Adaptive Neuro-Fuzzy Inference System Enhanced with Metaheuristic Optimization for Enhanced Predictive Modeling of Complex System Dynamics

Abstract

This research paper introduces a novel approach to predictive modeling of complex system dynamics by enhancing the Adaptive Neuro-Fuzzy Inference System (ANFIS) with metaheuristic optimization techniques. ANFIS, renowned for its ability to combine the learning capabilities of neural networks with the interpretability of fuzzy logic, often struggles with optimal parameter selection when applied to highly complex and non-linear systems. This study proposes a hybrid framework that leverages the strengths of both ANFIS and metaheuristic algorithms, specifically Particle Swarm Optimization (PSO) and Genetic Algorithms (GA), to optimize the antecedent and consequent parameters of the fuzzy inference system. The proposed methodology is rigorously evaluated using benchmark datasets representing diverse complex systems, including time series forecasting, system identification, and chaotic system prediction. The results demonstrate that the metaheuristic-optimized ANFIS significantly outperforms traditional ANFIS and other established predictive modeling techniques in terms of accuracy, robustness, and generalization ability. This research contributes to the advancement of intelligent systems by providing a powerful and versatile tool for analyzing and predicting the behavior of complex systems across various domains..