抽象的な

A Study of Web Log Analysis Using Clustering Techniques

Hemanshu Rana, Mayank Patel

Web usage mining is the area of web mining which deals with the extraction of interesting knowledge from web log information produced by web servers. Web usage mining techniques can be applied for web log analysis. Web access data, traditionally, are stored in the server log files. Several web usage mining approaches have been presented for exposing usage patterns with the most prominent ones being clustering, association rule, and sequential pattern mining. In this paper, three different algorithms are reviewed for generating clusters. The first one is simple K-means, second K-means using Neural Network concept and Self Organization Map (SOM). , This paper deals with study of a two-stage method that integrates algorithms, first of which uses Self-Organizing Feature Maps neural network to determine the number of clusters and cluster centroids, then the second one is a K-means algorithm to find the final solution.