Modifying Genetic Algorithm with Species and Sexual Selection by using K-means Algorithm

Presently, the optimization concept plays an important role in the problems related to engineering management and commerce etc. Recent trends in optimization, points towards the genetic algorithm and evolutionary approaches. Different genetic algorithms are proposed, designed and implemented for the single objective as well as for the multiobjective problems. GAS3 [2006] (Genetic Algorithm with Species and Sexual Selection) proposed by Dr. M. M. Raghuwanshi and Dr. O. G. Kakde is a distributed Quasi steady state real-coded genetic algorithm. In this work, we have modified GAS3 algorithm. We introduce a reclustering module in GAS3 after simple distance based parameter less clustering (species formation). GAS3KM (Modifying Genetic Algorithm with Species and Sexual Selection by using K-means algorithm) uses K-means clustering algorithm for reclustering. Experimental results show that GAS3KM has outperformed GAS3 algorithm when tested on unimodal and multimodal test functions.