Clustering is one of most commonly used approach in the literature of Pattern recognition and Machine Learning. K-means clustering algorithm is a fast and simple method in the clustering approaches. However, due to random selection of center of clusters and the adherence to preliminary results of center of clusters, the risk of trapping to a local minimum ever exist.in this study, we have taken help of effective hybrid of optimization algorithms, artificial bee colony (ABC) and differential evolution (DE), is proposed as a method to mentioned problems. The proposed method consists of two main steps. In first step, Seed Cluster Center Algorithm employed to best initial cluster centers. The combined evolutionary algorithm explores the solution space to find global solution. The performance of proposed method evaluated with standard data set. The evaluation results of the proposed algorithm and its comparison with other alternative algorithms in literature confirms its superior performance and higher efficiency.
CITATION STYLE
Bonab, M. B., Zaiton Mohd Hashim, S., Khalaf Zager Alsaedi, A., & Hashim, U. R. (2015). Modified K-means combined with artificial bee colony algorithm and differential evolution for color image segmentation. In Advances in Intelligent Systems and Computing (Vol. 331, pp. 221–231). Springer Verlag. https://doi.org/10.1007/978-3-319-13153-5_22
Mendeley helps you to discover research relevant for your work.