Florence Sèdes

A Semantic-Oriented Approach for Organizing and Developing Annotation for E-Learning

This paper presents a solution to extend the IEEE LOM standard with ontology-based semantic annotations for efficient use of learning objects outside Learning Management Systems. The data model corresponding to this approach is first presented. The proposed indexing technique for this model development in order to acquire a better annotation of learning resources is further presented. This technique extends and combines two consecrated alternative methods for structure-based indexing of textual resources: the mathematical approach of the latent semantic indexing and the linguistic-oriented WordNet-based text processing. Thus, the reason behind the good results provided by the first method becomes more transparent due to the linguistic controlled choices proposed by the second method. The paper results are important in the context of adopting semantic web technologies in the e-learning field, but also as a progress in the area of ontology-based indexing of textual resources.

A community-based algorithm for deriving users’ profiles from egocentrics networks: experiment on Facebook and DBLP

Nowadays, social networks are more and more widely used as a solution for enriching users’ profiles in systems such as recommender systems or personalized systems. For an unknown user’s interest, the user’s social network can be a meaningful data source for deriving that interest. However, in the literature very few techniques are designed to meet this solution. Existing techniques usually focus on people individually selected in the user’s social network and strongly depend on each author’s objective. To improve these techniques, we propose using a community-based algorithm that is applied to a part of the user’s social network (egocentric network) and that derives a user social profile that can be reused for any purpose (e.g., personalization, recommendation). We compute weighted user’s interests from these communities by considering their semantics (interests related to communities) and their structural measures (e.g., centrality measures) in the egocentric network graph. A first experiment conducted in Facebook demonstrates the usefulness of this technique compared to individual-based techniques and the influence of structural measures (related to communities) on the quality of derived profiles. A second experiment on DBLP and the author’s social network Mendeley confirms the results obtained on Facebook and shows the influence of the density of egocentrics network on the quality of results.

Querying a hypertext information retrieval system by the use of classification

Abstract We present in this paper a navigation approach using a combination of functionalities encountered in classification processes, Hypertext Systems and Information Retrieval Systems. Its originality lies in the cooperation of these mechanisms to restrict the consultation universe, to locate faster the searched information, and to tackle the problem of disorientation when consulting the restricted Hypergraph of retrieved information. A first version of the SYRIUS system has been developed integrating both Hypertext and Information Retrieval functionalities that we have called Hypertext Information Retrieval System (H.I.R.S.). This version has been extended using classification mechanisms. The graphic interface of this new system version is presented here. Querying the system is done through common visual representation of the database Hypergraph. The visualization of the Hypergraph can be parameterized focusing on several levels (classes, links,...).

A personalized recommendation framework based on cam and document annotations

This paper presents a solution for recommending documents to students according to their current activity that is tracked in terms of semantic annotations associated to the accessed resources. Our approach is based on an existing tracking system that captures the user current activity, which is extended to build a user profile that comprises his/her interests in term of ontological concepts. A recommendation service is elaborated, implementing an algorithm that is alimented by Contextualized Attention Metadata (CAM) comprising the annotation of documents accessed by learners. The user profile is updated as soon as an activity is completed; thus, recommendations provided by the service are up-to-date in real time. The original aspect of this recommendation approach consists in combining a user activity tracking system with the exploitation of the semantic annotations associated with resources.

Managing and querying efficiently distributed semantic multimedia metadata collections

Currently, many multimedia contents are acquired and stored in real time and on different locations. In order to retrieve efficiently the desired information and to avoid centralizing all metadata, we propose to compute a centralized metadata resume, i.e., a concise version of the whole metadata, which locates some desired multimedia contents on remote servers. The originality of this resume is that it is automatically constructed based on the extracted metadata. In this paper, we present a method to construct such resume and illustrate our framework with current Semantic Web technologies, such as RDF and SPARQL for representing and querying semantic metadata. Some experimental results are provided in order to show the benefits of indexing and retrieving multimedia contents without centralizing multimedia contents or their associated metadata, and to prove the efficiency of a metadata resume.

A Contribution to Multimedia Document Modeling and Querying

Metadata on multimedia documents may help to describe their content and make their processing easier, for example by identifying events in temporal media, as well as carrying descriptive information for the overall resource. Metadata is essentially static and may be associated with, or embedded in, the multimedia contents. The aim of this paper is to present a proposal for multimedia documents annotation, based on modeling and unifying features elicited from content and structure mining. Our approach relies on the availability of annotated metadata representing segment content and structure as well as segment transcripts. Temporal and spatial operators are also taken into account when annotating documents. Any feature is identified into a descriptor called “meta-document”. These meta-documents are the basis of querying by adapted query languages.

A Contribution to Multimedia Document Modeling and Organizing

This paper presents a solution to resolve the problem of multimedia documents collection reorganizing. This solution is based on a documentary warehouse enriched by metadata (for each media type) elicited, modeled and structured in XML meta-documents. To homogenize these meta-document representation, we based our annotation on a document indexing and segmentation process.The warehouse thus created is seen as the hyperbase to which the user will apply personalization and querying mechanisms. The personalization enables dynamic re-structuring and re-construction of documents answering to the user queries. This approach is based on the OOHDM methodology extension with the use of the metadata.

Enriching the spatial reasoning system RCC8

One of the necessary basic concepts for the spatial data analysis in GIS is to determine the spatial relations between arbitrary geographical objects. In a two-dimensional space (IR2), most existing topological models can distinguish the eight topological relations between two spatial regions A and B. These eight relations are written in the traditional form of the spatial reasoning system RCC8: DC, EC, EQ, PO, TPP, TPPi, NTPP and NTPPi. Because of the complexity of topological relations between geographic regions, it is difficult for these models to describe in detail the topological relations by defining the separation number of lines and points that characterize these relations, and which is very important to enrich the spatial relations of system RCC8. To overcome the insufficiency in existing models, the extension of the Intersection and Difference (ID) model has the ability to describe in detail the topological relations of system RCC8. In our study, we focus our work on the four relations EC, PO, TPP and TPPi which can be described by the boundary-boundary intersection operator ∂A∩∂B. The main contributions are these four detailed relations which are written and described in the general form ECmL, nP, kR, POmL, nP, jRI, kR, TPPmLT, nPT, kR and TPPimLT, nPT, kR. Then, we develop definitions for the generalization of these detailed relations. Finally, examples are provided to illustrate the generalization of these new detailed spatial relations.

Adaptive Solutions for Access Control within Pervasive Healthcare Systems

In the age of mobile computing and distributed systems, healthcare systems are employing service-oriented computing to provide users with transparent accessibility to reach their distributed resources at anytime, anywhere and anyhow. Meanwhile, these systems tend to strengthen their security shields to ensure the limitation of access to authorized entities. In this paper, we examine mobile querying of distributed XML databases within a pervasive healthcare system. In such contexts, policies - as XACML - are needed to enforce access control. We study the reactivity of this policy in the case of a user demanding access to unauthorized data sources showing that the policy will respond negatively to user demands. Thus, we propose to employ an adaptive mechanism that would provide users with reactive and proactive solutions. Our proposal is accomplished by using the RBAC scheme, the user profile and some predefined semantics in order to provide users with alternative and relevant solutions without affecting the systems integrity.

Social collaborative service recommendation approach based on user’s trust and domain-specific expertise

A few years ago, the Internet of (Web) Service vision came to offer services to all aspects of life and business. The increasing number of Web services make service recommendation a directive research to help users discover services. Furthermore, the rapid development of social network has accelerated the development of social recommendation approach to avoid the data sparsity and cold-start problems that are not treated very well in the collaborative filtering approach. On the one hand, the pervasive use of the social media provides a big social information about the users (e.g., personnel data, social activities, relationships). Hence, the use of trust relation becomes a necessity to filter and select only the useful information. Several trust-aware service recommender systems have been proposed in literature but they do not consider the time in trust level detection among users. On the other hand, in the reality, the majority of users prefer the advice not only of their trusted friends but also their expertise in some domain-specific. In fact, the taking into account of user’ s expertise in recommendation step can resolve the user’ s disorientation problem. For these reasons, we present, in this paper, a Web service decentralized discovery approach which is based on two complementary mechanisms. The trust detection is the first mechanism to detect the social trust level among users. This level is defined in terms of the users’ interactions for a period of time and their interest similarity which are inferred from their social profiles. The service recommendation is the second mechanism which combines the social and collaborative approaches to recommend to the active user the appropriate services according to the expertise level of his most trustworthy friends. This level is extracted from the friends’ past invocation histories according to the domain-specific which is known in advance in the target user’s query. Performance evaluation shows that each proposed mechanism achieves good results. The proposed Level of social Trust (LoT) metric gives better precision more than 50% by comparing with the same metric without taking into account the time factor. The proposed service recommendation mechanism which based on the trust and the domain-specific expertise gives, firstly, a RMSE value lower than other trust-aware recommender systems like TidalTrust, MoleTrust and TrustWalker.Secondly, it provides a better response rate than the recommendation mechanism which based only on trust with a difference equal to 4%.