Enhanced classification performance using computational intelligence

Abstract

This paper presents a computational intelligence technique for enhancing the performance of classifier using a proposed algorithm called Modified Genetic Search Algorithms (MGSA) that avoids local bad search space with merit and scaled fitness variables, detecting and deleting bad candidate chromosomes, thereby reducing the number of individual chromosomes from search space and subsequent iterations in next generations. It addresses the strength of Modified Genetic Search algorithm combined with the Artificial Neural Network (ANN). In this work dynamic Backpropagation Neural Network is used. For training purpose, dynamic learning rate is used that causes the learning rate to decrease in subsequent epoch. The combined MGSA-ANN is used for the classification of diabetes patients to identify positive and negative cases. It also discusses the main findings and concludes with promising result of the proposed model. The experimental results obtained by synergistic combination of Modified Genetic Search Algorithm with ANN surpass the performance of ANN by 1.4322%. © 2011 Springer-Verlag Berlin Heidelberg.