Web Usage Mining Based on Complex Structure of XML for Web IDS
Marjan Eshaghi1, S.Z. Gawali2

1Marjan Eshaghi, Department of Information Technology, College of Engineering, Bharati Vidyapeeth University, Pune (Maharashtra), India.
2Prof. S.Z. Gawali, Department of Information Technology, College of Engineering, Bharati Vidyapeeth University, Pune (Maharashtra), India.
Manuscript received on 15 April 2013 | Revised Manuscript received on 22 April 2013 | Manuscript Published on 30 April 2013 | PP: 323-326 | Volume-2 Issue-5, April 2013 | Retrieval Number: E0747042413/13©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: In current trend, most of the businesses are running through online web applications such as banking, shopping, and several other e-commerce applications. Hence, securing the web sites is becomes must do task in order to secure sensitive information of end users as well as organizations. Web log files are generated for each user whenever he/she navigates through such e-commerce websites, users every click is recorded into such web log files. The analysis of such web log files now a day’s done using concepts of data mining. Further results of this data mining techniques are used in many applications. Most important use of such mining of web logs is in web intrusion detection. To improve the efficiency of intrusion detection on web, we must have efficient web mining technique which will process web log files. In this project, our first aim is to present the efficient web mining technique, in which we will present how various web log files in different format will combined together in one XML format to further mine and detect web attacks. And because log files usually contain noisy and ambiguous data this project will show how data will be preprocessed before applying mining process in order to detect attacks. Hence mining process includes two parts, web log files preprocessing in order to remove the noise or ambiguous data mining process to detect the web attacks.
Keywords: Log Files, Web Mining, Preprocessing, IDS, XML, CRM.

Scope of the Article: Web Algorithms