Search

International audience; With the emergence of mobile devices (Smart Phone, PDA, UMPC, game consoles, etc.), and the growth of offers and needs of a company under formation in motion, multiply the work to identify relevant new learning platforms to improve and facilitate the process of distance learning. The next stage of distance learning is naturally the port of e-learning to new mobile systems. This is called m-learning (mobile learning). Because of the mobility feature, m-learning courses have to be adapted dynamically to the learner’s context. Several researches addressed this issue and implemented a mobile learning environment. In this paper, we compare a list of mobile learning architectures with methods presented in the literature. The evaluation presents a set of criteria specifically identified to qualify m-learning architectures dedicated to the context-change management.

International audience

Les documents électroniques (rapports, notes, articles...) évoluent et présentent des contenus de plus en plus riches et complexes. Ainsi, ils font l'objet de changements rapides a priori imprédictibles. Se pose alors le problème de détection de ces changements. En effet, il faut détecter les changements induits par les évolutions, en comparant les anciennes et les nouvelles versions des documents et en évaluant la similarité entre ces versions. Le besoin de pouvoir versionner et analyser ces documents augmente constamment, il convient donc de disposer des outils adéquats. Les entrepôts de documents présentent une solution d'intégration et d'historisation de ces documents. L'adjonction de l'aspect temporel dans ces entrepôts vise à proposer des solutions pour le versionnement des documents. L'objectif de cet article est de présenter et d'analyser l'état de l'art des travaux de recherche menés dans les entrepôts de documents XML. En particulier, il présente l'intégration de la notion du temps dans ce type d'entrepôts.

International audience; A Data Warehouse (DW) stores data coming from heterogeneous data sources at decisional ends. To query the stored data, there are specific operators, called OLAP operators which facilitate the analysis and the visualization of data. However, these operators, as they are defined in classic DW context, do not allow querying a MultiVersion Data Warehouse (MVDW) which takes account of the evolutions which can affect the members of dimension and/or the DW schema components. In order to appropriately analyze multiversion data, an extension to the traditional OLAP operator is required. In this paper, we propose a MVDW query language called MVOLAP. To this end, we extend the classic OLAP operators to adapt them to the MVDW context.

International audience; This paper describes our efforts to extend the PARSEME framework to Modern Standard Arabic. The applicability of the PARSEME guidelines was tested by measuring the inter-annotator agreement in the early annotation stage. A subset of 1,062 sentences from the Prague Arabic Dependency Treebank PADT was selected and annotated by two Arabic native speakers independently. Following their annotations, a new Arabic corpus with over 1,250 annotated VMWEs has been built. This corpus already exceeds the smallest corpora of the PARSEME suite, and enables first observations. We discuss our annotation guideline schema that shows full MWE annotation is realizable in Arabic where we get good inter-annotator agreement.

This article proposes a crisp-based approach for representing and reasoning about concepts evolving in time and of their properties in terms of qualitative relations (e.g., “before”) in addition to quantitative ones, time intervals and points. It is not only suitable to handle precise time intervals and points, but also imprecise ones. It extends the 4D-fluents approach with crisp components to represent handed data. It also extends the Allen's interval algebra. This extension allows reasoning about imprecise time intervals. Compared to related work, it is based on crisp set theory. These relations preserve many properties of the original algebra. Their definitions are adapted to allow relating a time interval and a time point, and two time points. All relations can be used for temporal reasoning by means of transitivity tables. Finally, it proposes a crisp ontology that based on the extended Allen's algebra instantiates the 4D-fluents-based representation.

International audience; In this paper, we propose an ontology-based approach for representing and reasoning about certain and uncertain temporal data. Ithandles temporal data in terms of quantitative time intervals and points and the qualitative relations between them (e.g., “before”). Itincludes three parts.(1)We extend the 4D-fluents approach with certain ontological components to represent the handled temporaldata in OWL 2.(2)We extend the Allen’s interval algebra to reason about certain and uncertain time intervals. We adapt theserelations to allow relating a time interval and a time point, and two time points. All relations can be used for temporal reasoning bymeans of transitivity tables.(3)The extended Allen’s algebra instantiates the 4D-fluents-based representation. Inferences are basedon SWRL rules. Based on this ontology, a prototype is implemented and integrated into an ontology-based memory prosthesis forAlzheimer’s patients to handle certain and uncertain temporal data inputs.

PurposeThe aim of this paper is to examine the impact of directors' home regions on corporate social responsibility (CSR) disclosure. Specifically, the authors aim to determine whether Anglo-American, European, French, other European and other regional directors' presence affects CSR disclosure differently.Design/methodology/approachThis empirical study uses panel data analysis of all listed firms on the SBF 120 from 2008 to 2019. The environmental, social and governance (ESG) scores are collected from the Bloomberg database and indicate the extent of CSR information disclosure by French companies. The paper is based on a dynamic generalized method of moments panel estimator that makes it possible to control for unobservable heterogeneity and endogeneity and reduces estimation bias.FindingsThe findings of this study provide evidence that home region diversity and the presence of Anglo-Americans on a board are positively and significantly associated with ESG disclosure and environmental disclosure, whereas they are negatively associated with social and governance disclosure. Surprisingly, when directors come from European countries, they disclose less ESG and environmental information. Nevertheless, when only French directors are present, the company tends to divulge all dimensions of CSR. Indeed, while there is a significant positive influence of French directors on ESG disclosure, the presence of other European directors displays negative and statistically significant regression coefficients.Research limitations/implicationsThis study may be interesting the French policy makers who can now pay more appropriate attention to directors' nationality or region. Thus, firms should identify the foreign directors who can support their strategy with relevant experience in terms of CSR. This could help to change the opinion of some companies that consider the internalization of the board as a constraint rather than an opportunity. These results will be useful for French-listed companies in setting the criteria for the appointment of foreign directors. It may be interesting to recruit directors across European boundaries.Practical implicationsThis paper attempts to provide a better understanding of the effects of the home regions of directors on CSR disclosure in order to enlighten corporate managers whose companies operate in different cultures given that they have to deal with this aspect. In this international business environment, CEOs should increasingly consider the international CSR experience of directors to be a resource. In addition, this study may be of relevance to French market authorities, which constantly encourage firms to diversify the profiles of directors on their boards and recruit more international members.Originality/valueThis study is the first to evince that the disclosure of each CSR disclosure score differs depending on the directors' home regions. Unlike previous studies, the authors focused simultaneously on the resource-based view (RBV) and institutional theory.

Edited by Jaroslaw Watrobski, Wojciech Salabun, Carlos Toro, Cecilia Zanni-Merk, Robert J. Howlett, Lakhmi C. Jain; International audience; Nowadays, special attention is directed to trust issues in the Decentralized Online Social Network (DOSN). In a distributed system for social networking, interactions and collaborations can be unreliable because some users resort to malicious behaviors in order to increase their trust values in the network to be chosen later by others, and launch trust-related attacks. In this unreliable situation, users will not be able to estimate the trustworthiness of the received social services’ list of recommendations. Hence, a trust management model becomes a necessity in order to overcome its trust-related attacks and to recommend trustworthy social services. In this respect, we propose a new trust management model that helps prevent trust-related attacks in order to ensure a reliable environment. Towards this end, our suggested model implements a new technology, called blockchain. Based on the studied trust-related attacks, we intend to add logical security to blockchain since this technology takes into account only the physical security. Evaluation values show the effectiveness of our model.

Data curation deals with managing the data by applying different tasks such as extraction, enrichment, cleaning to fit the purpose of use. Indeed, nowadays, there is an increasing need to implement such tasks in the big data era to maintain data management. Big data is involved in decision processes to perform analysis, visualization, prediction, etc. Thus, there is a dependency between the generated outcomes and the input data of such a process. Therefore, decision process features (e.g., decision context, user constraints, and requirements) need to be taken into account during the data management process, including the data curation phase. Although the proposed curation approaches in the literature are diverse, most of them are static and do not consider the decision process features. Moreover, most of the proposals are dedicated to curating a specific data source format (e.g., structured/unstructured data source). To overcome these limitations, we propose a new approach ACUSEC (Adaptive CUration SErvice Composition) that ensures adaptive curation services composition by considering different features: the source type, the user constraints and preferences, and the decision context. To do so, we rely on AI and machine learning mechanisms such as reinforcement learning. Following the approach's definition, we conducted experiments that show encouraging results in overall execution time and adaptation to the above features.

The computer science community is paying more and more attention to data due to its crucial role in performing analysis and prediction. Researchers have proposed many data containers such as files, databases, data warehouses, cloud systems, and recently data lakes in the last decade. The latter enables holding data in its native format, making it suitable for performing massive data prediction, particularly for real-time application development. Although data lake is well adopted in the computer science industry, its acceptance by the research community is still in its infancy stage. This paper sheds light on existing works for performing analysis and predictions on data placed in data lakes. Our study reveals the necessary data management steps, which need to be followed in a decision process, and the requirements to be respected, namely curation, quality evaluation, privacy-preservation, and prediction. This study aims to categorize and analyze proposals related to each step mentioned above.

International audience; In this paper, we propose an approach to handling uncertain time intervals and related qualitative relations, based on possibility theory. Four contributions are included in this approach. (1) Representing uncertain time intervals and related qualitative relations by extending the 4D-fluents approach with new ontological components. (2) Reasoning about uncertain time intervals by extending the Allen’s interval algebra. The resulting interval relations preserve the good properties of the original algebra. (3) Proposing an OWL 2 possibilistic temporal ontology based on 4D-fluents approach extension and Allen’s interval algebra extension. The proposed qualitative temporal relations are inferred via a set of SWRL rules. We validate our work by implementing a prototype based on this ontology. (4) Applying our work to PersonLink ontology and comparing the obtained results with our previous works.

International audience; Blockchain technology enables several untrustworthy parties to execute inter-organizational business processes in a tamper-proof manner. Existing approaches are based on smart contract code generation. Although the smart contract immutability guarantees that the process model is followed by each participant, any change in the process model makes the existing process instance smart contract not compliant with the process model and therefore, the deployment of a new smart contract becomes a requirement. In this paper, we propose CoBuP, a decentralized Collaborative Business Process execution architecture using blockchain. To address the inflexibility issue, this paper presents an interpreter of BPMN process models, supporting the instantiating, execution, monitoring of process instances. For this reason, one generic smart contract is deployed once, which helps generate a process instance, create BPMN elements by invoking the process instance predefined functions, and dynamically update the adaptation of a process at run time. For validation purposes, two use cases have permitted to carry out different experiments that demonstrate the technical feasibility of our approach. The obtained results of the experimental evaluation shows that our approach cost is similar or lower than that of the existing approaches.

International audience; The insurance industry is heavily dependent on several processes executed among multiple entities, such as insurer, insured, and third-party services. The increasingly competitive environment is pushing insurance companies to use advanced technologies to address multiple challenges, namely lack of trust, lack of transparency, and economic instability. To this end, blockchain is used as an emerging technology that enables transparent and secure data storage and transmission. In this paper, we propose CioSy, a collaborative blockchain-based insurance system for monitoring and processing the insurance transactions. To the best of our knowledge, the existing approaches do not consider collaborative insurance to achieve an automated, transparent, and tamper-proof solution. CioSy aims at automating the insurance policy processing, claim handling, and payment using smart contracts. For validation purposes, an experimental prototype is developed on Ethereum blockchain. Our experimental results show that the proposed approach is both feasible and economical in terms of time and cost.

Wildfire prediction from Earth Observation (EO) data has gained much attention in the past years, through the development of connected sensors and weather satellites. Nowadays, it is possible to extract knowledge from collected EO data and to learn from this knowledge without human intervention to trigger wildfire alerts. However, exploiting knowledge extracted from multiple EO data sources at run-time and predicting wildfire raise multiple challenges. One major challenge is to provide dynamic construction of service composition plans, according to the data obtained from sensors. In this paper, we present a knowledge-driven Machine Learning approach that relies on historical data related to wildfire observations to guide the collection of EO data and to automatically and dynamically compose services for triggering wildfire alerts.

Temporal data given by Alzheimer's patients are mostly uncertain. Many approaches have been proposed to handle certain temporal data and lack uncertain ones. This paper proposes an approach to represent and reason about quantitative time intervals and points and qualitative relations between them. It is suitable to handle certain and uncertain temporal data. It includes three parts. (1) The authors extend the 4D-fluents approach with certain components to represent certain and uncertain temporal data. (2) They extend the Allen's interval algebra to reason about certain and uncertain time intervals. They adapt these relations to relate a time interval and a time point, and two time points. All relations can be used for temporal reasoning by means of transitivity tables. (3) They propose a certain ontology based on the extensions. A prototype is implemented and integrated into an ontology-based memory prosthesis for Alzheimer's patients to handle uncertain data inputs. The evaluation proves the usefulness of the approach as all the inferences are well established and the precision results are promising.

International audience; The rapid development of blockchain technology has influenced several fields, including financial, healthcare, and supply chain systems. Recently, this technology has also been applied in education thanks to its unique features, including decentralization, trustworthiness, and security. Despite the bright side of blockchain, several concerns continue to undermine its adoption in education, such as legal, immutability, and scalability issues. Thus, a comprehensive survey about blockchain adoption in education deems necessary. This paper is a systematic literature review of blockchain applications in the education field. To do so, and after retrieving scientific publications on the topic, we classify the outcomes according to several categories. In this paper, we focus on two major themes: educational applications and benefits of blockchain integration. We combine the themes, then express and analyze the results as bubble charts. We analyze the proposed solutions in terms of the blockchain-based applications that have been developed for educational purposes and the benefits that the blockchain technology could bring to the education field. Finally, we describe some research gaps that need to be addressed and educational areas that could be explored for future research of blockchain adoption in education.

Data analytics based on the produced data from the Internet of Things (IoT) devices is expected to improve the individuals’ quality of life. However, ensuring security and privacy in the IoT data aggregation process is a non-trivial task. Generally, the IoT data aggregation process is based on centralized servers. Yet, in the case of distributed approaches, it is difficult to coordinate several untrustworthy parties. Fortunately, the blockchain may provide decentralization while overcoming the trust problem. Consequently, blockchain-based IoT data aggregation may become a reasonable choice for the design of a privacy-preserving system. To this end, we propose PrivDA, a Privacy-preserving IoT Data Aggregation scheme based on the blockchain and homomorphic encryption technologies. In the proposed system, each data consumer can create a smart contract and publish both terms of service and requested IoT data. Thus, the smart contract puts together into one group potential data producers that can answer the consumer’s request and chooses one aggregator, the role of which is to compute the group requested result using homomorphic computations. Therefore, group-level aggregation obfuscates IoT data, which complicates sensitive information inference from a single IoT device. Finally, we deploy the proposal on a private Ethereum blockchain and give the performance evaluation.

International audience; Understanding road safety issues is an essential step in proposing appropriate and relevant ways to improve road safety. In Tunisia, the balance sheet of road accidents shows a critical situation in terms of road safety when compared to other countries. The approach proposed in this article is to first describe the Tunisian context and highlight its geophysical, demographic, urban and socio-economic specificities. The contribution also proposes an inventory of mobility and road accidents and its characterization. The analysis of the situation provides a general perspective on the road safety system in Tunisia. Secondly, an empirical investigation among the institutional actors of road safety helps to put into perspective the results of the descriptive analysis and to establish an in-depth diagnosis of the dysfunctions of the public policy of road safety in Tunisia. This is a comprehensive qualitative approach. The analysis of the issues at stake, based on consensus and institutional divergences, leads to the establishment of possible courses of action to improve the situation. These concern both the field of structural, organisational and managerial reforms in favour of a better targeting of public road safety policies.; La compréhension des enjeux de sécurité routière est une étape indispensable pour proposer des pistes d’améliorations adaptées et pertinentes. En Tunisie, le bilan des accidents de la route laisse apparaître une situation critique en matière de sécurité routière, lorsqu’elle est comparée aux autres pays. La démarche proposée dans cet article est de s’attacher, en premier temps, à décrire le contexte tunisien et en souligner les spécificités géophysiques, démographiques, urbaines, socio-économiques. La contribution propose aussi un état des lieux de la mobilité et des accidents de la route et sa caractérisation. L’analyse de la situation permet de disposer d’une perspective générale dans laquelle s’inscrit le système de la sécurité routière en Tunisie. Dans un deuxième temps, une investigation empirique auprès des acteurs institutionnels de la sécurité routière aide à mettre en perspective les résultats de l’analyse descriptive et à établir un diagnostic approfondi des dysfonctionnements de la politique publique de sécurité routière en Tunisie. Il s’agit d’une approche qualitative compréhensive. L’analyse des enjeux, sur la base de consensus et de divergences institutionnels, conduit à établir des pistes d’actions possibles pour améliorer la situation. Celles-ci concernent à la fois le champ des réformes structurelles, organisationnelles, et managériales en faveur d’un meilleur ciblage des politiques publiques de sécurité routière.

La compréhension des enjeux de sécurité routière est une étape indispensable pour proposer des pistes d’améliorations adaptées et pertinentes. En Tunisie, le bilan des accidents de la route laisse apparaître une situation critique en matière de sécurité routière, lorsqu’elle est comparée aux autres pays. La démarche proposée dans cet article est de s’attacher, en premier temps, à décrire le contexte tunisien et en souligner les spécificités géophysiques, démographiques, urbaines, socio-économiques. La contribution propose aussi un état des lieux de la mobilité et des accidents de la route et sa caractérisation. L’analyse de la situation permet de disposer d’une perspective générale dans laquelle s’inscrit le système de la sécurité routière en Tunisie. Dans un deuxième temps, une investigation empirique auprès des acteurs institutionnels de la sécurité routière aide à mettre en perspective les résultats de l’analyse descriptive et à établir un diagnostic approfondi des dysfonctionnements de la politique publique de sécurité routière en Tunisie. Il s’agit d’une approche qualitative compréhensive. L’analyse des enjeux, sur la base de consensus et de divergences institutionnels, conduit à établir des pistes d’actions possibles pour améliorer la situation. Celles-ci concernent à la fois le champ des réformes structurelles, organisationnelles, et managériales en faveur d’un meilleur ciblage des politiques publiques de sécurité routière., RTS - Recherche Transports Sécurité, volume 2020

International audience

International audience

International audience

International audience

In this study, the authors present a new approach to segment and classify moving objects in video sequences by combining an unsupervised anomaly discovery framework called DeepSphere and generative adversarial networks. The proposed deep detector classifier employs and validates DeepSphere, which aims mainly to identify the anomalous cases in the spatial and temporal context in order to perform foreground objects segmentation. For post-processing, some morphological operations are considered to better segment and extract the desired objects. Finally, they take advantage of the power of generative models, which recognise the problem of semi-supervised learning as a specific missing data imputation task in order to classify the segmented objects. They evaluate the method with multiple datasets and the results confirm the effectiveness of the proposed approach, which achieves superior performance over the state-of-the-art methods having the capabilities of segmenting and classifying moving objects from videos surveillance.

International audience; Recommendation Systems have gained the intention of many researchers due to the growth of the business of personalizing, sorting and suggesting products to customers. Most of rating prediction in recommendation systems are based on customer preferences or on the historical behavior of similar customers. The similarity between customers is generally measured by the number of times customers liked or disliked the same item. Given the huge number and the variety of items, many customers cannot be considered as similar, as they did not evaluate the same items, even if they have similar tastes. This paper presents a new method of rating prediction in recommendation systems. The proposed method starts by identifying the taste directions or the interest centers based on the users' demographic information combined with their previous evaluations. Thus, it uses the Principal Component Analysis (PCA) to retrieve the major taste orientations. According to these orientations, user groups are created. Then, for each group, it generates a prediction model, that will be used to predict unknown rates of users within the corresponding group. In order to assess the accuracy of the proposed method, we compare its results with four baseline methods, namely: RegSVD, BiasedMF, SVD++ and MudRecS. Results prove that the proposed algorithm is more accurate than the base-line algorithms.

Aims: Prognosis of lung mathology severity after Covid-19 infection using chest X-ray time series Background: We have been inspired by methods analysing time series of images in remote sensing for change detection. During the current Covid-19 pandemic, our motivation is to provide an automatic tool to predict severity of lung pathologies due to Covid-19. This can be done by analysing images of the same patient acquired at different dates. Since no analytical model is available, and also no accurate quantification tools can be used due to many unknowns about the pathology, feature-free methods are good candidates to analyse such temporal images. Objective: This contribution helps improving performances of medical structures facing the Covid-19 pandemic. The first impact is medical and social since more lives could be saved with a 92% rate of good prognosis. In addition to that, patients in intensive care units (up to 15%) could a posteriori suffer from less sequels due to an early and accurate prognosis of their PP. Moreover, accurate prognosis can lead to a better planning of patient’s transfer between units and hospitals, which is linked to the second claimed economical impact. Indeed, prognosis is linked to lower treatment costs due to an optimized predictive protocol using ragiological prognosis. Methods: Using Convolutional Neural Networks (CNN) in combination with Recurrent Neural Networks (RNN). Spatial and temporal features are combines to analyse image time series. A prognosis score is delivered indicating the severity of the pathology. Learning is made on a publicly available database. Results: When applied to radiological time-series, promising results are obtained with an accuracy rates higher than 92%. Sensitivity and specificity rates are also very interesting. Conclusion: Our method is segmentation-free, which makes it competitive with respect to other assessment methods relying on time-consuming lung segmentation algorithms. When applied on radiographic data, the proposed ProgNet architecture showed promising results with good classification performances, especially for ambiguous cases. Specifically, the reported low false positive rates are interesting for an accurate and personalised care workflow.

BackgroundPublic health recommendations and governmental measures during the COVID-19 pandemic have enforced numerous restrictions on daily living including social distancing, isolation and home confinement. While these measures are imperative to abate the spreading of COVID-19, the impact of these restrictions on health behaviours and lifestyle at home is undefined. Therefore, an international online survey was launched in April 2020 in seven languages to elucidate the behavioral and lifestyle consequences of COVID-19 restrictions. This report presents the preliminary results from the first thousand responders on physical activity (PA) and nutrition behaviours.MethodsThirty-five research organisations from Europe, North-Africa, Western Asia and the Americas promoted the survey through their networks to the general society, in English, German, French, Arabic, Spanish, Portugese, and Slovenian languages. Questions were presented in a differential format with questions related to responses “before” and “during” confinement conditions.Results1047 replies (54% women) from Asia (36%), Africa (40%), Europe (21%) and other (3%) were included into a general analysis. The COVID-19 home confinement had a negative effect on all intensities of PA (vigorous, moderate, walking and overall). Conversely, daily sitting time increased from 5 to 8 hours per day. Additionally, food consumption and meal patterns (the type of food, eating out of control, snacks between meals, number of meals) were more unhealthy during confinement with only alcohol binge drink decreasing significantly.ConclusionWhile isolation is a necessary measure to protect public health, our results indicate that it alters physical activity and eating behaviours in a direction that would compromise health. A more detailed analysis of survey data will allow for a segregation of these responses in different age groups, countries and other subgroups which will help develop bespoke interventions to mitigate the negative lifestyle behaviors manifest during the COVID-19 confinement.

International audience; Several pieces of research during the last decade in intelligent perception are focused on the development of algorithms allowing vehicles to move efficiently in complex environments. Most of existing approaches suffer from either processing time which do not meet real-time requirements, or inefficient in real complex environment, which also does not meet the full availability constraint of such a critical function. To improve the existing solutions, an algorithm based on curved lane detection by using a Bayesian framework for the estimation of multi-hyperbola parameters is proposed to detect curved lane under challenging conditions. The general idea is to divide a captured image into several parts. The trajectory is modeled by a hyperbola over each part, whose parameters are estimated using the proposed hierarchical Bayesian model. Compared to the existing works in the state of the art, experimental results prove that our approach is more efficient and more precise in road marking detection.

International audience; Nowadays, due to rapidly changing technologies, applications handling more data and providing real-time services are becoming more frequent. Real-time database systems are the most appropriate systems to manage these applications. In this paper, we study statistically the behaviour of real-time transactions under the generalised earliest deadline first scheduling policy (GEDF). GEDF is a new scheduling policy in which a priority is assigned to a transaction according to both its deadline and a parameter which expresses the importance of the transaction in the system. In this paper, we focus our study on the influence of transactions composition. Precisely, we study the influence of transaction distribution on the system performances and on approximation of transactions success ratio behaviour by a probability distribution. To this end, we have developed our RTDBS simulator and we have conducted intensive Monte-Carlo simulations.

International audience; Reflectance confocal microscopy (RCM) allows fast data acquisition with a high resolution of the skin. In fact, RCM images are becoming more and more used for lentigo diagnosis. In this paper, we propose a new classification method to automate specific steps in lentigo diagnosis. Our method is based on a convolutional neural network (CNN) on InceptionV3 architecture combined with data augmentation and transfer learning. The experimental validation showed the efficiency of our model by reaching an accuracy of 98.14%.

International audience; L'Internet des Objets Social (SIoT) est un paradigme dans lequel l'Internet des Objets (IoT) est fusionné avec les réseaux sociaux. Dans ce type d'environnement, les participants sont en compétition afin d'offrir une variété de services attrayants. Néanmoins, certains d'entre eux ont recours à des comportements malveillants afin de propager des services de mauvaise qualité. Ils lancent ce qu'on appelle des attaques de confiance et brisent les fonctionnalités de base du système. Plusieurs travaux de la littérature ont traité ce problème et ont proposé différents modèles de confiance. Néanmoins, ces derniers proposent de classer les meilleurs noeuds du réseau SIoT. Ils ne permettent pas de détecter les noeuds malveillants. Pour remédier à ce problème, nous proposons un nouveau modèle de gestion de la confiance, capable de détecter et bloquer les noeuds malveillants afin d'obtenir un système fiable et résilient. ABSTRACT. The Internet of Things Social (SIoT) is a paradigm where the Internet of Things (IoT) is merged with social networks. In this type of environment, participants compete to offer a variety of attractive services. Nevertheless, some of them resort to malicious behavior in order to spread poor quality services. They commit so-called trust-related attacks and break the basic functionality of the system. Several works in the literature have addressed this problem and have proposed different trust-models. Nevertheless, they propose to classify the best nodes of the SIoT network. They do not detect different types of trust attacks or malicious nodes. To address this problem, we propose a new trust evaluation model able to detect and block malicious nodes in order to ensure a reliable and resilient system.

Nowadays, with the increasing number of data sources, especially in environmental domain, earth observation programs face major challenges for environmental data exploitation, mainly due to data sources heterogeneity of different types such as access techniques, used protocols, languages, data formats, etc. Although typical solutions abstract from this heterogeneity with a layer of data services, the development of such systems remains tedious in this context. In this paper, we propose an approach based on Model-Driven Engineering (MDE) combined with semantic annotations, to automate data service development on top of data sources. Our work contributes to the development of integrated service-based architectures driven by automatic service generation, data integration from existing environmental systems and automatic service annotations. Our solution, applied to the detection of natural disasters, provides 1) appropriate modelling of data sources and services to apply model-to-text (M2T) transformations, 2) automatic generation of Representational State Transfer (REST) data service code template, 3) automatic generation of semantically annotated Hypermedia-based descriptors of these services. We have implemented and evaluated our solution with a set of real data sources provided by the Sahara and Sahel Observatory (OSS), OpenWeatherMap and CHIRPS.

International audience; Ce travail de recherche présente MASBPL, une méthode d’aide à l’évaluation et à la sélection d’unlangage approprié pour la modélisation des processus métier sensibles (Sensitive Business Processes : SBP)dans une perspective de gestion des connaissances cruciales. Cette approche est basée sur l’aide multicritère àla décision. Elle est composée de quatre phases. Dans la première phase, un ensemble de « langages demodélisation des SBP de référence » est identifié. Dans la deuxième phase, ces langages sont analysés defaçon approfondie. Dans la troisième phase, une famille cohérente de critères d’évaluation est construite. Laquatrième phase consiste à évaluer, sur la base de ces critères, la capacité représentative des langages poursupporter parfaitement un SBP. Nous avons choisi BPMN 2.0.2 qui représente, aujourd'hui, le standard demodélisation des processus métier le plus développé et le mieux approprié pour enrichir la modélisation desSBP. MASBPL est le résultat de plusieurs expérimentations d’analyse et de modélisation des SBP dans ledomaine médical dans le cadre de l’Association de Sauvegarde des Handicapés Moteurs de Sfax-Tunisie.

National audience; Hypo-vigilance detection is becoming an important active research areas in the biomedical signal processing field. For this purpose, electroencephalogram (EEG) is one of the most common modalities in drowsiness and awakeness detection. In this context, we propose a new EEG classification method for detecting fatigue state. Our method makes use of a and awakeness detection. In this context, we propose a new EEG classification method for detecting fatigue state. Our method makes use of a Convolutional Neural Network (CNN) architecture. We define an experimental protocol using the Emotiv EPOC+ headset. After that, we evaluate our proposed method on a recorded and annotated dataset. The reported results demonstrate high detection accuracy (93%) and indicate that the proposed method is an efficient alternative for hypo-vigilance detection as compared with other methods.

International audience

International audience; Monitoring and analyzing sensor networks is essential for exploring energy consumption in smart buildings or cities. However, the data generated by sensors are affected by various types of anomalies and this makes the analysis tasks more complex. Anomaly detection has been used to find anomalous observations from data. In this paper, we propose a Pattern-based method, for anomaly detection in sensor networks, entitled CoRP “Composition of Remarkable Point” to simultaneously detect different types of anomalies. Our method detects remarkable points in time series based on patterns. Then, it detects anomalies through pattern compositions. We compare our approach to the methods of literature and evaluate them through a series of experiments based on real data and data from a benchmark.

Background: Public health recommendations and governmental measures during the COVID-19 pandemic have resulted in numerous restrictions on daily living including social distancing, isolation and home confinement. While these measures are imperative to abate the spreading of COVID-19, the impact of these restrictions on health behaviours and lifestyles at home is undefined. Therefore, an international online survey was launched in April 2020, in seven languages, to elucidate the behavioural and lifestyle consequences of COVID-19 restrictions. This report presents the results from the first thousand responders on physical activity (PA) and nutrition behaviours. Methods: Following a structured review of the literature, the &ldquo, Effects of home Confinement on multiple Lifestyle Behaviours during the COVID-19 outbreak (ECLB-COVID19)&rdquo, Electronic survey was designed by a steering group of multidisciplinary scientists and academics. The survey was uploaded and shared on the Google online survey platform. Thirty-five research organisations from Europe, North-Africa, Western Asia and the Americas promoted the survey in English, German, French, Arabic, Spanish, Portuguese and Slovenian languages. Questions were presented in a differential format, with questions related to responses &ldquo, before&rdquo, and &ldquo, during&rdquo, confinement conditions. Results: 1047 replies (54% women) from Asia (36%), Africa (40%), Europe (21%) and other (3%) were included in the analysis. The COVID-19 home confinement had a negative effect on all PA intensity levels (vigorous, moderate, walking and overall). Additionally, daily sitting time increased from 5 to 8 h per day. Food consumption and meal patterns (the type of food, eating out of control, snacks between meals, number of main meals) were more unhealthy during confinement, with only alcohol binge drinking decreasing significantly. Conclusion: While isolation is a necessary measure to protect public health, results indicate that it alters physical activity and eating behaviours in a health compromising direction. A more detailed analysis of survey data will allow for a segregation of these responses in different age groups, countries and other subgroups, which will help develop interventions to mitigate the negative lifestyle behaviours that have manifested during the COVID-19 confinement.

International audience; Configurable processes are increasingly being adopted by enterprises that seek experience sharing and best practice adoption. A configurable process is a customizable model that specifies how different enterprises perform similar processes. At the modeling level, a configurable process model provides for flexible business process (BP) reuse by (de)selecting the (ir)relevant parts to derive a particular process variant. At the exploitation level, it offers flexibility and agility to an enterprise looking to outsource its BP to different providers cooperating in a cloud federation. More specifically, an enterprise can use a configurable process model to derive particular process variants that it outsources depending on its objectives. In particular, it may opt for outsourcing the variant that results in the optimal deployment , e.g., having the minimal cost of allocated cloud services that fulfill the user quality of service (QoS) requirements. However, identifying the optimal deployment variants is a complex problem because of the heterogeneity of services within a cloud federation and the number of possible variants that can be derived from a configurable process model. In addition, the complexity of this problem increases for variable user QoS requirements. In this paper, we propose an approach to derive, from a configurable process model, the variant that has the optimal deployment in a cloud federation. We propose a linear programming approach that accounts for the variability of both the BP model and the user QoS requirements, and that ensures an optimal time-aware cloud service allocation. We experimentally show the effectiveness and flexibility of our approach on a generated testbed

Purpose Generally, the user requires customized information reflecting his/her current needs and interests that are stored in his/her profile. There are many sources which may provide beneficial information to enrich the user’s interests such as his/her social network for recommendation purposes. The proposed approach rests basically on predicting the reliability of the users’ profiles which may contain conflictual interests. The paper aims to discuss this issue. Design/methodology/approach This approach handles conflicts by detecting the reliability of neighbors’ profiles of a user. The authors consider that these profiles are dependent on one another as they may contain interests that are enriched from non-reliable profiles. The dependency relationship is determined between profiles, each of which contains interests that are structured based on k-means algorithm. This structure takes into consideration not only the evolutionary aspect of interests but also their semantic relationships. Findings The proposed approach was validated in a social-learning context as evaluations were conducted on learners who are members of Moodle e-learning system and Delicious social network. The quality of the created interest structure is assessed. Then, the result of the profile reliability is evaluated. The obtained results are satisfactory. These results could promote recommendation systems as the selection of interests that are considered of enrichment depends on the reliability of the profiles where they are stored. Research limitations/implications Some specific limitations are recorded. As the quality of the created interest structure would evolve in order to improve the profile reliability result. In addition, as Delicious is used as a main data source for the learner’s interest enrichment, it was necessary to obtain interests from other sources, such as e-recruitement systems. Originality/value This research is among the pioneer papers to combine the semantic as well as the hierarchical structure of interests and conflict resolution based on a profile reliability approach.

International audience; This work is aimed at developing a new process to separate alpha-cyclodextrin (CD) from binary alpha-CD/beta-CD mixtures. To achieve this objective, a membrane process was designed with water as solvent and using the selective accommodation of a guest Igepal Co-890 (IG) within the beta-CD cavity. In the first part, host-guest inclusion study suggested the formation of IG(2)/beta-CD complex in presence of IG excess. Moreover, increasing IG/CD molar ratio to 1.5 leads to the complete complexation of beta-CD while alpha-CD remains free. The second part was devoted to the separation of alpha- and beta-CD using UF membranes (GH and GK from GE-Osmonics). The influence of parameters including membrane molecular weight cut-off (MWCO), transmembrane pressure (Delta P), IG/beta-CD and alpha-CD/beta-CD molar ratios, was investigated. MWCO, Delta P, IG/beta-CD and alpha-CD/beta-CD molar ratios respectively of 1000 Da, 2 bar, 1.5 and 11:89 are the optimized values to reach an alpha-CD separation factor as high as 38. The experimental data fits very well with predicted values calculated using the parameters found in the complexation study and rejection of single solutions indicating that selectivity predominantly originates from steric exclusion of species by membrane GH.

International audience; Although Modern Standard Arabic is taught in schools and used in written communication and TV/radio broadcasts, all informal communication is typically carried out in dialectal Arabic. In this work, we focus on the design of speech tools and resources required for the development of an Automatic Speech Recognition system for the Tunisian dialect. The development of such a system faces the challenges of the lack of annotated resources and tools, apart from the lack of standardization at all linguistic levels (phonological, morphological, syntactic and lexical) together with the mispronunciation dictionary needed for ASR development. In this paper, we present a historical overview of the Tunisian dialect and its linguistic characteristics. We also describe and evaluate our rule-based phonetic tool. Next, we go deeper into the details of Tunisian dialect corpus creation. This corpus is finally approved and used to build the first ASR system for Tunisian dialect with a Word Error Rate of 22.6%.

Insufficient volume of the future liver remnant (FLR) is a major cause of non-resectable disease in patients presenting with primary or metastatic liver tumours. The objective of this study was to evaluate the safety and efficacy of the combined preoperative portal and hepatic vein embolization (biembolization) before extended right liver resections. This retrospective study was performed in a tertiary centre between 2014 and 2015. Combined right portal and hepatic vein embolization (biembolization) was proposed, as an alternative to ALPPS procedure, for all patients with primary or metastatic liver tumour, before right extended hepatectomy. CT scan liver volumetry was assessed before biembolization, three weeks after biembolization and one week after surgery. Seven patients underwent biembolization. All patients had right portal vein embolization (PVE) combined with right hepatic vein embolization (HVE, n = 4), median HVE (n = 2) and right + median HVE (n = 1). Three patients had preoperative liver disease and two received preoperative chemotherapy. No biembolization procedure-related complications occurred. The mean FLR regeneration rate was 52.6% (range: 18.2–187.9) after the biembolization. One patient with gallbladder carcinoma was not operated because of peritoneal carcinomatosis diagnosed after the biembolization. The remnant six patients did not develop postoperative liver failure. Biembolization seems to induce safe, reproducible and effective FLR growth before extended right hepatectomy, in patients with primary or metastatic liver tumour.

International audience; In this paper, we propose a method to disambiguate the output of a morphological analyzer of the Tunisian dialect. We test three machine-learning techniques that classify the morphological analysis of each word token into two classes: true and false. The class label is assigned to each analysis according to the context of the corresponding word in a sentence. In failure cases, we combine the results of the proposed techniques with a bigram classifier to choose only one analysis for a given word. We disam-biguate the result of the morphological analyzer of the Tunisian Dialect Al-Khalil-TUN (Zribi et al., 2013b). We use the Spoken Tunisian Arabic Corpus STAC (Zribi et al., 2015) to train and test our method. The evaluation shows that the proposed method has achieved an accuracy performance of 87.32%. Ó 2017 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

International audience; Ontology, as a useful knowledge engineering technique, has been widely used for reducing ambiguity and helping with information sharing. It is considered originally to be clear, comprehensive, and with well-defined format. It characterizes several domains purposes description through structured and formalized languages. In various areas of research, it has become a significant way to realize successful and powerful accomplishments. Actually, medical ontologies were turned into an efficient application in medical domains. They also become a relevant approach to process large medical data volumes. Consequently, they are behaving as a support decision system in some cases. Also, they ensure diagnosis process acceleration and assistance. Additionally, they have been integrated especially to represent human healthcare concepts. For that reason, plenty of research works applied ontologies to design and treat liver diseases. In this article, we present a general overview of medical ontologies to stand for this type of disease. We expose and discuss these works in details by a complete comparison. Also, we show their performance to arrange clinical data and extract results.

Temporal representation and reasoning are important facets in the design of many Semantic Web applications. Several approaches exist to represent and reason about precise temporal data in ontology. However, most of them handle only time intervals and associated qualitative relations. Besides, to the best of our knowledge, there is no approach devoted to handle imprecise temporal data (e.g., “late 1970s”). In this paper, we propose an ontology-based approach for representing and reasoning about precise and imprecise temporal data. Quantitative temporal data (i.e., time intervals and points) and qualitative ones (i.e., relations between time intervals, relations between a time interval and a time point and relations between time points) are taken into consideration. Our approach is three folds: (i) extending the 4D-fluents approach with new crisp and fuzzy components, to represent precise and imprecise temporal data, (ii) extending the Allen’s interval algebra to enable reasoning about precise and imprecise temporal data, and (iii) creating a Fuzzy-OWL 2 ontology TimeOnto that, based on the extended Allen’s interval algebra, instantiates our 4D-fluents-based representation. The extension that we propose for the Allen’s interval algebra handles precise and imprecise time intervals. Indeed, it enables expressing precise (e.g., “before”) and imprecise (e.g., “just before”) temporal relations. Compared to related work, our imprecise relations are personalized, in the sense that they are not limited to a defined set of interval relations and their meanings are determined by the domain expert. For instance, the classic Allen’s relation “Before” may be generalized in 5 imprecise relations, where “Before (1) ” means “just before” and gradually the time gap between the two intervals increases until “Before (5) ” which means “very long before”. To enable this representation, we propose an extension of the Vilain and Kautz’s point algebra and redefined the Allen’s relations by means of this extended algebra. We show in this paper that, unlike most related work, the resulting relations preserve many of the desirable properties of the Allen’s interval algebra. The definitions of the resulting interval relations are adapted to allow relating a time interval and a time point, and two time points, where time intervals and points maybe both precise or both imprecise. These relations can be used for temporal reasoning by means of four transitivity tables. Finally, we describe a prototype based on “TimeOnto” that infers new relations using a set of SWRL and fuzzy IF-THEN rules. This prototype was integrated in an ontology-based memory prosthesis for Alzheimer’s patients.

International audience; NoSQL document stores are well-tailored to efficiently load and manage massive collections of heterogeneous documents without any prior structural validation. However, this flexibility becomes a serious challenge when querying heterogeneous documents, and hence the user has to build complex queries or reformulate existing queries whenever new schemas are introduced in a collection. In this paper we propose a novel approach, based on formal foundations, for building schema-independent queries which are designed to query multi-structured documents. We present a query enrichment mechanism that consults a pre-constructed dictionary. This dictionary binds each possible path in the documents to all its corresponding absolute paths in all the documents. We automate the process of query reformulation via a set of rules that reformulate most document store operators, such as select, project, unnest, aggregate and lookup. We then produce queries across multi-structured documents which are compatible with the native query engine of the underlying document store. To evaluate our approach, we conducted experiments on synthetic datasets. Our results show that the induced overhead can be acceptable when compared to the efforts needed to restructure the data or the time required to execute several queries corresponding to the different schemas inside the collection.

International audience

International Conference on e-Business Engineering; International audience; Social Internet of Things (SIoT) is a new paradigm where the Internet of Things (IoT) is merged with social networks, allowing objects to establish autonomous social relationships. However, face to this new paradigm, users remain suspicious. They fear the violation of their privacy and revelation of their personal information. Without reliable mechanisms to enhance trustworthy communications between nodes, SIoT will not reach sufficient popularity to be considered as a leading technology. Hence, trust management becomes a major challenge to ensure qualified services and guaranteed security. Several works in the literature have tried to diagnose this problem. They proposed various trust evaluation models based on different features and aggregation methods, aiming to classify benign nodes of the SIoT network. However, related works did not allow to detect malicious nodes and couldn’t identify their types of attacks. As a result, we suggest a new trust-evaluation model in a deep learning framework. This model permits to find out the type of trust-related attacks performed by malicious nodes, which will be isolated from the network in order to achieve a reliable environment. Based on authentic data, experimentation is able to prove our system performance.

International audience; Parallel imaging technique using several receiver coils provides a fast acquisition of magnetic resonance imaging (MRI) images with high temporal and/or spatial resolutions. Against this background, the most difficult task is the full field of view images reconstruction without noise, distortions and artifacts. In this context, SENSitivity Encoding is considered the most often used parallel MRI (pMRI) reconstruction method in the clinical application. On the one side, solving the inherent reconstruction problems has known significant progress during the last decade. On the other side, the sparse Bayesian regularization for signal/image recovery has generated a great research interest especially when large volumes of data are processed. The purpose of this paper is to develop a novel Bayesian regularization technique for sparse pMRI reconstruction. The new technique is based on a hierarchical Bayesian model using a complex Bernoulli–Laplace mixture in order to promote two sparsity levels for the target image. The inference is conducted using a Markov chain Monte Carlo sampling scheme. Simulation results obtained with both synthetic and real datasets are showing the outperformance of the proposed sparse Bayesian technique compared to other existing regularization techniques.