Problem statement: Recently, Web usage mining techniques have been widely used to
build recommendation systems especially for anonymous users. Approach: Assigning the current user
to the best web navigation profile with similar navigation activities will improve the ability of the
prediction engine to produce a recommendation list then introduce it to the user. This study presents
iPACT an improved recommendation system using Profile Aggregation based on Clustering of
Transactions (PACT). Results: iPACT shows better prediction accuracy than the previous methods
PACT and Hypergraph. Conclusion: The users’ interests change over time; hence an incremental and
adaptive web navigation profiling is a key feature for the future works.

IPACT: Improved Web Page Recommendation System Using Profile Aggregation Based On Clustering of Transactions

Problem statement: Courseware is one of the educational aids in teaching and learning process. Nowadays, courseware together with multimedia elements is utilized to ease learners in grasping knowledge. However, the courseware for Visually-Impaired (VI) is yet to be developed. Approach: This study discusses the development of Assistive Courseware (AC) for visually impaired learners based on Theory of Multiple Intelligence (MI) and also adapt knowledge spiral model. It explains how the AC delivers knowledge to VI learners. The phases, design and development methods involved in the research are outlined. Results: Results showed that the AC is fully equipped with the eight types of MI theory and the use of SECI model in transferring knowledge between AC and VI learners has been proven. Conclusion: The AC has been proposed for the VI learners and observed on their reactions. Overall, the VI learners were vary positive upon the AC and was excited to learn with the AC. Next step of the study is not only to report on the findings from observation, but also to experiment the prototype with VI learners in terms of cognitive implications using empirical data.

Assistive Courseware for the Visually Impaired based on Theory of Multiple Intelligence and SECI Model

Original article can be found at : http://www.ejel.org/ Copyright Management Centre International Limited [Full text of this article is not available in the UHRA]

/pdf/an-automated-individual-feedback-and-marking-system-an-n1jir6o69e.pdf

An Automated Individual Feedback and Marking System: An Empirical Study.

Nowadays, Web based platforms are quite common in any university, supporting a very diversified set of applications and services. Ranging from personal management to student evaluation processes, Web based platforms are doing a great job providing a very flexible way of working, promote student enrolment, and making access to academic information simple and in an universal way. Students can do their regular tasks anywhere, anytime. Sooner or latter, it was expected that organizations, and universities in particular, begin to think and act towards better educational platforms, more user-friendly and effective, where students find easily what they search about a specific topic or subject. Profiling is one of the several techniques that we can use to discover what students use to do, by establishing their user navigation patterns on Web based platforms, and knowing better how they explore and search the sites" pages that they visit. With these profiles Web based platforms administrators can personalize sites according with the preferences and behaviour of the students, promoting easy navigation functionalities and better abilities to response to their needs. In this article we will present the application of Markov chains in the establishment of such profiles for a target eLearning oriented Web site, presenting the system we implemented and its functionalities to do that, as well describing the entire process of discovering student profiles on an eLearning Web based platform.

/pdf/discovering-student-web-usage-profiles-using-markov-chains-2ipc0izyb6.pdf

Discovering Student Web Usage Profiles Using Markov Chains.

Problem statement: The modern world is based on using physical, biological and social systems more effectively using advanced computerized techniques. A great amount of data being generated by such systems; it leads to a paradigm shift from classical modeling and analyses based on basic principles to developing models and the corresponding analyses directly from data. The ability to extract useful hidden knowledge in these data and to act on that knowledge is becoming increasingly important in today's competitive world. Approach: The entire process of applying a computer-based methodology, including new techniques, for discovering knowledge from data is called data mining. There are two primary goals in the data mining which are prediction and classification. The larger data involved in the data mining requires clustering and outlier analysis for reducing as well as collecting only useful data set. Results: This study is focusing the review of implementation techniques, recent research on clustering and outlier analysis. Conclusion: The study aims for providing the review of clustering and outlier analysis technique and the discussion on the study will guide the researcher for improving their research direction.

A Review on Clustering and Outlier Analysis Techniques in Datamining

Techniques which assist in recognizing various access patterns and interests of the Web
users are normally referred to as an application of Web usage mining. The application provides useful
insights to address crucial points such as user interests into a particular page, server load balancing,
Web site reorganization, clustering of similar browsing patterns, classification of user profiles, content
caching or data distribution and replication. In this study, we provide an updated focused survey of
major aspects and problems related to the task of modeling the user behavior. We also point out some
recent advancement in areas related to automatic Web navigation and implicit capturing of user
interests in regard to a particular page. Main future directions are also outlined in the conclusion.

/pdf/a-classification-of-techniques-for-web-usage-analysis-2ods6vjm04.pdf

A Classification of Techniques for Web Usage Analysis

With the introduction of Web-Based Instruction (WBI) the traditional classroom-based higher education could be made more effective form of instruction. But the studies have shown the negative results (1) . On the other hand the distance education has derived the direct benefit of WBI through extending classroom instruction in online to reach every remote student. However researchers have identified reasons for the lack of effectiveness of WBI in both classroom and distance education. WBI along with a suitable learning strategy is a tangible solution. As the learning strategy based entirely on the constructivists approach may not be feasible for the students with less or no experience our studies recommend a hybrid strategy called Integrating Multiple Learning Strategies (IMLS) that can be implemented to achieve the effect of e-Learning. This study presents the issues identified with the WBI-based learning paradigm and WebCT, various learning approaches and feasible e-Learning models around WebCT for IMLS approach.

/pdf/e-learning-under-webct-2914asblj5.pdf

E-Learning under WebCT

We introduce a visual framework for facilitating tasks associated with database maintenance and re-use. The prototype system embodying the framework is presented. The system utilizes various techniques and features of software visualization. The system supports visual displays of the database structure along with various implicit relationships found in it such as associations and path views. Information visualized is automatically extracted from the database schema. To assess the usefulness of the proposed framework in helping the programmers to quickly recognize path views among relations, an empirical evaluation was conducted. Results collected from the evaluation seem to support our hypothesis that the time required to manually recognize path views from the database schema is considerable and tends to increase as the depth between the relations increases. The evaluation also showed that by using our visual framework such time is negligible and tends to be static.

H. A. Ramadhan

Papers

A Classification of Techniques for Web Usage Analysis

E-Learning under WebCT

Automatic discovery of association paths in relational databases using software visualization