A Hybrid Clustering Algorithm Based on Honey Bees Mating Optimization and Greedy Randomized Adaptive Search Procedure

Abstract

This paper introduces a new hybrid algorithmic nature inspired approach based on the concepts of the Honey Bees Mating Optimization Algorithm (HBMO) and of the Greedy Randomized Adaptive Search Procedure (GRASP), for optimally clustering N objects into K clusters. The proposed algorithm for the Clustering Analysis, the Hybrid HBMO-GRASP, is a two phase algorithm which combines a HBMO algorithm for the solution of the feature selection problem and a GRASP for the solution of the clustering problem. This paper shows that the Honey Bees Mating Optimization can be used in hybrid synthesis with other metaheuristics for the solution of the clustering problem with remarkable results both to quality and computational efficiency. Its performance is compared with other popular stochastic/metaheuristic methods like particle swarm optimization, ant colony optimization, genetic algorithms and tabu search based on the results taken from the application of the methodology to data taken from the UCI Machine Learning Repository.KeywordsHoney Bees Mating OptimizationGreedy Randomized Adaptive Search ProcedureNature Inspired IntelligenceClustering Analysis