An Evolutionary Approach for Clustering User Access Patterns from Web Logs

摘要

In this paper rough c-means is applied to cluster user access patterns, in which PSO(Particle Swarm Optimization) algorithm is employed to tune the threshold and relative importance of upper and lower approximations. The Davies-Bouldin clustering validity index is used as the fitness function that is minimized while arriving at an optimal clustering. The effectiveness of the algorithm is demonstrated by an experiment.