A study on cluster validity using intelligent evolutionary K-means approach
Ming‐Hseng Tseng, Chang-Yun Chiang, Ping-Hung Tang, Hui‐Ching Wu · 2010
The K-means clustering is commonly used in applications of unsupervised classification and the related area due to its simplicity and effectiveness. In this study, an intelligent evolutionary K-means algorithm (IEKA) is firstly developed to optimize the cluster centers by using an improved real-coded genetic algorithm. Then, four cluster validation indices for data clustering are evaluated on six real-life datasets. Finally, experiments are conducted and the performance comparisons of the proposed IEKA approach with other six clustering techniques are reported in this paper.