Clustering Spatial Data with Obstacles Constraints by PSO

Abstract

This paper proposes a particle swarm optimization (PSO) method for solving Spatial Clustering with Obstacles Constraints (SCOC). In the process of doing so, we first use PSO to get obstructed distance, and then we developed the PSO K-Medoids SCOC (PKSCOC) to cluster spatial data with obstacles constraints. The experimental results show that PKSCOC performs better than Improved K-Medoids SCOC (IKSCOC) in terms of quantization error and has higher constringency speed than Genetic K-Medoids SCOC (GKSCOC).