Amar Balla

Learners' navigation behavior identification based on trace analysis

Identifying learners’ behaviors and learning preferences or styles in a Web-based learning environment is crucial for organizing the tracking and specifying how and when assistance is needed. Moreover, it helps online course designers to adapt the learning material in a way that guarantees individualized learning, and helps learners to acquire meta-cognitive knowledge. The goal of this research is to identify learners’ behaviors and learning styles automatically during training sessions, based on trace analysis. In this paper, we focus on the identification of learners’ behaviors through our system: Indicators for the Deduction of Learning Styles. We shall first present our trace analysis approach. Then, we shall propose a ‘navigation type’ indicator to analyze learners’ behaviors and we shall define a method for calculating it. To this end, we shall build a decision tree based on semantic assumptions and tests. To validate our approach, and improve the proposed calculation method, we shall present and discuss the results of two experiments that we conducted.

Indicators for Deducting the Learners' Learning Styles: Case of the Navigation Typology Indicator

Research in individual differences and in particular, learning and cognitive style, has become a basis to consider learner preferences in a web-based educational context. How learner’s learning style influences his/her navigation behavior has been investigated by several studies, which indicate that we can deduce the learning style from the navigation behavior. In this paper, we propose an indicator of “navigation typology”. We detail the way in which this indicator is calculated, based on tracks analysis, which are aggregated into low and intermediate level indicators to determine the value of the navigation typology.

Efficient distributed discovery and composition of OWL-S process model in P2P systems

AbstractSemantic Web services (SWs) has become the most dominant paradigm of the service-oriented computing and one of the hot issues in the area of distributed computing technology to perform business services composition more efficiently and effectively for a number of years now. The distributed composition of SWs according to their functionality increases the capability of an application to fulfill the user’s requirements. In this paper, we describe an efficient approach for improving the performance and effectiveness of automatic and cooperative composition of SWs in P2P systems. It implements a distributed solution based on scalable epidemic algorithm to discover and compose SWs in P2P systems. The main idea of our approach is to develop hybrid matching technique that operates on OWL-S process models in order to ensure high recall, further reduce the number of messages exchanged and reduce the execution time for discovering and composing SWs in the P2P network. Moreover, our matching technique is able to detect complex matching between these SWs based on their parameters and the user request. We propose a similarity measure that will be used to compose new discovered and heterogeneous collaborative Web services of large-scale distributed systems in a P2P network for satisfying user requirements, and to rank the results according to a similarity score expressing the affinities between each of them and a user-submitted query. The experimental results show that our approach is efficient and able to reduce considerably the execution time and message overhead, while preserving high levels of the distributed discovery and composition of SWs on large-size P2P networks.

Ranked Matching of OWL-S Process Model for Distributed Discovery of SWs in P2P Systems

Semantic Web services (SWs) and P2P computing have emerged as new paradigms for solving complex problems by enabling large-scale aggregation and sharing of distributed computational resources. In this paper, we present a scalable approach based on epidemic discovery algorithm to discover new distributed and heterogeneous collaborative applications of large-scale distributed systems in a P2P network, and to rank the results according to a similarity score expressing the affinities between each of them and a user-submitted query. In order to reduce the execution time and improve the applicability of the epidemic discovery algorithm for discovering SWs, we propose the matching of ontology OWL-S process model in the heart of this algorithm which reduces the search space while keeping an acceptable matching quality level. Moreover, our matching approach is able to detect complex mappings between OWL-S process models based on their parameters. Experiments showed that the matching technique reduces considerably the execution time, maintaining at the same time a good quality of the distributed discovery of SWs in a P2P network.

Detection of Learning Styles from Learner's Browsing Behavior During E-Learning Activities

One of the bases of adaptation and learning tracking is the learners modeling. Research in this field, or more generally in the field of user modeling, was sustained mainly on the detection of features related to the users knowledge, interests, goals, background, and individual traits [3]. We are interested in this last aspect, in particular the identification of the learning style. In this paper, we propose an approach for the learners activity perception on an e-learning platform to identify the users learning styles from observable indicators related to their learning path and interactions.

Hybrid Ontology-Based Matching for Distributed Discovery of SWS in P2P Systems

Semantic Web services (SWs) paradigm is considered as the most dominant technology of the Service-Oriented Computing (SOC). SWs have emerged as a major technology for deploying automated interactions between distributed and heterogeneous applications. This computing technology can be used to discover new distributed and heterogeneous collaborative applications of large-scale distributed systems in P2P systems. In this paper, we present a scalable P2P approach for distributed discovery of SWs. In this approach, we define a distributed solution based on epidemic discovery algorithm to achieve a specific goal through the distributed discovery of SWs in P2P networks. In order to improve the applicability of the epidemic discovery algorithm for discovering SWs, we propose the matching of ontology OWL-S in the heart of this algorithm which reduces the search space while keeping an acceptable matching quality level. Our matching approach relies on the use of several similarity metrics. Moreover, our matching approach is able to detect complex mappings between activities based on their parameters of OWL-S.

HPS5DSWS: A Hybrid P2P Strategy of the Distributed Discovery Mechanism for Semantic Web Services

Web services are the new generation of distributed software components. They are important for deploying automated interactions between distributed and heterogeneous applications of large-scale distributed systems. But with the evolution of the number of services available on the Web, in organizations and their large-scale use, a discovery mechanism of such a Web service in a distributed and heterogeneous environment has become a real challenge. In this paper, we describe a scalable P2P approach for automatic discovery of Semantic Web services (SWs), which supports the complexity of both SWs and task. Our architecture is based on P2P technology that has proven its effectiveness and robustness as distributed system. The particularity of our approach is to place the alignment of OWL-S in the heart of this architecture.

Efficient P2P Approach for a Better Automation of the Distributed Discovery of SWs

In this paper, we present a scalable approach for visualizing and browsing the search space of available Web services to effectively and efficiently resolve the problem of distributed discovery for Semantic Web services (SWs). We investigate the use of matching technique of ontologies OWL-S, an approach to provide a collaborative mechanism to discover basic SWs distributed among all peers in a purely distributed and heterogeneous P2P network. Our scalable approach is based on the matching technique of OWL-S in order to reduce the time complexity of the distributed discovery for SWs with respect to their semantic similarity, to simplify the management of the P2P network, to optimize the ratio of service exchange and to ensure the quality of service. The network peers offer their SWs to other ones in a distributed and heterogeneous P2P computing, and are able to use distant services to improve system responses to requests by the system that are asked. The experimental results show that the proposed approach enhances the network scalability while providing good overall performances. Also, we show that our approach can perform more effective and efficient distributed discovery of SWs with low cost in P2P computing.

Adaptation Based on Navigation Type and Learning Style

In this paper, we present an adaptation approach of e-learning content based on the navigation type indicator describing the learner’s behavior while browsing an e-learning course. This adaptation approach benefits from the found correlation between this indicator and learning styles, particularly Sequential/Global and Active/Reflective styles. Many studies use leaning styles for adaptation based on educational rules. Thus, we propose for each value of the navigation type indicator, to provide the learner with the appropriate adaptation to the learning style correlated with the indicator value.

A Dynamic Model to enhance the Distributed Discovery of services in P2P Overlay Networks

In Service Computing (SC), online Semantic Web services (SWs) is evolving over time and the increasing number of SWs with the same function on the Internet, a great amount of candidate services emerge. So, efficiency and effectiveness has become a stern challenge for distributed discovery to tackle uniformed behavior evolution of service and maintain high efficiency for large-scale computing. The distributed discovery of SWs according to their functionality increases the capability of an application to fulfill their own goals. In this paper, we describe an efficient and an effective approach for improving the performance and effectiveness of distributed discovery of SWs in P2P systems. As most Web services lack a rich semantic description, we extend the distributed discovery process by exploiting collaborative ranking to estimate the similarity of a SWs being used by existing hybrid matching technique of OWL-S (Ontology Web Language for Services) process models in order to reduce costs and execution time. We mapped our distributed discovery of OWL-S process models by developing a real application based on Gamma Distribution; a technique used to decrease the bandwidth consumption and to enhance the scalability of P2P systems. The particularity of the Gamma Distribution is then integrated for disseminating request about the P2P networks to perform quality based ranking so that the best SWs can be recommended first. The experimental result indicates that our approach is efficient and able to reduce considerably the execution time and the number of message overhead, while preserving high levels of the distributed discovery of SWs on large-size P2P networks.