Swarm optimization tuned Mamdani fuzzy controller for diabetes delayed model

Abstract

Diabetes is a chronic disease in which there are high levels of sugar in the blood. Insulin is a hormone that regulates the blood glucose level in the body. Diabetes mellitus can be caused by too little insulin, a resistance to insulin, or both. Although research activities on controlling blood glucose have been attempted to lower the blood glucose level in the quickest possible time, there are some shortages in the amount of the insulin injection. In this paper, a complete model of the glucose--insulin regulation system, which is a nonlinear delay differential model, is used. The purpose of this paper is to follow the glucose profiles of a healthy person with minimum infused insulin. To achieve these purposes, an intelligent fuzzy controller based on a Mamdani-type structure, namely the swarm optimization tuned Mamdani fuzzy controller, is proposed for type 1 diabetic patients. The proposed fuzzy controller is optimized by a novel heuristic algorithm, namely linearly decreasing weight particle swarm optimization. To verify the robust performance of the proposed controller, a group of 4 tests is applied. Insensitivity to multiple meal disturbances, high accuracy, and superior robustness to model the parameter uncertainties are the key aspects of the proposed method. The simulation results illustrate the superiority of the proposed controller.