Amel Bouzeghoub

A Framework for the Generation of Adaptive Courses Based on Semantic Metadata

This approach proposes the creation and management of adaptive learning systems by combining component technology, semantic metadata, and adaptation rules. A component model allows interaction among components that share consistent assumptions about what each provides and each requires of the other. It allows indexing, using, reusing, and coupling of components in different contexts powering adaptation. Our claim is that semantic metadata are required to allow a real reusing and assembling of educational component. Finally, a rule language is used to define strategies to rewrite user query and user model. The former allows searching components developing concepts not appearing in the user query but related with user goals, whereas the last allow inferring user knowledge that is not explicit in user model.

A RDF description model for manipulating learning objects

Our claim is that semantic metadata are required to allow a real reusing and assembling of learning objects. Our system is based on three models used to describe the knowledge domain, users and learning objects. In order to automatically process these models and make available basic reasoning capabilities, we have defined mappings to RDF. A prototype is being developed using Sesame, an RDF tool that supports the declarative query language SeRQL. This paper focuses on RDF mappings definition and how to use SeRQL to achieve the functionality required by our approach.

Situation-Aware Adaptive Recommendation to Assist Mobile Users in a Campus Environment

Users in a campus need information about relevant individuals, buildings, events and available resources. In this paper, we propose a system to perform situation-aware adaptive recommendation of information to assist mobile users in a campus environment. The idea is to show information about the most relevant buildings and particular individuals situated nearby the user, taking into account the user situation, i.e., a snapshot of his/her context in a given instant, including his/her current activity, position and profile. This recommendation must be adapted, depending on the dynamic evolution of the user situation. Thus, the system is pervasive in the sense that it performs the most suitable recommendation at the right moment in the right place. A prototype of the recommender is being implemented.

A situation-based delivery of learning resources in pervasive learning

Pervasive learning systems must define new mechanism to deliver the right resource, at the right time, at the right place to the right learner. This means that rich context information has to be considered: time, place, user knowledge, user activity, user environment and device capacity. As context is based on numerous information which may change frequently (coming from a collection of captors), a more aggregate view is defined to work on more abstract objects: the situations. Context information and situation information have to be widespread into all the models of learning systems: context preferences have to be handled in the learner model, well-adapted situation and situation scenarios have to be memorized in learning resource model. The adaptation process is enriched too.

Test-bed building process for context-aware peer-to-peer information retrieval evaluation

With the rapid growth of information rate in the web, it is of paramount importance to develop scalable information retrieval approaches. These approaches are based on distributed information retrieval systems. Likewise, the emergence of contextual information retrieval has introduced the research personalisation which attempts to reduce the research ambiguity and to return most appropriate information to the user. Therefore, it seems a compelling issue, to implement techniques related to contextual peer-to-peer information retrieval (P2P-IR) to better exploit the personalisation of information in order to achieve a more efficient access to data. In this respect, evaluating these approaches in contextual P2P-IR is a crucial step. Indeed, to the best of our knowledge, there is no available test-beds dedicated to the evaluation of contextual P2P-IR. In particular, we propose, two methods. The first is based on existing collections that are enriched with external semantic resources. The second offers the possibility to build test-beds from multiple sources data.

Use cases of heterogeneous learning ontologies

The emergence of new repositories of learning resources based on semantic technology raises the problem of ontologies interoperability. Learning resources are described by a set of metadata which may use different ontologies as referential. To handle the increasing number of heterogeneous ontologies it becomes necessary to develop automatic mapping approach. In this paper we propose to study technical solutions for ontologies handling through two use cases: (1) the comparison between a current learner profile and a target profile and (2) the search of learning resources among distributed repositories.

Experiments in Ubiquitous Computing for Communities of Practice Using Learning Resources

We present in this paper the interest of ubiquitous computing for the so called contextualized forums. These forums allow communities of practice exchanging and sharing experiences or situations already lived by using learning documents to classify these exchanges. These forums contain a lot of information which contribute to improve classical training. We study here ubiquitous computing possibilities to use this type of forums in order to improve professional training to business process by helping the user to put his/her acquisition into practice. The developed application is being tested and works mainly on smartphones.

A fuzzy semantic CEP model for situation identification in smart homes

Uncertainty is an essential issue for smart home applications. Events generated from sensors can be outdated, inaccurate, imprecise or in contradiction with other ones. These unreliable data can lead to dysfunction in smart home applications. To tackle these challenges, we propose a new model named FSCEP (Fuzzy Semantic Complex Event Processing) that integrates fuzzy logic paradigm, semantic features through an ontology and traditional CEP. We confronted FSCEP with other works tackling uncertainty for CEP and experimented it through simulation with early but promising result

An Efficient Peer-to-Peer Semantic Overlay Network for Learning Query Routing

In unstructured P2P systems, peers organize themselves into a random overlay. A challenging problem in these systems is to efficiently locate appropriate peers to answer a specific query. Recently, research works have focused on methods based on query history, which use the historical information of past queries and query hits to build a local knowledge base per peer. When a peer forwards a given query, it runs a learning algorithm that evaluates the query against the local knowledge base in order to select a set of relevant peers to whom the query will be routed. If the current peer fails to select a sufficient number of relevant peers it floods the query through the random overlay network, which badly affects the routing efficiency and effectiveness. To address the unsuccessful relevant peers search problem, we propose to organize the P2P network into semantic clusters of peers sharing similar knowledge bases. We implemented the proposed approach, and tested (i) its retrieval effectiveness in term of recall and precision, (ii) its routing efficiency in term of messages traffic. Experimental results show that our approach improves the recall and precision metrics while it dramatically reduce network traffic.

LEAF: Using Semantic Based Experience to Prevent Task Failures.

Using service robots at home is becoming more and more popular in order to help people in their life routine. Such robots are required to do various tasks, from user notification to devices manipulation. However, in such complex environments, robots sometimes fail to achieve one task. Failing is problematic as it is unpleasant for the user and may cause critical situations. Therefore, understanding and preventing failures is a challenging need. In this paper, we propose LEAF, an experience based approach to prevent task failure. LEAF relies on both semantic context knowledge through ontology and user validation, allowing LEAF to have an accurate understanding of failures. It then uses this new knowledge to adapt a Hierarchical Task Network (HTN) in order to prevent selecting tasks that have a high risk of failure in the plan. LEAF was tested in the Hadaptic platform and evaluated using a randomly generated dataset.