Anis Jedidi

The generic model for pervasive information system

The ubiquitous computing-also called pervasive computing-regroups the characteristic of mobile computing and the technique of context-awareness that are flexible, adaptable, and capable of acting autonomously on behalf of users. However, the pervasive computing introduces a variety of software, hardware and users engineering challenges. The pervasive computing modeling is a new research area. Indeed, we are interested in purposing methodology for modeling pervasive systems. This paper provides an overview of proposed generic model of pervasive information system. Also, we propose an instantiation process to validate this generic model. This purposed generic model represents the highest level of abstraction. It presents only the general concepts of pervasive system.

Topic and Thematic Description for Movies Documents

The descriptions of audiovisual documents used in the interrogation process should not be limited to the identification of some keywords selected from signal, or from the forms presented in the image. They should be however, extracted basically from the content whilst exploiting the knowledge conveyed in the document. In this context, the topic and thematic description represents important information from the content. This importance result from the effective presence of the documents’ content. Consequently, we concentrate efforts to propose a method that describe the theme and the topic of movies document based on the adaptation of the Latent Dirichlet Allocation (LDA) model by combining the textual and visual modalities from the pre-production movie document (Script) and from the superposed text in the image. The experiments results confirmed the interesting performance through two databases, namely, “Choi’s dataset” and our own created database from the Internet Movie Database Imdb (http://www.imdb.com/years2012/2013).

Automatic identification Genre of audiovisual documents

Identifying the Genre of an audiovisual document is among the major challenges for multimedia retrieval. Indeed, the lack of semantic metadata extraction makes these resources underused in the retrieval process. To overcome these difficulties, the extraction of semantic descriptions requires an analysis of the audiovisual documents content. The automation of the process of describing audiovisual documents is essential because of the richness and the diversity of the available analytical criteria. In this paper, we present a method that allows the identification of a semantic and automatic description from the content such as genre. We chose to describe the cinematic audiovisual documents based on the documentation prepared in the pre-production phase of films, namely synopsis. The experimental result on Imdb (Internet Movie Database) and the Wikipedia encyclopedia indicate that our method of genre detection is better than the result of these corpuses.

Semantic Web service and pervasive information system conceptual adaptation

Purpose One of the open questions is how to ensure the conceptual adaptation in the pervasive system. To answer this question, the authors needed to propose a generic model and a mechanism to describe this system and also need generic and semantic rules to ensure the adaptation. This paper aims to propose a model to describe the pervasive information system. Second, the authors suggest an approach to divide this model so as to describe each category of contextual information separately and ensure the adaptation in the pervasive system. Finally, the authors present examples of semantic rules executed in the pervasive system. Design/methodology/approach This paper proposes an approach to ensure the conceptual adaptation in the pervasive system. To do it, the authors proposed a model to design the pervasive system and used semantic Web services. They proposed to divide the model to six descriptions related to the pervasive system categories information. Findings Pervasive information system, conceptual adaptation, semantic Web services and OWL-S are presented in this paper. Originality/value The originality of this paper is presented in the purpose of the pervasive information system conceptual adaption in the pervasive system. In this, later, semantic Web services were used to ensure the adaptation by the adding of contextual information in the semantic Web service description.

Defining Semantic Relationships to Capitalize Content of Multimedia Resources

Existing systems or architectures hardly provide any way to localize sub-parts of multimedia objects (e.g. sub regions of images, persons, events…), which represents hidden semantics of resources. To simplify and automate discovering hidden connections between such resources, we describe and evaluate in this paper, an algorithm for creating semantic relationships between multimedia news resources, giving a contextual schema (represented in RDF) as a result. This latter, which could eventually be used under any retrieval system, is integrated in our main multimodal retrieval system.

Towards a Semantic Multi-modalities Description of Audiovisual Documents

The description of an audiovisual document represents a major challenge for multimedia retrieval. Indeed, the lack of descriptive metadata extraction makes these proliferated resources underused in the querying process. To overcome these difficulties, the extraction of the semantic metadata of the content and the different structures of an audiovisual document is required. In this paper, we present a method that enables an automatic description of audiovisual documents. This automatic process is mainly based on the use of a multitude of modalities for the description and modeling of audiovisual documents, the standardization of these descriptions in the MPEG-7 standard through its description definition language (DDL) and on the use of semantic web language to link between the audiovisual resources.

Pervasive Information Systems Adaptation Challenges

Initially,asignificantnumberofcontextualinformationcanbeemployedtodescribethepervasive system.Hence,todesignthistypeofsystem,thereisasternneedforanewinformationsystem. Unliketheclassicalinformationsystem,thenewsystemintegratesthemobiledevicescharacterized bydifferenthardwareandsoftwarecapacityandotherusefuldevices.Therefore,mostpervasive informationsystemdesignersprovidemechanismsandarchitecturestoeffectivelysave,recoverand submitthemostrelevantinformationtotheuserregardlessoflocation,timeandtheuser’sequipment which are independent of the network constraints. In this paper, the authors present a model to describethepervasiveinformationsystemthroughtheuseoftheexistingcontextualmodels.Inthe samecontext,theysuggestasemanticdescriptiontoadapttheuserstosixcategoriesofcontextual informationbytakingthesemantic-web-servicecreationasabasis.Finally,theypresentthesemantic rulesappliedtotheintendeddescriptionandnotificationsystemtovalidatetheserules. KeywoRdS Adaptation, Context, Design, OWL-S, Pervasive Information System, Web Service

Semantic / Fuzzy Information Retrieval System

In this paper, the authors present an overall description of their information retrieval system which makes a practical collaboration between Semantic Web and Fuzzy logic in order to have profit from their advantages in the information retrieval domain. Their system is dedicated for kids, for this reason the semantic/fuzzy collaboration materialized must be in the background of the information retrieval process because such category of users cannot certainly control semantic web technologies neither fuzzy logic commands. In this paper, the authors present the different services proposed by their system and how they use Semantic Web and Fuzzy logic to develop it. Evaluation tests of the system using universal measures show clearly its efficiency.

Semiotic Rules Generation and Inferences Reasoning for Movie Documents

With the rapid but still incomplete maturation of the information retrieval research related to multimedia document, the progress of a new solution requires the extraction of semantic information from the content. It should be however, not only extracted from the content but it should also present the different semiotics meaning conveyed in the content. In our work, we concentrate our efforts on the movie documents. In fact, the knowledge extracted separately can conceal the global vision on the sequence of events or analysis of history conveyed in a film. In this context, we are interested in this paper to generate relationships either between sub-parts of the same movie or between movies. Consequently, we propose an inference reasoning to build these relationships in order to reveal the hidden knowledge semantics of resources. These relationships are basically based on the semiotic description that poses a major challenge. A case study where we substantiate and prove the accurate performance of our proposed process is highlighted.

SPARQL Query Generation based on RDF Graph

Data retrieval is becoming more difficult due to the heterogeneity and the huge amount of Data flowing in the Web. On the other hand, novice users could not handle querying languages (e.g., SPARQL) or knowledge based techniques. To simplify querying process, we introduce in this paper, a proposal of automatic SPARQL query generation based on user-supplied keywords. The construction of a SPARQL query is based on the top relevant RDF sub-graph, selected from our RDF Triplestore. This latter rely on our defined semantic network and on our Contextual Schema both published in two different papers of our previous studies. We evaluate 50 queries by using three measures. Results show an F-Score of about 50%. This proposal is already implemented as a web interface and the whole queries interpretation and processing is performed over this interface.