Automatic Determination of the Initialization Number of Clusters in K-means Clustering Application by Using Co-occurrence Statistics Techniques for Multispectral Satellite Image
Nowadays, clustering is a papular tool for explora tory data analysis, such as K-means and Fuzzy C-mean. Auto matic determination or the initialization number of clusters In k-means clustering application is often needed in advance as an input parameter to the algorithm. In this paper, a method has been developed to determine rhe initialization number of clusters in satellite image clustering application using a data mining algorithm based on the co-occurrence matrix technique. The proposed method was tested using data from unknown number of clusters with multispectral satellite image in Thail and. The results from the tests confirm the effectiveness of the proposed method in rinding the initialization number of clus ters and compared with isodata algorithm.
determination a number of clusters number of cluster K-mean
Kitti Koonsanit Chuleerat Jaruskulchai
Department of Computer Science, Faculty of Science, Kasetsart University, Bangkok, 10900, Thailand
国际会议
成都
英文
1500-1504
2010-12-17(万方平台首次上网日期,不代表论文的发表时间)