الفهرس | Only 14 pages are availabe for public view |
Abstract The rapid increase in web sites has created lar~e volume of data in web environment, which generate a problem of how to extract and gain useful knowledge from such data. Extracting such knowledge introduces a rapid services, saves user time with web, and improves user’s efficiency and effectiveness in searching for information on the web. Also this knowledge helps to discovering, and predicting user’s behaviors based on their interaction with a website (Personalization). In this thesis an overview of approaches for data mining and its objectives, process and applications would be explained. Web mining concept (web content mining, web structure mining, web usage mining) and its applications would be introduced .General framework for fully stages of web usage mining including (preprocessing, pattern discovery and pattern analysis), and an approach for e-business and personalization operation would be discussed. Also an overview for different types of data sources, and a brief description for web log files structures would be discussed. Web muung techniques used for analyzing web data like Classification ,Clustering, Sequential Patterns, Association Rules ,and specially Artificial Neural Network behaviors (Operation, Architecture ,Different Training Rules Algorithms and Applications) would be discussed. The aim of this thesis is analyzing web log file data for Information System of Mansoura University Center using proposed Web Knowledge” Extraction from Logs Files (WKELF) analyzing system .This analysis |