Abstract
Multi-objective clustering has received widespread attention recently, as it can obtain more accurate and reasonable solution. In this paper, an improved multi-objective clustering framework using particle swarm optimization (IMCPSO) is proposed. Firstly, a novel particle representation for clustering problem is designed to help PSO search clustering solutions in continuous space. Secondly, the distribution of Pareto set is analyzed. The analysis results are applied to the leader selection strategy, and make algorithm avoid trapping in local optimum. Moreover, a clustering solution-improved method is proposed, which can increase the efficiency in searching clustering solution greatly. In the experiments, 28 datasets are used and nine state-of-the-art clustering algorithms are compared, the proposed method is superior to other approaches in the evaluation index ARI.
Highlights
Knowledge discovery is a process of analyzing data from different prospective and summarizing it into useful information [1]
Abubaker et al proposed a new automatic clustering algorithm based on multi-objective Particle Swarm Optimization (PSO) and Simulated Annealing (MOPSOSA) in [19]
The Adjusted Rand index (ARI) index of same datasets is compared since the author does not provide the source code of MCPSO, and results are dl Discarded solutions
Summary
Knowledge discovery is a process of analyzing data from different prospective and summarizing it into useful information [1]. Improved multi-objective clustering algorithm using particle swarm optimization social behavior of animals like fish schooling and bird flocking It has become an efficient method for searching approximate optimal solution due to its simplicity, few parameter configuration and global exploration ability on some complex problems [12]. Abubaker et al proposed a new automatic clustering algorithm based on multi-objective PSO and Simulated Annealing (MOPSOSA) in [19] This method simultaneously optimizes three different objective functions, which are used as cluster validity indexes for finding the proper number of clusters. The purpose of this paper is to address the limitations of previous work Towards this goal, an improved multi-objective clustering framework using particle swarm optimization (IMCPSO) is proposed, which finds well-separated and compact clusters without the predefined number of clusters.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
