Insulin-resistant control under uncertainty using a hybrid framework of fuzzy logic and metaheuristic algorithms

Type 1 diabetes is one of the most important chronic metabolic diseases that necessitates accurate and continuous control of blood glucose levels. In this study, a hybrid framework based on fuzzy logic and metaheuristic algorithms is proposed for insulin-resistant control under uncertainty. The proposed model, using two algorithms, the bat (BA) and the greedy man (GMOA), optimizes the fuzzy control structure including membership functions and rules in such a way that the accuracy of glucose regulation is maximized and insulin consumption is minimized. The designed control system is tested based on simulated and real data and its performance in the face of sudden fluctuations is investigated. The results show that the GMOA algorithm has a more accurate performance than BA in adjusting insulin dose and reducing glucose fluctuations. Also, comparing the model output with the exact solution in the GAMS environment confirms the validity of the proposed structure. This framework can be considered a suitable basis for the development of real-time diabetes control systems and the design of smart wearable systems.