Spatial Clustering with Obstacles Constraints Based on PSO and K-Medoids
Gaofeng Deng, Pla Information · Journal of Chinese Computer Systems · 2009
Spatial clustering is an important research topic in the Spatial Data Mining (SDM). Classical clustering algorithms have ignored the fact that many constraints exit in the real world and could affect the correctness of clustering result. This paper discussed the problem of Spatial Clustering with Obstacles Constraints (SCOC) and proposed a novel PSO K-Medoids SCOC (PKSCOC) based on the Particle Swarm Optimization (PSO) algorithm and the K-Medoids method. The experimental results proved that our method can not only give attention to local constringency and the whole constringency,but also consider the obstacles that exit in the real world and make the clustering result more practice. PKSCOC has better scalability than Genetic K-Medoids SCOC (GKSCOC),and it is fit for dealing with dynamic constraints.