基于增强蜂群优化与k-means的文本聚类算法

针对文本数据维度较高、空间分布稀疏及其聚类效果不佳的问题,提出一种基于增强蜂群优化搜索与k-means的高效文本聚类算法。首先为蜂群算法引入公平操作与克隆操作来提高全局搜索的能力,公平操作提高了样本多样性并增强了蜂群搜索能力,克隆操作则增强了各代之间的信息交流,提高了求解质量。最终引入k-means进行局部质心的提炼,提高聚类质量。基于文本数据集的试验结果证明,相较于其他聚类算法,本算法具有更高的聚类质量。

Enhanced bee colony optimal and k-means based document clustering algorithm

Aimed at the problem that the document data has the characteristics such as high-dimensionality and sparseness, a Enhanced bee colony optimal and k-means based document clustering algorithm is proposed. Firstly, the fairness and clone operation are introduced to bee colony to improve the global search power, the individuals diversity and the search power are enhanced by fairness operation, the information communication between different iterations is enhanced by clone operation, and the solution quality is improved. At last, the clustering quality is improved by k-means which is good at local refining. Experiments results based on the documents show that the proposed algorithm has better clustering quality than the other clustering algorithm.