Search

International audience; The obsession with how the brain and behavior are related is a challenge for cognitive neuroscience research, for which functional magnetic resonance imaging (fMRI) has significantly improved our understanding of brain functions and dysfunctions. In this paper, we propose a novel multi-modal spatial cerebral graph based on an attention mechanism called MSCGATE that combines both fMRI modalities: task-, and rest-fMRI based on spatial and cerebral features to preserve the rich complex structure between brain voxels. Moreover, it attempts to project the structural-functional brain connections into a new multi-modal latent representation space, which will subsequently be inputted to our trace regression predictive model to output each subject’s behavioral score. Experiments on the InterTVA dataset reveal that our proposed approach outperforms other graph representation learning-based models, in terms of effectiveness and performance.

In this paper, we proposed an extension of the classical Conditionally Gaussian Observed Markov Switching Model (CGOMSM) by incorporating fuzzy switches. The proposed approach allows the modeling of transient switches and handles the discontinuity feature in switching regime models by using fuzzy switches instead of hard jumps. Fuzzy switched based approach is more adapted to real-world application in which regime continuity is an intrinsic property. To define an efficient scheme for an exact smoothing in CGOMFSM, we adapt fast smoothing equations to cope with the fuzzy model. Finally, we show through several experiments the interest of the fuzzy switches model.

International audience; The interpretation of satellite images in a spatiotemporal context is a challenging subject for remote sensing community. It helps predicting to make knowledge driven decisions. However, the process of land cover change (LCC) prediction is generally marred by imperfections which affect the reliability of decision about these changes. Propagation of imperfection helps improve the change prediction process and decrease the associated imperfections. In this paper, an imperfection propagation methodology of input parameters for LCC prediction model is presented based on possibility theory. The possibility theory has the ability to handle both aleatory and epistemic imperfection. The proposed approach is divided into three main steps: 1) an imperfection propagation step based on possibility theory is used to propagate the parameters imperfection, 2) a knowledge base based on machine learning algorithm is build to identify the reduction factors of all imperfection sources, and 3) a global sensitivity analysis step based on Sobol's method is then used to find the most important imperfection sources of parameters. Compared with probability theory, the possibility theory for imperfection propagation is advantageous in reducing the error of LCC prediction of the regions of the Reunion Island. The results show that the proposed approach is an efficient method due to its adequate degree of accuracy.

International audience; Real life problems can be solved by a distributed way, in particular by multi-agent approaches. However, the fault tolerance is not guarantee when an agent, for example, does not have any activity (e.g. it dies). This problem is very crucial, when the interactional model is based on a Distributed CSP. Many algorithms have been proposed in the literature, but they give wrong results if an agent dies. This paper presents an approach which is based on a replication principle: each local CSP is replicated in another agent.

International audience; Safety-critical applications require complete high-coverage testing, which is not always guaranteed by model-based test generation techniques. Recently, automatic test generation by model checking has been reported to improve the efficiency of test suites over conventional test generation techniques. This study introduces our novel tool SimAutoGen, which employs the model checking technique (as a formal verification technique) to derive test vectors from Simulink models of automotive controllers according to structural coverage metrics. Model checking based on test generation is challenging for two reasons. First, the input model to the model checker requires conversion into a formal language. Second, standard tools have limited ability to generate test vectors for large-scale Simulink models because the state-space explodes with increasing model size. Our proposed SimAutoGen avoids the first problem by expressing the properties to be verified, which correspond to a structural coverage metric, in the Simulink language. To solve the state-space explosion problem, we developed a new algorithm that slices the Simulink model into hierarchical levels.

International audience; In this paper, we describe a Web services recommendation approach where the services' ecosystem is represented as a heterogeneous multigraph, and edges may have different semantics. The recommendation process relies on clustering techniques to suggest services "of interest" to a user. Our approach has been implemented as a tool called WesReG (Web services Recommendation with Graphs) on top of Neo4j and its cypher query language. We present the system implementation details and present the results of experiments on a collection of real Web services.

International audience; Microblogs have proved their potential to attract people from all over the world to express voluntarily what is happening around them during unexpected events. However, retrieving relevant information from the huge amount of data shared in real time in these microblogs remain complex. This paper proposes a new system named MASIR for real-time information retrieval from microblogs during unexpected events. MASIR is based on a decentralized and collaborative multi-agent approach analyzing the profiles of users interested in a given event in order to detect the most prominent ones that have to be tracked in real time. Real time monitoring of these users enables a direct access to valuable fresh information. Our experiments shows that MASIR simplifies the real-time detection and tracking of the most prominent users by exploring both the old and fresh information shared during the event and outperforms the standard centrality measures by using a time-sensitive ranking model.

International audience; This paper presents a learning-based approach for the selection of relevant feature categories in the context of information retrieval from microblogs during unexpected disasters. Our information retrieval strategy consists of identifying prominent microblog users who are susceptible to share relevant and exclusive information in a disaster case. To identify these users, we evaluate the effectiveness of the state-of-the-art features characterizing microblog users for the identification of prominent users in a specific context. We experimented with a different sets of feature categories to determine those that discriminate prominent users sets from non-prominent ones interacting in Twitter during the 2014 Her-ault floods that occurred in France. The achieved results show that on-and off-topical user activities features are the most representative features for identifying prominent users in a disaster context. We also note that SVM outperforms the ANN learning algorithm for this classification context especially when it is trained with additional spatial features.