Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Computer Science, Information Technology and Telecommunication Engineering (JCoSITTE)
Muhammad Khalil Gibran
Universitas Muhammadiyah Sumatera Utara
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
A Hybrid RBF Neural Network and FCM Clustering for Diabetes Prediction Dataset Muhammad Khalil Gibran; Amir Saleh
Journal of Computer Science, Information Technology and Telecommunication Engineering Vol 4, No 2 (2023)
Publisher : Universitas Muhammadiyah Sumatera Utara, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30596/jcositte.v4i2.15573

Abstract

This study aims to predict diabetes by combining the Radial Basis Function Neural Network (RBFNN) and Fuzzy C-Means (FCM) clustering methods. Diabetes prediction is an important part of research in an effort to prevent, manage, and reduce this type of disease. The FCM clustering method is used to group diabetes data into groups that have similar characteristics and obtain the final centroid. Then, the RBFNN method is used to build a predictive model using the center of each group as a reference point in the RBF function based on the centroid generated from the FCM clustering method. This step allows for modeling the non-linear relationship between health attributes and diabetes risk in more detail. In this study, the dataset obtained used input parameters regarding health data and risk factors for the disease. The goal of combining these methods is to develop a predictive model that can help identify individuals at high risk of developing diabetes. This hybrid approach has the potential to improve the effectiveness and accuracy of diabetes prediction. From the tests carried out, the proposed method obtained an accuracy of 92%, a precision of 90%, a recall of 92%, and an F1-score of 91%. By combining the clustering power of FCM clustering with RBF's ability to model non-linear relationships, this hybrid approach can make a good contribution to diabetes prediction and assist in efforts to prevent and control this disease.
Co-Authors Amir Saleh