K_means Clustering Algorithm with Fast Lookup Initial Start Center

The traditional k_means algorithm has sensitivity to the initial start center.The clustering accuracy of k_means is affected by the initial start center,and it is very easy to sink into the part best.To solve this problem,for k_means method,we give a new method for selecting initial start center based on sample data distribution to improve the clustering accuracy of k_means.Experiments on the standard database UCI show that the proposed method can produce a high accuracy clustering result and eliminate the sensitivity to the initial start centers.