Enhancing Decision-making in Uncertain Domains through Optimized Fuzzy Logic Systems

Fuzzy logic helps manage human-like reasoning in system control, mainly when traditional analysis does not work due to complex control processes. Despite its usefulness, fuzzy logic faces challenges in decision-making, especially in complex business situations and when combined with expert systems. It struggles with uncertainty and relies on various beliefs and assumptions, which is limiting compared to other methods for handling uncertainty. However, fuzzy logic can improve traditional control systems by adding a layer of intelligence. This study adapts mathematical functions like the straight-line point-slope equation, the absolute value function, and the Gaussian equation to develop accurate and flexible membership functions for fuzzy logic systems. By analyzing 10000 tasks of different sizes, we found our methods significantly more precise than traditional approaches, especially in determining degrees of membership for uncertain and complex environments. Our MATLAB research shows the potential of using varied membership functions to enhance fuzzy logic systems' accuracy and flexibility.