Research on Diabetes Aided Diagnosis Model Based on Deep Belief Network

Zhao, Zhijie and Liu, Yang and Sun, Huadong and Han, Xiaowei and Wang, Ran (2019) Research on Diabetes Aided Diagnosis Model Based on Deep Belief Network. In: Wireless and Satellite Systems. 10th EAI International Conference, WiSATS 2019, Harbin, China, January 12–13, 2019, Proceedings, Part I.

[thumbnail of 31604.pdf] PDF
31604.pdf

Download (406kB)

Abstract

Diabetes is a chronic disease that seriously endangers human health, which should be early detection, early diagnosis and early treatment by establishing prediction model. With the help of disease auxiliary diagnosis based on machine learning, the process of early diagnosis could be more reliable. Then, the patients have more chances of early treatment. Deep learning technology can take advantage of its own powerful feature learning ability to the application of disease auxiliary diagnosis, and has gained good results. This paper proposes a diabetes prediction model based on Deep Belief Network (DBN). The model is established by using Pima Indians Diabetes data set, combined with cross-validation, setting DBN structure and adjusting DBN network parameters. The experimental results show that the accuracy of the model is as high as 77.60% and the performance is good.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Date Deposited: 04 Mar 2026 12:02
Last Modified: 20 Nov 2026 12:57
URI: https://eprints.eai.eu/id/eprint/22414

Actions (login required)

View Item
View Item