Kun Hua Tsai

A service-based framework for personalized learning objects retrieval and recommendation

With vigorous development of Internet, especially the web page interaction technology, distant e-learning has become more and more realistic and popular. To solve the problems of sharing and reusing teaching materials in different e-learning systems, presently several standard formats, including SCORM, IMS, LOM, and AICC, etc., have been proposed by several different international organizations. SCORM LOM, i.e. the Learning Object Metadata, enables the indexing and searching of learning objects in a learning object repository by extended sharing and searching features. However, LOM is deficient in semantic-awareness operations in spite of its multifarious fields in describing a Learning Object. It is difficult for a learner, even for advanced learners, to completely specify so many terms when they are searching. This paper proposes a service-based framework for personalized learning objects retrieval and recommendation. The work of personalization harnesses the power of probabilistic semantic inference for query keywords, LOM-based user preference logging, and other users’ feedback for recommendation weighting to retrieve the most suitable learning object for users. An ontology-based query expansion algorithm and an integrated learning objects recommendation algorithm are also proposed.

An Ontological Approach for Semantic Learning Objects Interoperability

This paper presents a semantic-aware classification algorithm that can leverage the interoperability among semantically heterogeneous learning object repositories using different ontologies. The proposed algorithm is to map sharable learning objects, using meanings instead of just keyword matching, from heterogeneous repositories into a local knowledge base (an e-learning ontology). Significance of this research lies in the semantic inferring rules for learning objects classification as well as the full automatic processing and self-optimizing capability. This approach is sufficiently generic to be embedded into other e-learning platforms for semantic interoperability among learning object repositories. Focused on digital learning material and contrasted to other traditional classification technologies, the proposed approach has experimentally demonstrated significantly improvement in performance.

A two-layer cryptographic scheme for an e-service framework based on mobile agents

We present an e-service framework, designed in allusion to the service-on-demand concept, for the next generation service-based Internet applications. A two-layer cryptographic security infrastructure is laid in the e-service framework for secured services. By separating the service functionality from its operating medium, the framework successfully prevents many security hazards from happening. It also offers a most desirable benefit to both service providers and users. For service providers, deployment of a service is as easy as inserting a plug-n-play interface card and for service users, using a service is as easy as filling out a downloaded form. The main goal of this framework is to offer a total solution for providing and using secured services easily instead of programming for services hardly.

Using Comprehensive Memory Cycle Updating in Extensive Reading

English is a global language and thus learning it is important in many contexts. One way to approach this learning task is to undertake extensive reading of English texts. However, if students have an inadequate vocabulary, it is difficult for them to select appropriate articles to read. To address this problem, a number of studies have applied the theory of the memory cycle to help learners memorize words more efficiently. However, the method is inefficient when it just uses to update the memory cycle of the target words directly. In this work we propose a new framework, comprehensive memory cycle updating, which can not only update the memory cycle of the word directly, but also can update the memory cycle indirectly via learner response. This framework can reduce the number of times a learner needs to review a word in order to memorize it. In addition, by adopting the concept of the memory cycle, this framework can find articles, which contain words that the learners have already learned, as well as those they have almost forgotten.

A Discrete Particle Swarm Optimization Based Approach for Review Course Composition

In the present learning cycle, new knowledge learning and known knowledge review are two important learning processes. This paper proposes the review course composition system which adopts the discrete particle swarm optimization to quickly pick the suitable materials, and can be customized in accordance with the learners intention. As a result, such a composition system satisfies the majority of learners with the customized review courses based on their needs.