论文部分内容阅读
为了克服传统K-Means算法初始聚类中心选择的盲目性,提高聚类精度和聚类结果的稳定性,提出一种基于闻香识源的人工蜂群聚类算法,用于数据聚类.该算法首先利用样本数据稠密度反馈的信息(花香)来寻找初始聚类中心,接着交替进行K-Means聚类,人工蜂群在高密度数据区以贪婪原则搜索最佳聚类中心,往复多次以达到良好且稳定的聚类效果.实验表明该算法简单高效,聚类效果好.
In order to overcome the blindness of the initial clustering center selection and improve the clustering accuracy and the stability of clustering results, an artificial bee colony clustering algorithm based on smelling knowledge is proposed for data clustering. The algorithm firstly uses the information of the sample data density feedback (flower) to find the initial cluster centers, and then alternates the K-Means clustering. The artificial bee colony searches for the best cluster centers in the high-density data area by greedy principle, Time to achieve good and stable clustering results.Experiments show that the algorithm is simple and efficient, clustering effect is good.