期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2015
卷号：4
期号：4
页码：1591-1597
出版社：Shri Pannalal Research Institute of Technolgy
摘要：K-means is one of the simplest unsupervised learning and partitional clustering algorithms. This algorithm classifies a given data set by finding a certain number of clusters (K). The clusters are differentiated by their centers. The best selection is to place them possibly far away. K-means is a most w idely used approach in unsupervised machine learning algorithms tho ugh it w as proposed 50 years ago and is very fast the algorithm is highly sensitive to initial placement of the cluster centers.The survey exa mined KDD process w ith care in order to draw facts leading to a enhanced K-means algorithm to give overwhelming results.This study explore various clustering algorithms/techniques, traditional k-means and on the same some recent work.The review has revealed stupendous ideas which can be recommended.
