A Text Clustering Algorithm Hybriding Invasive Weed Optimization with K-Means
Chunmei Fan, Taohong Zhang, Zhiyong Yang, Li Wang · 2015
Invasive Weed Optimization (IWO) is an optimization algorithm with powerful explorative and exploitive capability. K-MEANS method is a clustering algorithm sensitive to the initial point selection and easy to fall into local optimum. In order to improve the performance of traditional K-MEANS, in this paper, a clustering algorithm framework hybirding IWO with K-MEANS is argued. This paper mainly focus on dicussing different manner of combining those two algorithms, we try two methods and apply them to the Chinese text clustering. To our knowledge, such applications of IWO-KMEANS hasn't been reported in other literatures. The experimental results shows that compared with the traditional K-MEANS algorithm, as well as the Differential Evolution optimization based K-MEANS(DE-KMEANS) algorithm, employing IWO optimization to select cluster center outperforms all aforementioned methods.