A Deterministic K-means Algorithm based on Nearest Neighbor Search
Omar Kettani, Benaissa Tadili, Faycal Ramdani · International Journal of Computer Applications · 2013
In data mining, the k-means algorithm is among the most commonly and widely used method for solving clustering problems because of its simplicity and performance.However, one of the main drawback of this algorithm is that its accuracy and performance are sensitive to the initial choice of clustering centers, which are generated randomly.To overcome this drawback, we propose a simple deterministic method based on nearest neighbor search and k-means procedure in order to improve clustering results.Experimental results on various data sets reveal that the proposed method is more accurate than standard K-means algorithm.