Date Added: Nov 2012
High dimensional data is observable fact in real-world data mining applications. Developing efficient clustering techniques for high dimensional dataset is a challenging dilemma because of the curse of dimensionality. The accurateness of the resultant value possibly not up to the level of anticipation while the dimension of the dataset is high because users cannot say that the dataset chosen are free from noises and faults. Generally, k-means clustering algorithm is employed however it results in time consuming, computationally expensive and the eminence of the resulting clusters relies on the selection of initial centroid, the dimension of the data and the similarity measure.