科研之友
微信
新浪微博
Facebook
分享链接
摘要
Clustering is a popular data-analysis and data-mining technique that has been addressed in many contexts and by researchers in many disciplines. The K-means algorithm is one of the most popular clustering algorithms because of its simplicity and easiness in application. However, its performance depends strongly on the initial cluster centers used and can converge to local minima. To overcome these problems, many scholars have attempted to solve the clustering problem using meta-heuristic algorithms. However, as the dimensionality of a search space and the data contained within it increase, the problem of local optima entrapment and poor convergence rates persist; even the efficiency and effectiveness of these algorithms are often unacceptable. This study presents a simplex method-based social spider optimization (SMSSO) algorithm to overcome the drawbacks mentioned above. The simplex method is a stochastic variant strategy that increases the diversity of a population while enhancing the local search ability of the algorithm. The application of the proposed algorithm on a data-clustering problem using eleven benchmark datasets confirms the potential and effectiveness of the proposed algorithm. The experimental results compared to the K-means technique and other state-of-the-art algorithms show that the SMSSO algorithm outperforms the other algorithms in terms of accuracy, robustness, and convergence speed.
