Data Clustering Using Chaotic Particle Swarm Optimization
Li‐Yeh Chuang, Yu‐Da Lin, Cheng‐Hong Yang · 2012
Clustering is an important analysis tool employed in data statistics. Identification of the structure of large-scale data has become an increasingly important topic in data mining problem. We propose Gauss chaotic map particle swarm optimization (GaussPSO) method for clustering, which uses a Gauss chaotic map to adopt a random sequence with a random starting point as a parameter, the method relies on this parameter to update the positions and velocities of the particles. The Gauss chaotic map provides the significant chaos distribution to balance the exploration and exploitation capability of search process. This easy and fast function generates random seed processes, and further improves the performance of PSO due to its unpredictability. In the study, eight different clustering algorithms were extensively compared on six test data sets. The results indicate that the performance of the GaussPSO method is significantly better than the performance of other algorithms for data clustering problems.