Classifying of Diabetes Symptoms Using the Backpropagation Neural Network Method

DOI

10.2991/978-94-6463-413-6_7How to use a DOI?

Keywords

Backpropagation; Diabetes; Classifying

Abstract

This study aims to develop a technology that can help diagnose diabetes symptoms accurately. The Backpropagation Neural Network method is used to classify diabetes symptoms based on various parameters such as blood pressure, heart rate, body temperature, sugar levels, cholesterol, uric acid, and oxygen levels. The network training process is carried out using Visual Gene Developer 2.1, with a learning rate of 0.01, momentum of 0.1, and a maximum iteration limit of 50,000 times. The number of neurons in the hidden layer is varied between 1 and 10 at each training session. The results show that the smallest final Sum of Squared Errors (SSE) value is produced by an architecture that uses 7 neurons in the hidden layer, namely 0.0389. In the validation stage, the architecture used is a network that achieves the smallest SSE value during the training process. Validation is carried out using data that is not included in the training on each network. The best network architecture is selected based on the smallest SSE value obtained during the validation stage. The validation results for a 10-7-1 network architecture with a binary activation function of 0.1 show an SSE value of 0.4387. The Backpropagation Neural Network method is chosen because of its ability to learn complex patterns from input data and produce output with a high level of accuracy. By using this method, it is hoped that it can produce an accurate and reliable health classification to improve understanding of diabetes symptoms. The results of this study can be used to improve the quality of health services provided by Health Center I in East Denpasar City to the community, especially in the diagnosis and treatment of diabetes.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Putu Wina Sahyuni
AU  - Putu Sugiartawan
AU  - Wayan Sauri Peradhayana
PY  - 2024
DA  - 2024/05/13
TI  - Classifying of Diabetes Symptoms Using the Backpropagation Neural Network Method
BT  - Proceedings of the First International Conference on Applied Mathematics, Statistics, and Computing (ICAMSAC 2023)
PB  - Atlantis Press
SP  - 62
EP  - 74
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-413-6_7
DO  - 10.2991/978-94-6463-413-6_7
ID  - Sahyuni2024
ER  -