Accelerated modified sine cosine algorithm for data clustering

Abstract

In artificial intelligence, data mining is a process that automatically discover valuable information from huge amounts of data in order to obtain knowledge. The most important unsupervised technique of data mining is the clustering technic, which his main task is dividing the dataset into homogeneous groups. Metaheuristics based clustering is an actual research area where optimization algorithms have demonstrated their efficiencies to provide near optimal solutions to this problem in a reasonable time, including the recent Sine Cosine metaheuristic Algorithm (SCA). However, its convergence rate is still rather slow. In this paper, an upgraded adaptation of SCA is proposed to improve the exhibition capacities of the quest strategy for ideal results for data Clustering problem, named AMSCAC. In this algorithm, both the local and global search procedures are enhanced by additional strategy. The experimental results on five standard datasets are promising and confirm the superiority of AMSCAC, for the clustering results over SCA, cuckoo search algorithm (CS), differential evolution algorithm (DE), and genetic algorithm (GA)