A new hybrid algorithm based on black hole optimization and bisecting k-means for cluster analysis
Mohammad Eskandarzadehalamdary, Behrooz Masoumi, Omid Sojodishijani · 2014
Clustering is a popular data analysis and data mining technique. In bisecting k-means clustering technique, the data is incrementally partitioned into K clusters. However, the performance of bisecting k-means algorithm highly depends on the initial state and it may converge to a local optimum solution. To solve these problems, a hybrid evolutionary algorithm using combination of BH (black hole) and bisecting k-means algorithms, called BH-BKmeans is proposed. With this, a dataset would be precisely clustered in a reasonable time complexity and led to global optimum with local refine in clustering. The performance of the proposed algorithm is evaluated through several benchmark data sets. The simulation results show that the proposed algorithm outperforms other typical clustering algorithms such as bisecting k-means, BH and PSO.