Fuzzy Parameter Adaptation in Genetic Algorithms for the Optimization of Fuzzy Integrators in Modular Neural Networks for Multimodal Biometry

Abstract

In this paper, we propose a new method for fuzzy adaptation of the Gap Generation and mutation parameters in Genetic algorithms to optimize Fuzzy Systems used as integration methods in modular neural networks for multimodal biometrics. The Genetic Algorithm is an optimization method inspired on the evolutionary ideas of natural selection and genetics; therefore, we propose an improvement to the convergence of the genetic algorithms using fuzzy logic. Simulation results show that the proposed approach improves the performance of Genetic Algorithms. A comparison of the proposed method using type-1 fuzzy logic for dynamic parameter adaptation with respect to the original Genetic Algorithms approach is presented. Additionally, a statistical test is presented to prove the performance enhancement in the application provided by fuzzy parameter adaptation in the genetic algorithm. The main contribution in this work is the fuzzy adaptation of parameters in the genetic algorithm using type-1 fuzzy logic and with this finding the optimal values of the parameters of the fuzzy integrators, to improve the recognition percentage of the modular neural network for multimodal biometrics.