Jawad Berri

Ontology-based framework for context-aware mobile learning

Mobile learning is becoming an important research topic as people are increasingly connected through smart phones that combine telephony, computing, messaging, and multimedia. The process of designing, communicating and presenting learning resources for mobile learners poses new challenges to the research community. This is mainly due to the limited bandwidth of wireless networks, limited resource available on mobile devices, and the special requirements of mobile learners. In this paper, an attempt is made to solve some of these problems by proposing an ontology-based framework for context-aware mobile learning. The system consists mainly of a rule-based ontology and a search agent. The rule-based ontology component is driven by the learner profile to contextualize learning content accordingly. The goal is to extract from a source ontology a lightweight target ontology by firing a set of rules based on the learner profile. The extracted conceptual knowledge is then mapped to a set of learning objects that meet the technical requirements of the used mobile technology. The mapping is geared by a search agent that searches a set of distributed learning objects repositories for feasible lightweight learning objects.

Time-dependent learning

Traditional learning systems work offline. Their output acquired after some unknown long time delay is a comprehensive instruction. However, the utility of such knowledge reduces in a time-constrained environment where instruction has to be completed by a certain deadline. As learning material scale up and longer instruction times become common, knowledge acquisition become time-dependent and is increasingly acquired on the fly due to considerable changes in todays know-how economy requirements. In this paper, we propose a procedural tradeoff between the time allocated to an instruction and the quality of the corresponding knowledge volume.

Ontology based clinical decision support system for diabetes diagnostic

This paper presents a diagnosis and treatment recommendation system for diabetes. The system considers patient information, symptoms and signs, risk factors and lab tests and suggests a treatment plan according to the diabetes type as recommended by the Clinical Practice Guidelines (CPG). The work consisted in the acquisition, modeling and implementation of diabetes domain expertise from experts, the CPG and other sources to develop a domain ontology and a decision support system to handle the diabetes in an early stage. The proposed system uses an ontology to allow a standard representation of domain concepts and relationships and enable clinical knowledge sharing, update and reuse. The proposed ontology is designed and developed by OWL-DL, the rules are constructed by the Semantic Web Rule Language (SWRL) and executed by JESS inference engine.

Context reasoning for mobile systems

Reasoning about context is a cornerstone component of mobile systems. These systems are ubiquitous and need to adapt continuously to their surroundings in order to provide high quality interaction with users and to fit with their actual needs. Context-aware systems have emerged as a particular type of mobile systems that can understand the user requirements and accordingly personalize the interaction with the mobile system. Context-aware systems rely mainly on two components: i) a comprehensive context model to represent all the contextual elements surrounding the mobile system, and ii) a reasoning engine that runs a continuous context management process which gathers environment data from sensors and web services, checks the consistency of the context instance and finally updates it. In this paper we show the context model and describe the context reasoning process. The implementation of the system is then presented and illustrated through an example.

Web-Based Arabic Morphological Analyzer

This paper presents an Arabic morphological analyzer1 that is a component of an architecture which can process unrestricted text from Internet. The morphological analyzer uses an object-oriented model to represent the morphological rules for verbs and nouns, a matching algorithm to isolate the affixes and the root of a given word-form, and a linguistic knowledge base consisting in lists of words. The morphological rules fall into two categories: the regular morphological rules of the Arabic grammar and the exception rules that represent the language exceptions. The representation and the implementation of these rules and the matching algorithm are discussed in this paper.

Leveraging Web Information for E-Learning

Reusing web information to create instructional content is an important opportunity for e-learning. Web information is diverse and rich in content and can serve to a great deal the learning field if it is described and annotated semantically to fit educational purposes. Hypermedia web resources are particularly interesting as they promote the development of interactive and non-linear material for learning. Exploiting web resources to generate learning material for e-learning represents the key idea of the Web of Learning – a learning ecosystem build on the top of the existing web that makes use of existing web resources to fit learning purposes. The paper presents the Web of Learning architecture and a mobile learning system that creates instructional material on-demand. The system discovers and retrieves hypermedia resources based on semantic descriptions and reuse them to create learning objects that constitute the building blocks of learning material delivered to users.

M-learning activity-based context management

It is usually difficult to formally define and efficiently reason with the various contextual elements of the learner’s context space. The latter is multi-dimensional, heterogeneous and of complex structure. It is also not well known how to use context to predict the dynamic learner behavior. In this paper an attempt is made to solve some of these challenges. In particular, the paper contribution is a context-aware model capable of recognizing and coordinating learner’s goals and activities in order to map these activities onto available learning services and resources. This is achieved through a structured and flexible ontology formulation of context, based on context fusion and cooperation, and driven by the learner’s goals and activities. The proposed context reasoning and recognition process relies on three ontologies where semantic structures, often crossing semantic levels, are used by a semantic matchmaker that can perform reasoning for context-oriented service discovery and access.

A Framework for Ontology Instructional Design and Planning

Although several standards have come out to defi ne a common convention for learning object metadata defi nition and representation, knowledge and components embedded in most existing e-learning systems are far from being sharable and reusable. This is mainly due to the lack of a general framework for standard-based, ontology-aware courseware design and development. In this paper, we propose a new approach for developing ontology compliant learning objects. A set of ontology-based rules is applied for building ontology-aware learning material. The proposed e-learning environment is based on IEEE-LTSC LOM (Learning Object Metadata) standard. In this paper, the LOM is extended with ontology related metadata that provides common vocabulary for domain knowledge representation and conceptual information about embedded content. Thus, the use of ontology provides a great potential for exchanging learning material, facilitating collaborative learning, and effi ciently retrieving context-based information from learning object repositories available on the web.

Effective reuse and sharing of best teaching practices

The widespread use of computer technologies in education has reshaped the roles of instructors, who are encouraged to innovate interactive forms of technology‐supported instruction that promote participation and collaboration. This in turn engenders new experiences of teaching that need to be gathered and capitalized as teaching assets to be shared among communities of instructors. Among these experiences, best teaching practices (BTPs) are instructional practices accumulated in teaching that have been proven to work well, give good results, and can therefore be recommended as a model. Identifying and sharing best practices means duplicating successes which help instructors learn from each other and deliver better quality teaching. This paper presents a knowledge management framework for acquiring, coding, sharing, and reusing BTPs. To encourage instructors’ participation, the framework is based on peer scoring of BTPs, which stimulates contribution and interaction. The framework has been implemented as a knowledge portal that allows instructors to create, store, search, and share BTPs and to receive feedback and comments from other users, providing many useful functionalities and services to users as individuals and communities. The paper presents also a real‐life case study, lessons learned from using the system within a community of instructors, and a system evaluation of the effectiveness of reusing BTPs using the reuse effort and impact metrics.

Knowledge Management of Best Practices in a Collaborative Environment

Identifying and sharing best practices in a domain means duplicating successes, which help people, learn from each other and reuse proven practices. Successful sharing of best practices can be accomplished by establishing a collaborative environment where users, experts and communities can interact and cooperate. A detailed review of previous research in best practice knowledge management shows that existing models have focused on developing methodologies to manage best practices but most of them did not propose solutions towards the development of full-fledge systems that make use of technologies to allow effective sharing and reuse of best practices. This paper presents a life cycle model to manage expertise for communities of practice. The proposed model is implemented in the education field as a knowledge management system that promotes and values user’s contributions. We focus on the case of best teaching practice (BTP) as they develop instructor’s abilities and improve overall instruction quality in higher education. For this purpose, we developed a computer environment including a knowledge management system and a web portal to assist instructors in higher education in the creation, sharing and application of BTPs.