• [Conférence intertnationale] Nouha Dammak et Yassine Ben Ayed. Indexing and Classifiying Video Genres using Support Vector Machines. 12th ACS/IEEE International Conference on Computer Systems and Applications AICCSA 2015, novembre, 2015, Marrakech, Maroc

    In this paper, classifying and indexing hierarchical video genres using Support Vector Machines (SVMs) are based on only audio features. In fact, segmentation parameters are extracted at block levels, which have a major benefit by capturing local temporal information. The main contri-bution of our study is to present a powerful combination between the two employed audio descriptors; Mel Fre-quency Cepstral Coefficients (MFCC) and signal energy in order to classify a big YouTube dataset that includes multi-Arabic dialects video genres and even sub-genres: several sports analysis and various matches categories (foot-ball, basket-ball, hand-ball and volley-ball), both studio and fields news scenes over and above various multi-singer and multi-instruments music clips. Validation of this approach was carried out on over 18 hours of video span yielding a classification accuracy of 98,5% for ge-nres, 97% for sports sub-genres and 76% for music sub-genres. Finally we discuss SVM kernels performance on our proposed dataset.

  • [Journal] Yousri Kessentini, Thierry Paquet, Laurent Heutte, clément chatelain et Simon Thomas. A Deep HMM model for multiple keywords spotting in handwritten documents. , novembre, 2015, accepted in Pattern Analysis and Applications
  • [Conférence intertnationale] Achraf Mtibaa, Taher LABIDI et Faiez Gargouri. Modèle exhaustif à base d’ontologie pour le SLA dans le Cloud Computing. Les cinquièmes Journées Francophones sur les Ontologies JFO 2014, novembre, 2015, Conférence, Nabeul, Tunisie
  • [Conférence intertnationale] Ahmed Rekik, Achraf Ben-Hamadou et Walid Mahdi. Unified system for visual speech recognition and speaker identification. ACIVS 2015, octobre, 2015, Catania, Italie
    This paper proposes a unified system for both visual speech
    recognition and speaker identification. The proposed system can handle
    image and depth data if they are available. The proposed system consists
    of four consecutive steps, namely, 3D face pose tracking, mouth region
    extraction, features computing, and classification using the Support Vector Machine method. The system is experimentally evaluated on three
    public datasets, namely, MIRACL-VC1, OuluVS, and CUAVE. In one
    hand, the visual speech recognition module achieves up to 96 % and
    79.2 % for speaker dependent and speaker independent settings, respectively. On the other hand, speaker identification performs up to 98.9 %
    of recognition rate. Additionally, the obtained results demonstrate the
    importance of the depth data to resolve the subject dependency issue.
  • [Conférence intertnationale] Ahmed Rekik, Achraf Ben-Hamadou et Walid Mahdi. Human Machine Interaction via Visual Speech Spotting. ACIVS 2015, octobre, 2015, Catania, Italie
    In this paper, we propose an automatic visual speech spotting system adapted for RGB-D cameras and based on Hidden Markov
    Models (HMMs). Our system is based on two main processing blocks,
    namely, visual feature extraction and speech spotting and recognition.
    In feature extraction step, the speaker’s face pose is estimated using a
    3D face model including a rectangular 3D mouth patch used to precisely
    extract the mouth region. Then, spatio-temporal features are computed
    on the extracted mouth region. In the second step, the speech video is
    segmented by finding the starting and the ending points of meaningful
    utterances and recognized using Viterbi algorithm. The proposed system
    is mainly evaluated on an extended version of the MIRACL-VC1 dataset.
    Experimental results demonstrate that the proposed system can segment
    and recognize key utterances with a recognition rates of 83 % and a reliability of 81.4 %.
  • [Conférence intertnationale] Chihebeddine Ammar, Kais Haddar et Romary Laurent. Automatic Construction of a TMF Terminological Database Using a Transducer Cascade. RANLP2015, septembre, 2015, pages 17–23, Bulgarie
    The automatic development of terminological databases, especially in a standardized format, has a crucial aspect for multiple applications related to technical and scientific knowledge that requires semantic and terminological descriptions covering multiple domains. In this context, we have, in this paper, two challenges: the first is the automatic extraction of terms in order to build a terminological database, and the second challenge is their normalization into a standardized format. To deal with these challenges, we propose an approach based on a cascade of transducers performed using CasSys tool of the Unitex linguistic platform that benefits from both: the success of the rule-based approach for the extraction of terms, and the performance of the TMF standard for the representation of terms. We have tested and evaluated our approach on an Arabic scientific and technical corpus for the Elevator domain and the results are very encouraging.
  • [Conférence intertnationale] Mariem Ben Hassen, Mohamed Turki et Faiez Gargouri. Sensitive Business Process Modeling for Knowledge Management. International Conference on Database and Expert Systems Applications (DEXA’2015), septembre, 2015, Valencia, Espagne
  • [Conférence intertnationale] Yousri Kessentini et Thierry Paquet. Keyword spotting in handwritten documents based on a generic text line HMM and a SVM verification. International Conference on Document Analysis and Recognition (ICDAR 2015), aout, 2015
  • [Conférence intertnationale] Fadwa Yahya, Khouloud boukadi, Zakaria Maamar et Hanêne Ben Abdallah. Enhancing Business Processes with Web 2.0 Features. ICE-B 2015, juillet, 2015, Colmar, France
  • [Conférence intertnationale] Mohamed Kharrat, Anis Jedidi et Faiez Gargouri. A semantic approach for transforming XML data to RDF triples. 14th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2015, juillet, 2015, Las vegas, Etats-Unis

    We propose here a novel approach for extracting hidden semantic from semi-structured data resources and transformed to RDF triples, to be queried through semantic query languages. Unlike existing approaches that only explore the structure or use ontologies, we present a system that allows us to utilize all available information. Our approach constructs a semantically related data from XML represented in RDF via “semantic network” described here. These data could be queried by SPARQL/XQUERY or both simultaneously in multimodal way to perform a semantic search on a set of multimedia news resources.

  • Date de création : 19 Décembre 2012
    MIRADOC 2011 : Journées doctorales du laboratoire Miracl. Décembre 2011. Touzeur , Tunisie
  • Date de création : 19 Décembre 2012
    MIRADOC’2010, Rencontre Doctorale de Miracl Date : 19-22 décembre 2010. Lieu: Douz , Tunisie
  • Date de création : 19 Décembre 2012
    Les 2éme Journées sur les Réseaux Bayésiens et leurs Applications Date et lieu : octobre 2011, Sfax, Tunisie. Abstract The Bayesian Networks are graphical models that are easy to interpret and update. These models are useful if the knowledge is uncertain, but they lack some means to express ambiguity. To face this problem, we propose Fuzzy Evidence in Bayesian Networks and combine the Fuzzy Logic and Bayesian Network. This has allowed to benefit from mutual advantages of these two approaches, and to overcome the problem of data and observation ambiguity. This paper proposes an inference algorithm which uses the Bayesian Network and Fuzzy Logic reliability. This solution has been implemented, tested and evaluated in comparison with the existing methods.
  • Faiez Gargouri, Wassim Jaziri  Ontology Theory, Management and Design: Advanced Tools and Models ». IGI Global. ISBN-978-1-61520-   859-3. Mars 2010. Description Ontologies and formal representations of knowledge are extremely powerful tools for modeling and managing large applications in several domains ranging from knowledge engineering, to data mining, to the semantic web. Ontology Theory, Management and Design: Advanced Tools and Models, explores the wide range of applications for ontologies, while providing a complete view of the both the theory behind the design and the problems posed by the practical development and use of ontologies. This reference presents an in-depth and forward looking analysis of current research, illustrating the importance of this field and pointing toward to the future of knowledge engineering, management and information technology.  
  • Titre : Finite State Language Engineering Autheurs : BEN HAMADOU A., MESFAR S., SILBERZTEIN M.  ISBN : 978-9973-37602-2 Livre, Edition CPU, Tunis, 2010
  • Titre :  Les Systèmes décisionnels : Théorie et pratique Autheurs : BEN-ABDALLAH H., BOULMARKOUL A., BOUSSAID O., FEKI J., GARGOURI F. ISBN : 789973990020. Nombre des pages: 130 pages Livre, Nouha Editions, 2010.