A new hybrid strategy for data clustering using cuckoo search based on Mantegna levy distribution, PSO and k-means

Abstract

Data clustering is one of the data mining techniques which is widely used in some applications, such as pattern recognition, machine learning, image processing, etc. Swarm intelligence-based algorithms are extensively used in data clustering in recent years. Cuckoo Search (CS) is one of the recently proposed algorithms in the category of swarm intelligence-based techniques. In this paper, a new hybrid algorithm which utilises CS, Particle Swarm Optimisation (PSO) and k-means has been proposed (HCSPSO). The proposed algorithm employed PSO and k-means to produce new nests in standard CS to obtain better results. It also benefits from Mantegna levy distribution to obtain higher convergence speed as well as local search. To eliminate the problem of the high number of functional evaluations in standard CS, a fraction of nests has assigned to every section of the algorithm. The proposed algorithm's performance was evaluated by ten standard benchmark datasets. Evaluation results show that the proposed algorithm is an efficient method for data clustering and produces more optimised results in comparison with standard CS, PSO, Elephant Search Algorithm (ESA), Enhanced Bat Algorithm (EBA), Bird Flock Gravitational Search Algorithm (BFGSA), Improved Cuckoo Search (ICS) and k-means.