Comparison Of K-Nearest Neighbor And CNN Classification Methods In Diabetic Data Sets

Authors

  • Ajeng Arina Nisa R STMIK KAPUTAMA
  • A M H Pardede STMIK KAPUTAMA
  • Marto Sihombing STMIK KAPUTAMA

DOI:

https://doi.org/10.59934/jaiea.v3i1.272

Keywords:

Diabetes, Data Mining, K-Nearest Neighbor, Convolutional Neural Network, Classification, Python

Abstract

The number of diabetics worldwide is projected to increase by 204 million (48%), from 425 million in 2017 to 629 million in 2045. Indonesia ranks sixth out of ten countries with the most number of diabetics in the world or 10 million people. The majority of people with diabetes are between 20 and 64 years old, or 327 million people, compared to 123 million people between 65 and 99 years old. The incidence of diabetes increases by about 4.8% at the age of 55-64 years, and women (1.7%) suffer from diabetes more than men (1.4%). Therefore, the authors will create a program to determine the patient's diabetes. One approach is to use machine learning as a data mining classification technique. The author will do a classification comparison with the two methods, namely the KNN and CNN methods to provide the best results of the two methods for testing. So that the accuracy of the data from the diagnosis and photo images of the disease can be known to provide early treatment before the severity of the disease.

Downloads

Download data is not yet available.

References

Argina, A.M. (2020). Application of the K-Nearest Neigbor Classification Method to Diabetic Datasets. Indonesian Journal of Data and Science, 1(2), 29-33.

Muslih, M., & Rachmawanto, E. H. (2022). Convolutional Neural Network (CNN) for Image Classification of Diabetic Retinopathy. SKANIKA, 5(2), 167-176.

Sholeh, M., Andayati, D., & Rachmawati, R. Y. (2022). DATA MINING CLASSIFICATION MODEL USING K-NEAREST NEIGHBOR ALGORITHM WITH NORMALIZATION FOR DIABETES PREDICTION. TeIKA, 12(02), 77-87.

Syahrul, F. H., & Sasongko, P. S. Application of the Convolutional Neural Network for Classifying the Severity of Diabetic Retinopathy in Patients with Diabetes Mellitus. Journal of the Informatics Society, 13(1), 1-14.

Marcella, Dewi, Yohannes Yohannes, and Siska Devella. "Classification of eye disease using Convolutional Neural Network with VGG-19 architecture." Journal of Algorithms 3.1 (2022): 60-70.

Agustin, Tinuk. ANALYSIS OF THE COMBINATION OF CONVOLUTIONAL NEURAL NETWORK (CNN) AND SUPPORT VECTOR MACHINE (SVM) IN THE AUTOMATIC DETECTION OF NON-PROLIFERATIVE DIABETIC RETINOPATHY. Diss. AMIKOM Yogyakarta University, 2021.

Zakiya, Putri Nada, and Ledya Novamizanti. "Classification of Retinal Macular Pathology Through Oct Image Using Convolutional Neural Network With Mobilenet Architecture." eProceedings of Engineering 8.5 (2021).

Putry, N.M. (2022). COMPARISON OF KNN AND NAÏVE BAYES ALGORITHMS FOR DIABETES MELLITUS DIAGNOSIS CLASSIFICATION. Evolution: Journal of Science and Management, 10(1).

Downloads

Published

2023-10-15

How to Cite

Nisa R, A. A., Pardede, A. M. H., & Sihombing, M. (2023). Comparison Of K-Nearest Neighbor And CNN Classification Methods In Diabetic Data Sets. Journal of Artificial Intelligence and Engineering Applications (JAIEA), 3(1), 128–134. https://doi.org/10.59934/jaiea.v3i1.272