Abstract Views :178 |
PDF Views:0
Authors
Affiliations
1 PG and Research Department of Computer Science, Quaid-E-Millath Government College for Women (A), Chennai- 600002, Tamil Nadu, IN
Source
Indian Journal of Science and Technology, Vol 8, No 29 (2015), Pagination:
Abstract
Background/Objectives: Web Usage Mining (WUM) is one of the categories of web mining that identifies user patterns of web data, with the help of knowledge acquires from web logs. Methods/Statistical Analysis: The structure of the web site has to be reorganised to suit the user requirements to facilitate the user for the required pages with less page access delay. The Splay trees are efficient balanced trees when total running time is the measure of interest. Findings: The motive of mining is to find users’ access models automatically and quickly from the vast Web log data, like frequently accessed pages and time spent on those pages. Web usage mining consist of three phases namely Data pre-processing, Pattern discovery and Pattern analysis. Pre-processing tasks are used to translate unprocessed log files which are composed from web server into structured log file data. Pre-processed log file data are used for further process of web usage mining. This paper present the pre-processing technique and an approach for re-organisation of website based on the access frequency of web pages using splay tree structure. Application/Improvements: The nodes of the splay tree can be added with the information about priority of recently accessed web pages to reduce the page access delay.
Keywords
Pre Processing, Splay Tree, Web Log, Web Site Reorganisation, Web usage Mining
Full Text
