细菌觅食算法与K-means结合的Web用户会话聚类

Integration of bacterial foraging with K-means for Web user session clustering

Web用户会话聚类是电子商务领域的NP-难问题,目的是发现相似的用户访问行为模式。该问题难度在于对大规模的Web会话进行聚类,且每个会话都表示为高维向量。提出一种细菌觅食算法和K-means相结合的优化算法,用知名的数据集测试其有效性。对Web会话进行聚类,与流行的聚类算法进行比较,实验结果显示该算法高效且性能更优。

Web user session clustering is an NP-hard problem of the e-commerce field. The purpose is to discover user access patterns of behavior. The difficulty of the problem is that large-scale Web session clustering, and each session is indicated for the high-dimensional vector. This paper presents a type of clustering algorithm combining bacterial foraging algorithm with K-means algorithm, using the well-known data set to test their effectiveness, and the Web session clustering. Compared with the popular clustering algorithm, the experimental results show that the algorithm is efficient and has better performance.