An improved K-Means clustering algorithm

The K-Means clustering algorithm is proposed by Mac Queen in 1967 which is a partition-based cluster analysis method. It is used widely in cluster analysis for that the K-means algorithm has higher efficiency and scalability and converges fast when dealing with large data sets. However it also has many deficiencies: the number of clusters K needs to be initialized, the initial cluster centers are arbitrarily selected, and the algorithm is influenced by the noise points. In view of the shortcomings of the traditional K-Means clustering algorithm, this paper presents an improved K-means algorithm using noise data filter. The algorithm developed density-based detection methods based on characteristics of noise data where the discovery and processing steps of the noise data are added to the original algorithm. By preprocessing the data to exclude these noise data before clustering data set the cluster cohesion of the clustering results is improved significantly and the impact of noise data on K-means algorithm is decreased effectively and the clustering results are more accurate.

[1]  Panagiotis Kanellis,et al.  Data warehouse clustering on the web , 2005, Eur. J. Oper. Res..

[2]  J. MacQueen Some methods for classification and analysis of multivariate observations , 1967 .

[3]  Charu C. Aggarwal A human-computer interactive method for projected clustering , 2004, IEEE Transactions on Knowledge and Data Engineering.

[4]  Jinxin Dong,et al.  K-means Optimization Algorithm for Solving Clustering Problem , 2009, 2009 Second International Workshop on Knowledge Discovery and Data Mining.