support Vector Machine for Classification of Metal Imagery. Scientific Journal of Technology and Informatics, 5(2), 134–142.

Rahmawati, D., & Hamdani, A. (2022). Implementation of Machine Learning in Metal Waste Treatment in Small Industries. Journal of Industrial Engineering, 11(3), 201–210.

Nugroho, A., & Firmansyah, R. (2020). Analysis of Inorganic Waste Classification Using SVM and KNN Methods. Journal of Informatics Mulawarman, 15(2), 89–95.

Siregar, T. M., & Sihombing, F. (2019). Classification of metal materials based on physical properties using data mining. Journal of Intelligent Systems, 3(1), 55–62.

Aditya, B. R., & Susilo, A. (2021). Kernel's Influence on SVM for Multicategory Data Classification. Journal of Computer Technology and Systems, 9(1), 35–42.

Fauzi, M. R., & Hidayat, R. (2023). SVM Parameter Optimization Using Grid Search in Metal Object Detection. Journal of Informatics and Science, 11(2), 105–113.

Wahyuni, I., & Ramli, A. (2020). Application of SVM Method for Classification of Used Materials Based on Color and Texture Features. Journal of Electrical and Computer Engineering, 7(3), 221–228.

Kurniawan, A. T., & Dwi, R. (2021). The industrial waste classification system uses machine learning. Journal of Informatics and Technology, 4(2), 88–95.

Putri, R. D., & Hidayatullah, F. (2020). SVM Performance Analysis in Industrial Material Classification. Journal of Information and Computer Technology, 8(2), 146–152.

Lestari, M., & Nugraha, D. (2022). Application of Feature Extraction on SVM for Metal Detection. Journal of Data Processing, 6(1), 59–67.

Fadli, M. R., & Yuniarti, D. (2021). Implementation of Support Vector Machine Algorithm in the Recycling Industry. Journal of Systems Engineering, 9(1), 97–104.

Santosa, A., & Dewi, L. (2019). Evaluation of SVM Algorithms for Multiclass Classification with Confusion Matrix. Journal of Information Systems, 11(2), 84–90.

Akbar, I., & Prasetyo, E. (2021). Utilization of Metal Physical Data for SVM-Based Automatic Classification System. Journal of Technology and Applied Science, 10(3), 213–220.

Yuliana, S., & Zulfikar, M. (2020). Comparative Analysis of SVM and Decision Tree for Classification of Used Materials. Journal of Informatics and Computers, 7(1), 72–80.

Rohman, A., & Wijayanto, B. (2022). Predict the type of material using a machine learning model. Journal of Computer Engineering, 5(2), 133–140.

Nasution, R. F., & Kurnia, D. (2021). Analysis of Characteristics of Scrap Metal with SVM and PCA. Journal of Science and Informatics, 3(4), 187–195.

Maulana, R., & Putra, H. (2023). Data Mining Application for Optimization of Iron Waste Management. Journal of Information Technology, 12(1), 45–52.

Salsabila, T., & Lestari, F. (2020). Classification of inorganic solid waste using image-based SVM. Journal of Intelligent Systems, 4(2), 114–121.

Wibowo, A., & Hidayah, N. (2021). Comparison of SVM Kernels in Industrial Metal Type Classification. Journal of Informatics Engineering, 13(2), 101–108.

Ramadhan, F., & Setiawan, R. (2022). Classification of Materials Based on Magnetic Sensor and SVM Data. Journal of Electrical Technology, 5(3), 198–206.

Zulfa, M., & Farhan, R. (2021). Automatic Classification System for SVM-Based Used Goods. Journal of Computer Science, 6(1), 66–74.

Nurhaliza, D., & Saputra, R. (2023). Implementation of Machine Learning for Classification of Used Industrial Materials. Journal of Information Technology Engineering, 11(2), 157–165.

Juwita, S., & Hamzah, A. (2020). Analysis of the Use of SVM Algorithm in Light Industrial Applications. Journal of Computer Science and Its Applications, 8(3), 183–190.

Firmansyah, A., & Haris, N. (2021). The Utilization of SVM in the Automatic Sorting System of Industrial Used Materials. Journal of Applied and Computer Technology, 9(2), 120–127.