Global K-Means (GKM) Clustering Algorithm: A Survey

Abstract

means clustering is a popular clustering algorithm but is having some problems as initial conditions and it will fuse in local minima. A method was proposed to overcome this problem known as Global K-Means clustering algorithm (GKM). This algorithm has excellent skill to reduce the computational load without significantly affecting the solution quality. We studied GKM and its variants and presents a survey with critical analysis. We also proposed a new concept of Faster Global K-means algorithms for Streamed Data sets (FGKM-SD). FGKM-SD improves the efficiency of clustering and will take low time & storage space. the randomly chosen sets. Every run should be initialized using the K final centroid locations from one of the run of 10 subsets. The K center location that we get from this run will be used to initialize the K-means algorithm for the complete data set. The Global K-Means algorithm (The GKM algorithm) (2) is the incremental approach of clustering. We can dynamically add one cluster center at a time using deterministic global search procedure from suitable initial positions. It is consists of N (Where N is the size of the dataset) executions of K- means algorithm. Experimental results of the algorithm show that GKM algorithm considerably out performs the K-means algorithms.