Mohamed Ben Ahmed

Towards an intelligent possibilistic web information retrieval using multiagent system

Purpose – The purpose of this paper is to make a scientific contribution to web information retrieval (IR).Design/methodology/approach – A multiagent system for web IR is proposed based on new technologies: Hierarchical Small‐Worlds (HSW) and Possibilistic Networks (PN). This system is based on a possibilistic qualitative approach which extends the quantitative one.Findings – The paper finds that the relevance of the order of documents changes while passing from a profile to another. Even if the selected terms tend to select the relevant document, these terms are not the most frequent of the document. This criterion shows the asset of the qualitative approach of the SARIPOD system in the selection of relevant documents. The insertion of the factors of preference between query terms in the calculations of the possibility and the necessity consists in increasing the scores of possibilistic relevance of the documents containing these terms with an aim of penalizing the scores of relevance of the documents no...

Arabic speech synthesis using a concatenation of polyphones: the results

This research paper is within the project entitled ”Oreillodule” : a real time embedded system of speech recognition, translation and synthesis The core of our interest in this work is the presentation of the hybrid system of the Arabic speech synthesis and more precisely of the linguistic and the acoustic treatment Indeed, we will focus on the grapheme-phoneme transcription, an integral stage for the development of this speech synthesis system with an acceptable quality Then, we will present some of the rules used for the realization of the phonetic treatment system These rules are stocked in a data base and browsed several times during the transcription We will also present the module of syllabication in acoustic units of variable sizes (phoneme, diphone and triphone), as well as the corresponding polyphones dictionary We will list the stages of the establishment of this dictionary and the difficulties faced during its development Finally, we will present the results of the statistical survey of understanding, achieved on a corpus.

Distributed blackboard architecture for multi-spectral image interpretation based on multi-agent system

For an interpretation system, a priori knowledge of the observed scene is necessary to identify objects and if necessary to determine their description. These objects are identified by comparing the extracted data from images to an a priori description of the object or object class. Therefore the use of an appropriate knowledge can efficiently reduce the complexity of matching image data to object descriptions due to different object classes, contexts and viewing conditions. Blackboard architectures are well suited to the task of selecting and applying the relevant knowledge to each situation as it is encountered. In this paper, we present a hierarchical approach based on the use of blackboard architecture and multiagent system and how to provide a convenient way for scene interpretation and modeling issued from a multispectral satellite image

An approach of a semantic annotation and thematisation of AV documents

In this work, we propose an approach of thematisation of audiovisual (AV) documents for a research according to topics evoked in each document. The first step of our approach is to define the descriptive metadata allowing a bibliographical description of the whole documents. The second step is divided into three stages: the first one is a temporal segmentation, the second one is space segmentation and the last is a semantic thematized description. Topics are modeled by classes of annotations such as (person, event, site and activity, etc.) and their instances (such as an event political, sporting, and cultural, etc.). In order to illustrate our work of semantic annotation we used platform ADVENE. This one will create semantic annotations by video and thereafter generating hypervideos for an active reading. This platform thus makes practices of thematized reading it possible. After this experiment, we will see to which extent and by which means our solution of thematisation, will give a better search of heterogeneous audiovisual documents.

Usage-Oriented Topic Maps Building Approach

In this paper, we present a collaborative and incremental construction approach of multilingual Topic Maps based on enrichment and merging techniques. In recent years, several Topic Map building approaches have been proposed endowed with different characteristics. Generally, they are dedicated to particular data types like text, semi-structured data, relational data, etc. We note also that most of these approaches take as input monolingual documents to build the Topic Map. The problem is that the large majority of resources available today are written in various languages, and these resources could be relevant even to non-native speakers. Thus, our work is driven towards a collaborative and incremental method for Topic Map construction from textual documents available in different languages. To enrich the Topic Map, we take as input a domain thesaurus and we propose also to explore the Topic Map usage which means available potential questions related to the source documents.

CITOM: incremental construction of topic maps

This paper proposes the CITOM approach for an incremental construction of multilingual Topic Maps. Our main goal is to facilitate the users navigation across documents available in different languages. Our approach takes into account three types of information sources: (a) a set of multilingual documents, (b) a domain thesaurus and (c) all the possible questioning sources such as FAQ and users or experts requests about documents. We have been validating our approach with a real corpus from the sustainable construction domain.

State of the Art on Topic Map Building Approaches

Topic Maps standard (ISO-13250) has been gradually recognized as an emerging standard for information exploration and knowledge organization. One advantage of topic maps is that they enable a user to navigate and access the documents he wants in an organized manner, rather than browsing through hyperlinks that are generally unstructured and often misleading. Nowadays, the topic maps are generally manually constructed by domain experts or users since the functionality and feasibility of automatically generated topic maps still in progress. In this paper, we give an overview of Topic Map building approaches. These approaches take as input different data types: structured documents, structured knowledge, unstructured documents and semi-structured data, and propose different techniques to build a Topic Map such as merging, mapping from RDF to TM and learning techniques. Some other research works are dedicated to cooperative Topic Map building and another research area deals with automatic generation of TM from XML documents.

Towards an intelligent approach based on multi-agent system and cellular automata for modeling land use change

In the recent years, new forms of simulation based on multispectral satellite imagery have come into popular use in geography and social science offering a significant potential for understanding the change of land use and land cover. Models and simulation issued can be characterized by an innovative approach to model dynamic and complex landscapes especially in urban phenomena. Recently, cellular automata have found their way in statistical and theoretical applications specially for modeling dynamic and complex phenomena. In an urban context, models based on cellular automata can provide valuable tools for planning and exploring urban scenarios issued from land use policies. The urban development can be represented as a self-organizing system temped by controls and constraints to pattern the urban process

Analyzing satellite image with blind separation of sources, knowledge based system and fusion of multisource images

In this paper, an intelligent satellite image analysis is proposed from blind source separation (BSS) method, knowledge based system and fusion of multisource images. The experimental results demonstrate that the proposed hybrid method provides an effective intelligent technique for remotely sensed images classification. This approach is validated on optical images of the satellite SPOT4 and radar images of the satellite ERS2 acquiring on the central Tunisian region for five classes of land.

Ontologies for Dynamic Modeling of Genetics Regulatory Networks

A Genetic Regulatory Network (GRN) is a collection of DNA segments in a cell which interact with each other and with other substances in the cell, thereby governing the rates at which genes in the network are transcribed into mRNA. Dynamic modeling of GRNs consists in modeling these networks in both space and time. It allows predicting the functional robustness of these networks against variations of internal and external parameters. Ontologies are powerful tools to make dynamic modeling of GRNs. In this paper we propose an approach based on ontologies for dynamic modeling of GRNs. We have experimented our approach on the ABC model of the flower development of Arabidopsis Thaliana plant. Our approach enables to cluster Arabidopsis Thaliana genes into functional entities (genes responsible for salt resistance and genes responsible for ultra violet rays resistance).