Fuzzy Logic and Differential Evolution Based Expert System for Defining Top Athlete's Aerobic and Anaerobic Thresholds

Abstract

This article describes an expert system for defining an athlete's aerobic and anaerobic thresholds that successfully mimics the decision-making done by sport medicine professionals. The functionality of our system is based on the fuzzy comparison measure, generalized mean, fuzzy membership functions and differential evolution. Differential evolution is used to tune the parameters in our comparison measure. This measure is based on the use of fuzzy equivalences and a modification factor that tunes the shape of the membership function in hand. The measure presented is especially suitable for expert systems. We will test our system in order to show that our result does not show any statistically significant difference from the values estimated by experts.