By Topic

Collaborative E-Learning for Remote Education; An Approach For Realizing Pervasive Learning Environments

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
C. Manikandan ; Madras Inst. of Technol., Chennai ; AS Meenakshi Sundaram ; M Mahesh Babu

Remote education in developing countries is a challenging task. Pervasive learning is "always on" education that is available anywhere, at any time. It is a social process connecting learners to communities of devices, people, and situations, so that learners can construct relevant and meaningful learning experiences, that they author themselves. Collaborative learning is one of the components of pervasive learning, the others being autonomy, location and relationship. It is an umbrella term for a variety of approaches in education that involve joint intellectual effort by students of similar caliber. Groups of students work together, to understand concepts, share ideas and ultimately succeed as a whole. Students of similar caliber can be identified by a formative assessment of their abilities. In a traditional learning system, students are graded using summative assessment based on marks by which the similarities of student can be identified. But using marks alone is fairly insufficient to evaluate the caliber of students. We make this possible by using formative assessment considering the factors such as prerequisite knowledge, memory capacity, interestedness, read amount, reading speed in addition to the marks scored by the students in their previous semester. We suggest using Web-mining techniques to evaluate students and use their results as inputs to clustering techniques. We derive various attributes of students from their browsing patterns. The link analysis Web mining technique is used for calculating the scores of the features proposed. The categorization of students having similar caliber is done using k-means clustering technique.

Published in:

2006 International Conference on Information and Automation

Date of Conference:

15-17 Dec. 2006