An Efficient Algorithm to fix Initial Centroid for Clustering High Dimensional data

Main Article Content

M. Saranya
P. Krishnakumari


Clustering is one of the primary data analysis methods and K-Means clustering is one of the most well known popular clustering algorithm. The K-Means algorithm is one of the most frequently used clustering method in data mining, due to its performance in clustering massive data sets. The final clustering result of the K-Means clustering algorithm greatly depends upon the correctness of the initial centroids, which are selected randomly. Because of the initial cluster centers produced arbitrarily, K-Means algorithm does not promise to produce the consistent clustering results. Efficiency of the original K-Means algorithm heavily rely on the initial centroids. The number of distance calculations increases exponentially with the increase of the dimensionality of the data. An algorithm is proposed which uses the Principal Component Analysis (PCA) in the first phase that simplifies the analysis and visualization of multi dimensional data set and in the second phase, a method is proposed to find the initial centroids to make the algorithm more effective and efficient. The proposed algorithm is implemented using MATLAB 7.10. This method provides more accurate results with less computational time compared to the existing algorithm.



Keywords: Clustering, K-Means, PCA.


Download data is not yet available.

Article Details