Sofiane Labidi

Subvocal Speech Recognition Based on EMG Signal Using Independent Component Analysis and Neural Network MLP

The performance of speech recognition systems is commonly degraded by either speech-related disabilities or by real-world factors such as the environmentpsilas noise level and reverberation. In this work, we propose a subvocal speech recognition system based on EMG signal for subvocal acquisition, Independent Component Analysis (ICA) for feature extraction and Neural Networks for classification. We have evaluated the systempsilas performance using a vowel phonemes database. The success rate was 93,99%.

Technology-assisted instruction applied to cooperative learning: the SHIECC project

This work is part of the SHIECC Project, whose aim is to design and implement a computer-supported collaborative learning environment applied to courses in engineering. The authors focus here on the conceptual model of the system; the present their agent-based architecture and propose new cooperative learning strategies to be applied within the cooperative learning sessions of SHIECC.

A semantic matching method for clustering traders in B2B systems

This is a part of the ICS (intelligent commerce system) project whose aim is to design and implement an effective intelligent B2B commerce system. We present a practical application on semantic Web and Web services concepts where a matching procedure to associate potential buyers and suppliers in a B2B system is shown and the use of patterns and tools in the development of semantic Webs structure is proposed as an alternative for its implementation.

Student modeling and semi-atutomatic domain ontology construction for SHIECC [atutomatic read automatic]

We are designing and implementing, within the SHIECC Project, a computer supported collaborative learning system applied to courses in engineering and mathematics. We address the problems of student modeling and knowledge domain construction within SHIECC. The proposed models have benefits of treating the specificity of cooperative learning and remedying the limitations of existing models.

Aprendizagem cooperativa e o problema de formação de grupos

Este trabalho apresenta o problema da divisao de uma classe de alunos em grupos para aprendizagem cooperativa sujeita a fatores pedagogicos. Propomos uma abordagem baseada em algoritmos geneticos para a formacao dos grupos no qual aplicamos os fatores de aceitacao de um grupo, pelo professor, baseada no perfil dos alunos e pela coesao do grupo, baseada no uso de tecnicas socio-metricas. Esta abordagem e usada no ambiente NetClass de ensino-aprendizagem cooperativa.

Information Filtering for a Collaborative Learning Environment: A Multiagent Approach

A multiagent filtering information system is proposed in this paper. The agents improve the teaching-learning process in a computer-based learning environment by means of information filtering. The system is developed using the PASSI agent development methodology. Furthermore, the paper describes agents specification and implementations for NetClass..

Inferring Socio-Affective Factors and Cooperation Capacity in Computer Assisted Collaborative Teaching/Learning Environments

Nowadays, socio-affective factors such as cooperation, motivation, socio-cognitive affinities, pro-activity, interaction and others, tend to be widely exploited in teacher/student and in between pupils relationship, so that the results of the building of knowledge be reached in a collaborative fashion. This is because these factors would play an encouraging role towards collaboration, acting positively in building human relationships within a socio-cultural panorama. Therefore, this work will show the importance of considering socio-affective factors in collaborative learning environments focusing on the relevant socio-affective factor that we designate as Collaboration Capacity, describing its manual and computed aided inference mechanisms. The rest of the relevant socio-affective factors quoted in this work, will be described and inferred along the course of the dissertation concluding research.

Mobile agents for information extraction in MathNet system

The authors proposed and designed, within the MathNet Project, a computer supported collaborative learning system applied to courses in Engineering and Mathematics. The MathNet artifact is one of the little software packages that implement effective collaborative learning paradigm. It offers new opportunities in education by integrating collaborative learning with computer, multimedia and network technologies in a manner that we believe will challenge traditional methods of pedagogy and benefit the learning process in a fundamental way. In this paper, the authors present the structure and architecture of an intelligent searching tool based on the learner profile and using the mobile agents technology applied in MathNet system. The learner profile will be used for the mobile search agents to obtain custom information. That information is used for help learners to answer their questions during the learning process. The intelligent search tool can be extended for use in other Interactive Learning Environments.

Sistema Inteligente de Desafios Abertos - IOCS : uma proposta de adaptação dos padrões do método clínico piagetiano em plataforma multiagentes

O Sistema Inteligente de Desafios Abertos (Intelligent Open Challenges System) - IOCS e uma proposta de adaptar em um sistema multiagentes alguns padroes do Metodo Clinico Piagetiano, em desenvolvimento pelo Laboratorio de Estudos em Linguagem, Interacao e Cognicao – LELIC/UFRGS e o Laboratorio de Sistemas Inteligentes – LSI/UFMA. Tem como caracteristicas funcionais simular o papel do Experimentador e ser um Objeto de Aprendizagem, ao ser re-utilizado por outras plataformas. E constituido por tres partes principais: o Sistema, o Usuario e o Agente Estrategista, realizando a mediacao entre o sistema e o usuario. Este Sistema tem como proposta trabalhar a aprendizagem por meio da aplicacao de desafios constituidos de provas logico-matematicas de concepcao aberta construidas de acordo com os exames de Piaget, preocupando-se em reconhecer e registrar, as razoes do usuario ante a solucao encontrada, alem de dar visibilidade aos processos cognitivos em curso, desencadeados nao apenas pelo desafio em si, mas pelo proprio dialogo, nos termos do Metodo Clinico, estabelecido pelos agentes com o usuario, permitindo a visualizacao do relacionamento entre os processos mentais cognitivos, possibilitando um suporte a docencia e a formacao continuada em ambientes informatizados.

Increasing matchmaking semantics in intelligent commerce system

This work is part of the ICS (intelligent commerce system) project whose aim is to design and implement an effective intelligent B2B commerce system. We present a practical application of semantic Web and Web services concepts where a matching procedure to associate potential buyers and suppliers in an B2B system is shown and the use of patterns and tools in the development of semantic Webs structure is proposed as an alternative for its implementation.