Laboratory of Modelization

Meknès, Morocco

Laboratory of Modelization

Meknès, Morocco
SEARCH FILTERS
Time filter
Source Type

Sael N.,Laboratory of Information Technology and Modelization | Marzak A.,Laboratory of Information Technology and Modelization | Behja H.,Laboratory of Modelization
International Review on Computers and Software | Year: 2012

Web usage mining is a complex process used to extract knowledge about the characterization of surfers who frequent a Web site and the identification of their navigation patterns. It's an emerging discipline, notably on e-learning domain, often referred to as educational data mining. In this paper, we propose the use of educational data mining techniques to analyze learners' behavior and how they exploit the contents of a given course. We are particularly interested in the preprocessing step which is considered the most crucial phase in the whole process. Based on Scorm course content, our work aims to develop an efficient preprocessing tool for elearning platform using Moodle logs. To be able to get more insights into the course exploitation, we suggest extracting the knowledge describing students' behavior in each part of this course content. © 2012 Praise Worthy Prize S.r.l.


Chakhmoune R.,Laboratory of Modelization | Behja H.,Laboratory of Modelization | Benghabrit Y.,Laboratory of Modelization | Marzak A.,Laboratory of Information Technology and Modelization
International Review on Computers and Software | Year: 2013

The goal of software development in today's industry is to provide products meeting customer requirements at the lowest cost, the best quality and the shortest time. Design knowledge is needed, and cases and developer's experiences should be utilized at most as possible. In addition, software development is becoming increasingly knowledge intensive and collaborative. In this situation, the need for an integrated know-how, know-why and know-what to support the representation, capture, share, and reuse of knowledge among distributed professional actors becomes more critical. Our approach consists in studying each stage of the process of software development and defining knowledge necessary to capitalize in order to organize the project memory based on domain ontology. Afterwards, the development of such knowledge base will be used to help professional actors to accomplish their task in bringing knowledge of past projects. © 2013 Praise Worthy Prize S.r.l. - All rights reserved.


Chbihi Louhdi M.R.,University Sidi Mohammed Ben Abdellah | Behja H.,Laboratory of Modelization | Ouatik El Alaoui S.,University Sidi Mohammed Ben Abdellah
International Review on Computers and Software | Year: 2013

Relational Databases (RDB) are used as the backend database by most of information systems. RDB encapsulate conceptual model and metadata needed in the ontology construction. Most of existing methods for ontology building from RDB suffer from limitations that prevent advanced database mining for having rich ontologies. In this paper, we propose a hybrid method for automatic ontology building from a RDB. It combines reverse engineering, schema mapping and data analysis techniques. The extracted ontology is refined by renaming the components whose names do not reflect their real meaning. Our method allows (1) recovering lost tables, during the mapping of ER-Model components to relations, by using reverse engineering technique, for the generalization and specialization cases; (2) transforming in the schema mapping phase, the different constructs and cases such as multiple inheritance, n-ary relations, etc.; (3) analyzing stored data to detect disjointness and totalness constraints in hierarchies, and calculating the participation level of tables in n-ary relations. In addition, our method is generic; hence it can be applied to any RDB. Finally, the proposed method was evaluated using two RDBs. The obtained results show that the built ontologies are richer in terms of extracted concepts, taxonomic relationships and ontology's depth. © 2013 Praise Worthy Prize S.r.l. - All rights reserved.

Loading Laboratory of Modelization collaborators
Loading Laboratory of Modelization collaborators