期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2011
卷号：2
期号：4
页码：1747-1749
出版社：TechScience Publications
摘要：This paper presents the analysis of leader- follower, k-means and k-medians clustering algorithms in outlier detection based on some statistical models and spatial proximity. Clustering and classification plays a vital role in data mining. Clustering groups the similar data together based on the characteristics they possess. Clustering, which is so much used in pattern recognition, reduces the searching load. Leaderfollower algorithm is the simplest one. K-means clustering algorithm clusters the similar data with the help of the mean value and squared error criterion whereas in k-medians algorithm, median value is used. Outliers, the one which is different from norm, should be detected and handled properly. Otherwise, it will affect the original data in clustering in a great manner. Dataset for simulation has been generated using “weka” software.
