Predicting the user navigation pattern from web logs using weighted support approach

<p class="Abstract"><span id="docs-internal-guid-f3d644ee-7fff-d3c1-15b5-f75fe28d3e2d"><span>A weblog contains the history of previous user navigation pattern. If the customer accesses any portal of organization website, the log is generated in web server, based on sequence of user transaction. The weblog stored in the web server as unstructured format, it contains both positive and negative responses i.e. successful and unsuccessful responses, identifying the positive and negative response is not useful for identifying user behavior of individual user. Initially the successful response is taken, from that conversion of unstructured log format to structured log format through data preprocessing technique. The process of data preprocessor contains three step process data cleaning, user identification and session identification. The pattern is discovered by preprocessing technique from that user navigation pattern is generated. From that navigation pattern classifier technique is applied, the conversion of sequence pattern to sub sequence pattern by clustering technique. This research is to identify the user navigation pattern from weblog. The Improved Spanning classification algorithm classifies the frequent, infrequent and semi frequent pattern. To identify the optimal webpage using classificatopn algorithm from thet user behavior is identified.</span></span></p>

User behaviour pattern for online learning system: UiTM iLearn portal case

<span>A Web server log files contain an entire record of the user’s browsing history such as referrer, date and time access, path, operating system (OS), browser and IP address. User navigation pattern discovery involves learning of user’s browsing behaviour to gain the pattern from web server log file. This paper emphasizes on identifying user navigation pattern from web server log file data of iLearn portal. The study implements the framework for user navigation including phases of acquisition of weblog, log query parser, preprocessor, navigational pattern modelling, clustering, and classification. This study is conducted in the context of the actual data logs of the iLearn portal of Universiti Teknologi MARA (UiTM). This study revealed the navigational patterns of online learners which relatively related to their intake or group along the semester of 14 weeks. Besides, access patterns for students along the semester are different and can be classified into three (3) quarter, namely Q1, Q2 and Q3 based on the total of week per semester. Future work will focus on the development of prototype to improve the security of online learning especially during the assessment progress such as online quiz, test and examination.</span>

Visualizing Pathway on 3D Maps for an Interactive User Navigation in Mobile Devices

3D maps have become an essential tool for navigation aid. The aim of a navigation aid is to provide an optimal route from the current position to the destination. Unfortunately, most mobile devices' GPS signal accuracy and the display of pathways on 3D maps in the small screen of mobile devices affects the pathway architectural from generating accurate initial positions to destinations. This chapter proposed a technique for visualizing pathway on 3D maps for an interactive user navigation aid in mobile devices. This technique provides visualization of 3D maps in virtual 3D workspace environments which assists a user to navigate to a target location. The Bi-A* path-finding algorithm was used for establishing dynamic target location in Voronoi diagram/Delaunay triangulation. This approach could navigate more than two users in a 3D walk-space and at the same time showing their whereabouts on 3D projections mapped. The map shows the users' location in the scene to navigate from source to the target and the target also moves to the source to meet on the same physical location and image plane.