Affiliations: [a] Hebei University of Engineering, Handan, Hebei 056038, China | [b] Hebei University of Technology, Tianjin 300401, China | [c] School of Information and Electrical Engineering, Hebei University of Engineering, Handan, Hebei 056038, China | [d] School of Mathematics and Physics, Hebei University of Engineering, Handan, Hebei 056038, China | [e] College of Teacher Education, University of the Cordilleras, Baguio City 2600, Philippines
Correspondence:
[*]
Corresponding author: Xue-Guang Wang, School of Information and Electrical Engineering, Hebei University of Engineering, Handan, Hebei 056038, China. E-mail: [email protected].
Abstract: Diabetes is a disease that seriously endangers human health. Early detection and early treatment can reduce the likelihood of complications and mortality. The predictive model can effectively solve the above problems and provide helpful information for the clinic. Based on this, it is proposed to apply the idea of integrated algorithm in DBN algorithm, collect the hospital data by investigating its related factors, clean and process the collected data, and sample and model the processed data multiple times. It is shown that a single DBN classifier is better than support vector machine and logistic regression algorithm. The model established by the integrated deep confidence network has a significant improvement in classification accuracy compared to a single DBN classifier, and solves the unstable classification effect of a single DBN classifier.
Keywords: Diabetes mellitus, deep learning, integrated algorithm, deep believe neural network, prediction model
