ACO-based Type 2 Diabetes Detection using Artificial Neural Networks

Authors

  • Aliakbar Tajari Siahmarzkooh

DOI:

https://doi.org/10.37506/ijfmt.v15i1.13666

Keywords:

Diabetes detection, Artificial Neural Network (ANN), Ant Colony Optimization (ACO).

Abstract

Background: Type 2 diabetes is one of the most common diseases among people. Early diagnosis and
treatment can reduce mortality and morbidity. So far, various solutions have been proposed to predict this
type of disease.
Materials and Method: In this paper, a method for diagnosing diabetes was proposed using the Ant
Colony Optimization (ACO) algorithm. To this end, data set properties are first reduced using artificial
neural network features and then prepared for classification purpose. Finally, some components of accuracy
assessment on the proposed system were calculated.
Results: The simulation results show that by adjusting the parameters of ANN and ACO, about 3.2% better
prediction accuracy is obtained than other researches.
Conclusion: The results of experiments represent that the proposed method is proper for health management
in diabetes.

Author Biography

  • Aliakbar Tajari Siahmarzkooh

    Assistant Professor, Department of Computer Science, Faculty of Sciences, Golestan University, Gorgan, Iran

Downloads

Published

2020-12-31

How to Cite

ACO-based Type 2 Diabetes Detection using Artificial Neural Networks. (2020). Indian Journal of Forensic Medicine & Toxicology, 15(1), 1765-1771. https://doi.org/10.37506/ijfmt.v15i1.13666