Linearly Decreasing Weight Particle Swarm Optimization with Accelerated Strategy for Data Clustering

Clustering technique helps effectively to simplify the complexity of a large amount of data and identify the structure between data to data. It is a common technique for statistical data analysis that is used in many fields, e.g., machine learning, data mining, pattern recognition, image analysis, and bioinformatics. The distribution of information can be in different sizes or shapes. An improved technique combines the linearly decreasing weight particle swarm optimization (LDWPSO) and an acceleration strategy is proposed in this paper. The accelerated linearly decreasing weight particle swarm optimization (ALDWPSO) searches for cluster centers in an arbitrary data set and identifies global optima effectively. ALDWPSO is tested through six experimental data sets, and its performance is compared with the performance of PSO, NM-PSO, K-PSO, K-NM-PSO, LDWPSO and K-means clustering methods. The results indicate that ALDWPSO is a robust and suitable method for solving the clustering problems.