Artificial Intelligence-Based Diabetes Diagnosis with Belief Functions Theory

Ellouze, Ameni; Kahouli, Omar; Ksantini, Mohamed; Alsaif, Haitham; Aloui, Ali; Kahouli, Bassem

doi:10.3390/sym14102197

Open AccessArticle

Artificial Intelligence-Based Diabetes Diagnosis with Belief Functions Theory

by

Ameni Ellouze

^1,2,

Omar Kahouli

^3,*,

Mohamed Ksantini

¹

,

Haitham Alsaif

⁴

,

Ali Aloui

³ and

Bassem Kahouli

⁵

¹

Control & Energies Management Laboratory (CEM-Lab), National Engineering School of Sfax, University of Sfax, Sfax 3038, Tunisia

²

Higher Institute of Computer Science and Multimedia of Gabes, University of Gabes, Gabes 6029, Tunisia

³

Department of Electronics Engineering, Community College, University of Ha’il, Ha’il 2440, Saudi Arabia

⁴

Department of Electrical Engineering, College of Engineering, University of Ha’il, Ha’il 2440, Saudi Arabia

⁵

Department of Management Information Systems, Community College, University of Ha’il, Ha’il 2440, Saudi Arabia

^*

Author to whom correspondence should be addressed.

Symmetry 2022, 14(10), 2197; https://doi.org/10.3390/sym14102197

Submission received: 18 August 2022 / Revised: 12 October 2022 / Accepted: 14 October 2022 / Published: 19 October 2022

Download

Browse Figures

Versions Notes

Abstract

We compared various machine learning (ML) methods, such as the K-nearest neighbor (KNN), support vector machine (SVM), and decision tree and deep learning (DL) methods, like the recurrent neural network, convolutional neural network, long short-term memory (LSTM), and gated recurrent unit (GRU), to determine the ones with the highest precision. These algorithms learn from data and are subject to different imprecisions and uncertainties. The uncertainty arises from the bad reading of data and/or inaccurate sensor acquisition. We studied how these methods may be combined in a fusion classifier to improve their performance. The Dempster–Shafer method, which uses the formalism of belief functions characterized by asymmetry to model nonprecise and uncertain data, is used for classifier fusion. Diagnosis in the medical field is an important step for the early detection of diseases. In this study, the fusion classifiers were used to diagnose diabetes with the required accuracy. The results demonstrated that the fusion classifiers outperformed the individual classifiers as well as those obtained in the literature. The combined LSTM and GRU fusion classifiers achieved the highest accuracy rate of 98%.

Keywords: artificial intelligence; machine learning; deep learning; LSTM; diabetes; belief functions

Share and Cite

MDPI and ACS Style

Ellouze, A.; Kahouli, O.; Ksantini, M.; Alsaif, H.; Aloui, A.; Kahouli, B. Artificial Intelligence-Based Diabetes Diagnosis with Belief Functions Theory. Symmetry 2022, 14, 2197. https://doi.org/10.3390/sym14102197

AMA Style

Ellouze A, Kahouli O, Ksantini M, Alsaif H, Aloui A, Kahouli B. Artificial Intelligence-Based Diabetes Diagnosis with Belief Functions Theory. Symmetry. 2022; 14(10):2197. https://doi.org/10.3390/sym14102197

Chicago/Turabian Style

Ellouze, Ameni, Omar Kahouli, Mohamed Ksantini, Haitham Alsaif, Ali Aloui, and Bassem Kahouli. 2022. "Artificial Intelligence-Based Diabetes Diagnosis with Belief Functions Theory" Symmetry 14, no. 10: 2197. https://doi.org/10.3390/sym14102197

APA Style

Ellouze, A., Kahouli, O., Ksantini, M., Alsaif, H., Aloui, A., & Kahouli, B. (2022). Artificial Intelligence-Based Diabetes Diagnosis with Belief Functions Theory. Symmetry, 14(10), 2197. https://doi.org/10.3390/sym14102197

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Artificial Intelligence-Based Diabetes Diagnosis with Belief Functions Theory

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI