Search

A new hyperspectral texture descriptor, Relative Spectral Difference Occurrence Matrix (RSDOM) is proposed. Developed in a metrological framework, it simultaneously considers the distribution of spectra and their spatial arrangement in the hyperspectral image. It is generic and adapted for any number of spectral band or range. As validation, a texture classification scheme is applied on HyTexiLa dataset using RSDOM. The obtained accuracy is excellent (95.6%), comparable to Opponent Band Local Binary Pattern (OBLBP) but at a much-reduced feature size (0.1% of OBLBP's). © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

[Context] Product line engineering is a conception and production paradigm in which the purpose is no longer to develop a single product but to develop a collection of products. They present a strategy that provides to the organizations a more competitive edge by improving productivity and decreasing costs. However, these benefits can be missed if users find difficulties when they are configuring a product from the line. This situation is widespread mainly when they deal with large product lines that contain a plethora of characteristics. [Problem] In these cases, the configuration process becomes monotonous and an error prone task. Furthermore, it is crucial to guide stakeholders by providing assistance during such complex process. Consequently, the configuration process envisages recommending the best configuration alternatives to users until leading them to a satisfying experience. [Contribution] Our proposal aims to enhance future configuration processes and maximize the user satisfaction based on previous executions. Therefore, we mine and analyze previous product line configurations by logging user's actions. User guidance is orchestrated by a goal-question-metric approach. [Results] Our research has shown that guidance solutions can be proposed according to the trace mining. Integrating these solutions throughout the configuration process can assist potential users that they are configuring complex lines. The usability of analyzing traces in order to guide future configurations is demonstrated using an e-shop case study from the software industry.

International audience

International audience; Robust calibration of next-generation radio-interferometers, as the square kilometer array (SKA) for instance, is a crucial prepro-cessing step for sky imaging. Recently, several robust calibration es-timators based on the use of well known strong sources in the field of view (FOV) have been proposed in the literature. For that, usually a compound-Gaussian (CG) noise is considered since it can take into account the presence of outliers, such that unknown weak sources in the FOV, and remains mathematically tractable. Specifically, the CG model is a zero-mean Gaussian process with a random variance, usually called texture. Performance bounds provide the lowest mean squared error (MSE) that an unbiased estimator can hope to reach. To the best of our knowledge, there is a lack of practical bounds dedicated to the robust calibration of future radio interferometers as far as they can be used as design tools for a given FOV. In this work, the hybrid Cramér-Rao bound (HCRB) is derived for a propagation model based on the Jones-matrix formalism corrupted by a CG noise for several texture distributions (K-distribution, Student's t, Cauchy, and Inverse-Gaussian compound Gaussian distribution (IG-CG)). In this standard physical model, the waveform propagation model is parametrized by a set of deterministic physical parameters of interest (complex gains, phases, DOA, etc.). In this work, we show that the HCRB w.r.t. the physical deterministic parameters is in fact given by the modified CRB (MCRB). The MCRB is easy to derive since only the first-order moment of the inverse of the texture variable is needed.

With the increase in measurement/sensing technologies, the collected data are in intrinsically multidimensional in a large number of applications. This can be interpreted as a growth of the dimensionality/order of the associated tensor. There exists therefore a crucial need to derive equivalent and alternative models of a high-order tensor as a graph of low-order tensors. In this work we consider a " train " graph, i.e., a Q-order tensor will be represented as a Tensor Train (TT) composed of Q − 2 3-order core tensors and two core matrices. In this context, it has been shown that a canonical rank-R CPD / PARAFAC model can always be represented exactly by a TT model whose cores are canonical rank-R CPD/PARAFAC. This model is called TT-CPD. We generalize this equivalence to the PARALIND model in order to take into account potential linear dependencies in factors. We derive and discuss here uniqueness conditions for the case of the TT-PARALIND model., Avec l'accroissement des moyens d'acquisition et de mesures, les données d'intérêt sont par essence de nature multidimensionnelle. Ceci peut s'interpréter comme un accroissement de la dimension/ordre des modèles tensoriels associés. Il y a donc un besoin crucial d'avoir à notre disposition des représentations équivalentes d'un tenseur d'ordre élevé en un graphe de tenseurs d'ordre réduit. Dans ce travail nous considérons un graphe de type "train", c'est-à-dire, qu'un tenseur d'ordre Q sera représenté par un train de tenseur (TT) composé de Q − 2 coeurs tensoriels d'ordre 3 et deux coeurs matriciels. Dans ce cadre, il a été démontré qu'un modèle CPD/PARAFAC de rang canonique R peut être toujours représenté de manière exacte par un modèle TT dont les coeurs sont eux-même CPD/PARAFAC de rang canonique R. Ce modèle est nommé TT-CPD. Nous généralisons cette équivalence au modèle PARALIND afin de prendre en compte des potentielles dépendances linéaires dans les facteurs. Nous donnons et discutons ici les conditions d'unicité dans le cas du modèle TT-PARALIND.

Data as a Service (DaaS) is seen as a promising cloud offering for wrangling the overload of information and making it available across cloud platforms anytime and anywhere. While there exist a large number of DaaS providers in the market, each one has a different way to describe its provided services as well as supplied datasets. The lack of a well-defined machine-readable model strongly hinders the automatic selection and composition of DaaSs. This paper presents MoDaaS, a model-driven framework for the modeling and the description of DaaS services. MoDaaS enables DaaS providers to describe their services capabilities and concerns according to a shared ontology, thereafter it enables them to automatically generate service views in order to assist the integration and data exchange between heterogeneous services.

International audience; Spaceborne and airborne sensors deliver a huge number of Earth Observation Data every day. In this context, we can easily observe the whole earth from its different sides. Therefore, this big data is important in remote sensing and could be exploited in several domains requiring image classification, natural hazard monitoring, global climate change, agriculture, urban planning. Over the last five years, Convolutional Neural Networks (CNN) emerged as the most successful technique for the image classification task, as well as a number of other computer vision tasks. However, to train millions of parameters in CNN one requires a huge amount of annotated data. This requirement leads to a significant challenge if the available training data is limited for a target task at hand. To address this challenge, in the recent literature, researchers proposed various ways to apply a technique called Transfer Learning to transfer the knowledge gained by training CNNs parameters on some large annotated dataset to the target task with limited availability of training data. Most of our work in this paper was dedicated to proposing a hybrid classification of remote sensing images. This architecture combines Spark RDD image coding to consider image's local regions, pre-trained VGGNET-16 and UNET for image segmentation and SVM (Support Vector Machines) from spark Machine Learning to achieve labeling task.

International audience; Unmanned Aerial Vehicles (UAVs) have known much popularity for dangerous missions for human operators or for applications which do not need human intervention (such as monitoring and surveillance of physical infrastructures and interest areas). They operate in frequency bands (IEEE L-Band, IEEE S-Band, and ISM band) shared with other users. Accordingly, these frequency bands have become overcrowded and UAVs may face the issue of spectrum scarcity. Furthermore, there are particular difficulties associated with aeronautical communication links. Cognitive radio (CR) has emerged as a promising strategy for resolving the problems caused by scarce spectrum. It checks the spectrum availability and allows the adjustment of the transmission parameters. The aim is to opportunistically use spectral bands with minimum interference to applications or other users. In this paper, we present a centralized CR based frequency allocation scheme for UAV-Ground Control Station (GCS) communication in surveillance applications within an urban environment. In the proposed model, the GCS monitors and allocates available WiMAX frequencies using CR and Software Defined Radio (SDR). If no WiMAX frequency is available at a given time, the Wi-Fi will be used. Therefore in the worst case, our approach will have the same performance as when the Wi-Fi is only used for UAV-GCS communication.

International audience; In recent years, a large number of researchers investigate the conception of systems that use a unique Unmanned Ariel Vehicles (UAV) or multiple independent UAVs to conduct civil or military missions, with minimal human intervention. In this paper we focus on using multiple UAVs to cooperatively monitor a crowded area. Communication in such UAVs network is an ongoing project. Due to the lack of proper communication standards and rules, designing a reliable communication model is essential for: (i) multi-UAV coordination, (ii) efficient bandwidth sharing according to data priority and urgency and (iii) avoiding useless transmission of the same data by multiple UAVs. To address the above challenges, we propose a centralized data-oriented communication architecture for crowd surveillance allocations using an UAV fleet. The Ground Control Station (GCS) is used as a central coordinator to manage bandwidth usage for the UAV fleet in its coverage area. To allow UAVs to send priority messages urgently to the GCS, we define two classes of urgent messages: critical state and important result. The class of the data as well as other relevant information about the detected event will be used by the GCS to authorize or not UAV data transmission and hence to optimize the bandwidth usage efficiency.

This thesis deals with the formal description and development of an electronic grammar of Arabic language. This work is a prerequisite for the creation of automatic Arabic processing tools. This language presents many challenges for automatic processing. Indeed the order of words in Arabic is relatively free,the morphology is rich and the diacritics are omitted in written texts. Although several research studies have addressed some of these issues, electronic resources useful for the processing of Arabic remain relatively rare or not widely available. In this thesis work, we are interested in the representation of syntax (word order) and the meaning of modern standard Arabic. As a formal system of language representation, we chose the formalism of Tree Adjoining Grammar. Thus we proposed an electronic adjoint tree grammar of Arabic named"ArabTAGV2.0". This resource partially reuses the pre-existing modeling in the manually defined grammar "ArabTAG" and integrates it into an abstract representation called meta-grammar. The linguistic expert canthus describe the syntax and semantics of the language with abstraction tools facilitating the maintenance and extension of the grammar. The new described grammar has 1074 syntactical rules (not lexicalized) and27 semantic frameworks (predicative relations). This resource was evaluated by analyzing a corpus from excerpts of an Arabic textbook.; Cette thèse traite de la description formelle et du développement d’une grammaire électronique de la langue arabe. Ce travail est un prérequis à la création d’outils de traitement automatique de l’arabe.Cette langue présente de nombreux défis pour un traitement automatique. En effet l’ordre de mots en arabe est relativement libre, la morphologie y est riche et les diacritiques sont omis dans les textes écrits. Bien que plusieurs travaux de recherche aient abordé certaines de ces problématiques, les ressources électroniques utiles pour le traitement de l’arabe demeurent relativement rares ou encore peu disponibles. Dans ce travail de thèse, nous nous sommes intéressés à la représentation de la syntaxe (ordre des mots) et du sens de l’arabe standard moderne. Comme système formel de représentation de la langue, nous avons choisi le formalisme des grammaires d’arbres adjoints (Tree Adjoining Grammar). Nous avons ainsi proposé une grammaire d’arbres adjoints électronique de l’arabe nommée « ArabTAG V2.0 ». Cette ressource réutilise en partie la modélisation préexistante dans la grammaire définie manuellement «ArabTAG » et l’intègre à une représentation abstraite appelée méta-grammaire. L’expert linguiste peut ainsi décrire la syntaxe et sémantique de la langue avec des outils d’abstraction facilitant la maintenance et l’extension de la grammaire. La grammaire ainsi décrite compte 1074 règles syntaxiques (non lexicalisées) et 27 cadres sémantiques (relations prédicatives). Cette ressource a été évaluée en analysant un corpus issu d’extraits d’un manuel scolaire d’apprentissage de l’arabe.

This thesis deals with the formal description and development of an electronic grammar of Arabic language. This work is a prerequisite for the creation of automatic Arabic processing tools. This language presents many challenges for automatic processing. Indeed the order of words in Arabic is relatively free,the morphology is rich and the diacritics are omitted in written texts. Although several research studies have addressed some of these issues, electronic resources useful for the processing of Arabic remain relatively rare or not widely available. In this thesis work, we are interested in the representation of syntax (word order) and the meaning of modern standard Arabic. As a formal system of language representation, we chose the formalism of Tree Adjoining Grammar. Thus we proposed an electronic adjoint tree grammar of Arabic named"ArabTAGV2.0". This resource partially reuses the pre-existing modeling in the manually defined grammar "ArabTAG" and integrates it into an abstract representation called meta-grammar. The linguistic expert canthus describe the syntax and semantics of the language with abstraction tools facilitating the maintenance and extension of the grammar. The new described grammar has 1074 syntactical rules (not lexicalized) and27 semantic frameworks (predicative relations). This resource was evaluated by analyzing a corpus from excerpts of an Arabic textbook.; Cette thèse traite de la description formelle et du développement d’une grammaire électronique de la langue arabe. Ce travail est un prérequis à la création d’outils de traitement automatique de l’arabe.Cette langue présente de nombreux défis pour un traitement automatique. En effet l’ordre de mots en arabe est relativement libre, la morphologie y est riche et les diacritiques sont omis dans les textes écrits. Bien que plusieurs travaux de recherche aient abordé certaines de ces problématiques, les ressources électroniques utiles pour le traitement de l’arabe demeurent relativement rares ou encore peu disponibles. Dans ce travail de thèse, nous nous sommes intéressés à la représentation de la syntaxe (ordre des mots) et du sens de l’arabe standard moderne. Comme système formel de représentation de la langue, nous avons choisi le formalisme des grammaires d’arbres adjoints (Tree Adjoining Grammar). Nous avons ainsi proposé une grammaire d’arbres adjoints électronique de l’arabe nommée « ArabTAG V2.0 ». Cette ressource réutilise en partie la modélisation préexistante dans la grammaire définie manuellement «ArabTAG » et l’intègre à une représentation abstraite appelée méta-grammaire. L’expert linguiste peut ainsi décrire la syntaxe et sémantique de la langue avec des outils d’abstraction facilitant la maintenance et l’extension de la grammaire. La grammaire ainsi décrite compte 1074 règles syntaxiques (non lexicalisées) et 27 cadres sémantiques (relations prédicatives). Cette ressource a été évaluée en analysant un corpus issu d’extraits d’un manuel scolaire d’apprentissage de l’arabe.

International audience; To fulfill its complex business demands, an organization may require the integration of many SaaS applications. A main challenge in this regard is to select the suitable SaaS offerings that satisfy all the business requirements. Due to the diversity of QoS needs and the large number of SaaS providers, selecting the suitable set of SaaS applications to be integrated may result in QoS degradation and higher costs. In this paper, we propose to use a System-of-Systems (SoS)-based approach for the selection and integration of SaaS. We believe that the use of SoS and its dynamic properties could improve the service selection at SaaS level. To do so, we propose three Mixed Integer Programming models that optimize the global SaaS behavior by minimizing the overall delivery costs, and maximizing the global functional and QoS utilities. The implementation of the approach and the experimental results highlight the efficiency of our proposed solution.

The explosion of web 2.0 and social networks has created an enormous and rewarding source of information that has motivated researchers in different fields to exploit it. Our work revolves around the issue of access and identification of social information and their use in building a user profile enriched with a social dimension, and operating in a process of personalization and recommendation. We study several approaches of Social IR (Information Retrieval), distinguished by the type of incorporated social information. We also study various social recommendation approaches classified by the type of recommendation. We then present a study of techniques for modeling the social user profile dimension, followed by a critical discussion. Thus, we propose our social recommendation approach integrating an advanced social user profile model., L’explosion du web 2.0 et des réseaux sociaux a crée une source d’information énorme et enrichissante qui a motivé les chercheurs dans différents domaines à l’exploiter. Notre travail s’articule autour de la problématique d’accès et d’identification des informations sociales et leur exploitation dans la construction d’un profil utilisateur enrichi d’une dimension sociale, et son exploitation dans un processus de personnalisation et de recommandation. Nous étudions différentes approches sociales de RI (Recherche d’Information), distinguées par le type d’informations sociales incorporées. Nous étudions également diverses approches de recommandation sociale classées par le type de recommandation. Nous exposons ensuite une étude des techniques de modélisation de la dimension sociale du profil utilisateur, suivie par une discussion critique. Ainsi, nous présentons notre approche de recommandation sociale proposée intégrant un modèle avancé de profil utilisateur social.

The explosion of web 2.0 and social networks has created an enormous and rewarding source of information that has motivated researchers in different fields to exploit it. Our work revolves around the issue of access and identification of social information and their use in building a user profile enriched with a social dimension, and operating in a process of personalization and recommendation. We study several approaches of Social IR (Information Retrieval), distinguished by the type of incorporated social information. We also study various social recommendation approaches classified by the type of recommendation. We then present a study of techniques for modeling the social user profile dimension, followed by a critical discussion. Thus, we propose our social recommendation approach integrating an advanced social user profile model. L’explosion du web 2.0 et des réseaux sociaux a crée une source d’information énorme et enrichissante qui a motivé les chercheurs dans différents domaines à l’exploiter. Notre travail s’articule autour de la problématique d’accès et d’identification des informations sociales et leur exploitation dans la construction d’un profil utilisateur enrichi d’une dimension sociale, et son exploitation dans un processus de personnalisation et de recommandation. Nous étudions différentes approches sociales de RI (Recherche d’Information), distinguées par le type d’informations sociales incorporées. Nous étudions également diverses approches de recommandation sociale classées par le type de recommandation. Nous exposons ensuite une étude des techniques de modélisation de la dimension sociale du profil utilisateur, suivie par une discussion critique. Ainsi, nous présentons notre approche de recommandation sociale proposée intégrant un modèle avancé de profil utilisateur social.

Nowadays, Wireless Body Area Networks (WBANs) are revolutionizing the field of healthcare applications which is deeply related to human life and requires a noteworthy attention. In this medical context, reliability, energy consumption and real time monitoring are the main Quality of Service (QoS) challenges to satisfy. This kind of networks relies on wireless channel medium which is sensitive to several factors such as body shadowing, interference, human postures and body signal absorption. In this paper, our main focus is to exploit the knowledge related to the link quality to select the most appropriate Body Node Coordinator (BNC) in order to improve the overall network performance. Our experimental study which is based on real testbeds revealed that the position of the BNC is sensitive to human morphology and practiced activity.

International audience; The increasing amount of remote sensing data has opened the door to new challenging research topics. Nowadays, significant efforts are devoted to pixel and object based classification in case of massive data. This paper addresses the problem of semantic segmentation of big remote sensing images. To do this, we proposed a top-down approach based on two main steps. The first step aims to compute features at the object-level. These features constitute the input of a multi-layer feed-forward network to generate a structure for classifying remote sensing objects. The goal of the second step is to use this structure to label every pixel in new images. Several experiments are conducted based on real datasets and results show good classification accuracy of the proposed approach. In addition, the comparison with existing classification techniques proves the effectiveness of the proposed approach especially for big remote sensing data.

International audience; In-network caching in Named Data Networking (NDN) based Internet of Things (IoT) plays a central role for efficient data dissemination. Data cached throughout the network may quickly become obsolete as they are transient and frequently updated by their producers. As such, NDN-based IoT networks impose stringent requirement in terms of data freshness. While various cache replacement policies were proposed, none has considered the cache freshness requirement. In this paper, we introduce a novel cache replacement policy called Least Fresh First (LFF) integrating the cache freshness requirement. LFF evicts invalid cached contents based on time series forecasting of sensors future events. Extensive simulations are performed to evaluate the performance of LFF and to compare it to the different well-known cache replacement policies in ICN-based IoT networks. The obtained results show that LFF significantly improves data freshness compared to other policies, while enhancing the server hit reduction ratio, the hop reduction ratio and the response latency.

International audience; La résolution d'anaphores est une tâche fondamentale pour la plupart des applications du TALN. Cette tâche reste un problème difficile qui nécessite plusieurs sources de connaissances et des techniques d'apprentissage efficaces, notamment pour la langue arabe. Cet article présente une nouvelle approche de résolution d'anaphores pronominales dans les textes arabes en se basant sur une méthode d'Apprentissage par Renforcement AR qui utilise l'algorithme Q-learning. Le processus de résolution comporte une étape d'identification des pronoms et des antécédents candidats et une autre de résolution. L'algorithme Q-learning permet d'apprendre dans un environnement dynamique et incertain. Il cherche à optimiser pour chaque pronom anaphorique, une séquence de choix de critères pour évaluer les antécédents et sélectionner le meilleur. Le système de résolution est évalué sur des textes littéraires, des textes journalistiques et des manuels techniques. Le taux de précision atteint jusqu'à 77,14\%.

International audience; Spectro-spatial dimensionality reduction in HyperSpectral Images (HSI) classification is a challenging task due to the problem of curse dimensionality, i.e. the high number of spectral bands and the heterogeneity of data. In this context, many dimensionality reduction methods have been developed to overcome the high correlation between bands and the redundancy of information in order to improve the classification accuracy. Most of these methods represent the original HSI as a set of vectors. Therefore, they only exploit spectral properties, neglecting the spatial information, i.e. the spatial rearrangement is lost. To jointly take advantage of spatial and spectral information, HSI has been recently represented as a tensor. In order to preserve the spatial and spectral information, we develop a hybrid method using both the Tensor Locality Preserving Projections method (TLPP) projecting the original data into a lower subspace and the Constrained Band Selection method (CBS) to select the relevant bands. These two methods will be jointly used to get high-level quality classification. Moreover, since the two obtained classifications are uncertain and imprecise, we propose to fuse them using the Dempster-Shafer's Theory (DST) to obtain an accurate classification preserving the spectro-spatial information. The proposed approach has been applied on real HSI showing its efficiency compared with conventional dimensionality reduction methods.

International audience; Business intelligence (BI) is a set of technologies and strategies allowing analyzing data and providing information to help in the decision-making process. Today, BI is used in many sectors and shows marvelous results. In this paper, we are interested in supporting decision-making in higher education. BI concepts when integrated to the process of academic affairs can make significant improvement. The present paper aims at describing a BI solution to support academic affairs at Taibah University. Using BI, we can take advantages of a set of analytical tools that support decision-making for different types of users (students, faculty members, administrators and decision makers). The proposed BI solution consists essentially of three mains tasks: (1) collecting data from different sources using the three operations (Extract, Transform and Load), (2) proposing a multidimensional solution that describes the academic processes, and (3) visualizing results through a set of dashboards and reports. Experiments are made using the SQL Server Data Tools. Three steps are detailed which are: SQL Server Integration Services, SQL Server Analysis Services and SQL Server Reporting Services. The proposed solution provides many statistical and predictive indicators needed in academic tasks.

International audience; The increasing volume of data generated by earth observation programs such as Copernicus, NOAA, and NASA Earth Data, is overwhelming. Although these programs are very costly, data usage remains limited due to lack of interoperability and data linking. In fact, multi-source and heterogeneous data exploitation could be significantly improved in different domains especially in the natural disaster prediction one. To deal with this issue, we introduce the PREDICAT project that aims at providing a semantic service-oriented platform to PREDIct natural CATastrophes. The PREDICAT platform considers (1) data access based on web service technology; (2) ontology-based interoperability for the environmental monitoring domain; (3) data integration and linking via big data techniques; (4) a prediction approach based on semantic machine learning mechanisms. The focus in this paper is to provide an overview of the PREDICAT platform architecture. A scenario explaining the operation of the platform is presented based on data provided by our collaborators, including the international intergovernmental Sahara and Sahel Observatory (OSS).

International audience; This work presents algorithms to extend tenant Virtualized Network Functions Forwarding Graphs (VNF-FG) to embed new networking functions and introduce gradually additional services into the already deployed tenant dedicated slices. The related service graph extension problem is addressed through an Integer Linear Programming (ILP) algorithm that serves as a reference for performance comparisons with a proposed heuristic algorithm. An eigendecomposition approach is proposed, evaluated and compared

International audience; Nowadays, detecting and interpreting random variation extracted from satellite image time series is a far-reaching real-world issue. A more adequate approach should be designed to deal with this challenge. In this paper, we propose an efficient knowledge-based approach for vegetation monitoring using normalized derivation vegetation index time series. First, a decomposition process is designed to separate seasonal, trend and remainder components. Then, a genetic based schema is proposed to generate association rules. The extracted knowledge is intended to interpret the remainder component extracted during the previous phase by discovering the hidden link between random variation and climate observations. For validation purpose, a database covering the regions in Northwestern Tunisia is used for a period starting from 2000 to 2012. The data have been derived from Moderate resolution Imaging Spectroradiometer and fused with ground climate data (temperature and precipitation) in the form of fuzzy association rules. The obtained results show the efficiency of the proposed approach by reducing the non-stationarity effect.

National audience; This thesis is interested in the relationship between expres- sivity and simplicity in the context of illustrations production. More precisely, it focuses on the design of systems and workflows allowing novice users to produce illustrations in an easier and faster way with a high level of expressivity while still allowing experts users to boost their production performance.; Cette thèse s’intéresse à la relation entre expressivité et simplicité dans un contexte de production d’illustrations. Plus précisément, elle se concentre sur le design de sys- tèmes et techniques permettant aux utilisateurs novices de facilement et rapidement produire des illustrations avec un haut niveau d’expression tout en permettant aux utilisateurs experts d’augmenter leur performance.

National audience; The advent of autonomous vehicles is leading to deep changes in the automotive sector for the next decade. As one of the few ways to test an autonomous vehicle, road traffic simulators take a new lease of life. However, traffic generators do not consider crashes : the tested vehicle's behavior cannot face unforeseen cases. We state that it is a major issue and we propose a para-metric model leading to traffic generation characterized by a wide behavioral spectrum. Instead of planned crashes, this model allows the emergence of crashes due to interactions among vehicles. After a description of the behavioral model, we show that simulations are able to exhibit stylized facts recognized in this field.; Avec l'avènement du véhicule autonome et la mutation que va connaître le secteur automobile dans les dix prochaines années, la simulation de trafic routier a pris un nouvel essor. C'est notamment l'un des rares moyens pour tester un véhicule autonome in silico [7]. Pour y parvenir, les générateurs actuels doivent augmenter leur réalisme. Nous soutenons ici que l'un des points majeurs de ce réalisme concerne la capacité des générateurs à produire des accidents dans l'environnement du véhicule testé. À notre connaissance, aucun des générateurs existants ne prend en compte cette considération nécessitant une description plus fine que celle habituellement utilisée pour décrire le comporte-ment de conduite. Nous décrivons dans cet article un modèle de comportement paramétrique permettant une telle performance, et montrons qu'il répond aux faits stylisés reconnus en accidentologie.

Many studies aim at introducing recent technologies in Electric Vehicles (EVs) to accurately estimate their energy consumption. In this paper, we reviewed the current energy consumption model in SUMO. This latter is known to be the most reliable traffic simulator used for evaluating traffic management and vehicular technologies. We proposed a set of improvements that must be applied on SUMO energy model and we focused on integrating the ambient temperature factor. Finally, simulation results show the accuracy of the proposed solution from different perspectives.

International audience; Multi-source observed data are generally characterized by their syntactic, structural and semantic heterogeneities. A key challenge is the semantic interoperability of these data. In this context, we propose an ontology-based system that supports environmental monitoring. Our contributions could be resumed around 1) the construction of an ontology which allows to represent the knowledge and reuse it in a real-world way, 2) the guarantee of the semantic interoperability of ontological modules since the proposed ontology is based on the upper level ontology Basic Formal Ontology (BFO) 3) the modularity of the proposed ontology in order to facilitate its reuse and evolution. The proposed ontology has been implemented and evaluated using quality metrics. We also present a real use case study that demonstrates how the proposed ontology allows implicit knowledge generation.

International audience; In this paper, we design and experiment ODYSSE (Opportunistic Duty cYcle based routing protocol for wirelesS Sensor nEtworks) protocol. It combines three main mechanisms: (i) duty cycle, where nodes alternate between active and sleep states, (ii) opportunistic routing where routing tables do not exist and the next hop is elected once the packet arrives, and (iii) source coding with LDPC (Low-Density Parity-Check) codes in order to face packet losses while minimizing energy consumption. We focus on two heterogeneous scenarios: bulk image transmission and infrequent events reporting. Modeling the average waiting delay of forwarders, we show that simple relay selection strategies are effective. We used 45 Arduino nodes communicating with IEEE 802.15.4 (XBee) within the large platform FIT IoT-LAB (IoT-LAB is part of the large platform FIT: Future Internet of Things). We implement and extensively study the behavior and performance of our proposal ODYSSE. We show that the three techniques fit perfectly, yielding a robust low complexity protocol for highly constrained nodes in typical IoT applications.

International audience; This paper addresses the problem of human action recognition from sequences of 3D skeleton data. For this purpose, we combine a deep learning network with geometric features extracted from data lie on a non-Euclidean space, which have been recently shown to be very effective to capture the geometric structure of the human pose. In particular, our approach claims to incorporate the intrinsic nature of the data characterized by Lie Group into deep neural networks and to learn more adequate geometric features for 3D action recognition problem. First, geometric features are extracted from 3D joints of skeleton sequences using the Lie group representation. Then, the network model is built from stacked units of 1-dimensional CNN across the temporal domain. Finally, CNN-features are then used to train an LSTM layer to model dependencies in the temporal domain, and to perform the action recognition. The experimental evaluation is performed on three public datasets containing various challenges: UT-Kinect, Florence 3D-Action and MSR-Action 3D. Results reveal that our approach achieves most of the state-of-the-art performance.

International audience; In this paper we tackle the problem of data analysis on high dimensional space of hyperspectral images. The remote sensing data analysis is a complex task due to many factors such as the large spectral and spatial variability. In fact, several approaches suffer from the pixel-mixed problem since mixed pixels are often sources of uncertainty and inaccuracy. Although spectral un-mixing techniques can provide abundance fractions for each class in mixed pixels, spatial distribution of these classes remains still unknown. Sub-pixel mapping techniques provide any solutions to the above-mentioned problem. Nevertheless, most of the proposed methods treat one particular type of objects because they assume that mixed pixels in a single image are identical. Sub-pixel mapping methods employing zonal objects are based on the spatial dependence assumption; the same assumption is used for linear objects while considering objects direction. Whereas, in case of encapsulated objects no spatial correlation is applied. As a result, each type of object requires special treatment, hence, the need for object recognition at sub-pixel scales. In this paper to improve sub-pixel object recognition accuracy in coarse spatial resolution image, we develop in this paper a spectro-spatial method based on a graph model, which discriminates between each type of sub-pixel object. The latter is classified into three categories: zonal, linear and small encapsulated objects based on their spatial information in neighboring pixels and their spectral information. In order to determine the suitability and the effectiveness of the proposed approach, experiments are performed with a simulated and a real hyperspectral image.

Data lakes have recently emerged as an alternative solution to costly traditional data warehouse solutions. To exploit data lakes, however, there is a need for means that assist users in combining and integrating data stored within a data lake. In this paper, we position ourselves in the recurrent context where a user has a local dataset that is not sufficient for processing the queries that are of interest to him/her. We show how data lakes, or more specifically the service lakes, since we are focusing on data providing services, can be leveraged to answer user queries, taking into account the quality of the services and respecting the (time and monetary) budget set by the user.

Wireless Body Area Networks are nowadays attracting both academic and industrial worlds. Combining collected data related to patient context with original health measurement can enhance the general health state monitoring and help to better understand the patient disease evolution. Daily activity is one of the important features that may influence the patient health state. Thus, recognizing the user activity can be a useful way for improving quality of health services. Relying on supervised learning, we study the feasibility of extracting and classifying the human activities from channel gain measures, which is an important feature that characterizes the WBAN channel links.

The attempts to reduce vehicle’s CO2 emissions and fuel consumption are actually motivating the manufacturers in the transport and automotive sectors to focus their interests on Electric Vehicle (EV) concept. Battery autonomy and charging process are still a big issue for that kind of vehicles. The evaluation of EV’s instantaneous energy consumption through realistic scenarios and based on consistent energy models are needed to take step forward on these issues. In this paper, we provide a deep insight on EV consumption dynamics and make a review of the energy model implemented in SUMO, one of the most popular traffic simulation framework used to evaluate vehicular technologies and strategies. We propose a set of energy consumption estimation improvements and show through simulation the achieved improvements in terms of accuracy compared to the sumo implementation.

In this paper, we propose a joint power control and resource allocation approach for co-channel deployed high dense small-cells in macro-cell networks, denoted as Two-tier Optimized Resource and Power Allocation approach (TORPA). The ultimate goal of our contribution is to mitigate the co-tier and cross-tier interference faced by indoor and outdoor users in downlink communications and efficiently satisfy their resource requirements. With this in mind, we formulate the resulting optimization problem as a Mixed-Integer Linear Program (MILP) that aims to minimize the total transmit power and achieve an efficient two-tier physical resource allocation. Then, we propose a semi-centralized scheme to solve it. Extensive simulations show that TORPA can efficiently allocate power and distribute spectrum resources to both Small-cell Users (SUs) and Macro-Users (MUs) compared to the distributed resource allocation scheme and a prominent state of the art gametheoretic approach. In particular, TORPA improves the SU’s throughput by up to 9 times and 22% in comparison to these both schemes.

International audience; Land cover change (LCC) models aim to track spatiotemporal changes made in land cover. In most cases, LCC models contain uncertainties in their main components (i.e., input parameters and model structure). These uncertainties propagate through the modeling system, which generates uncertainties in the model outputs. The aim of this manuscript is to propose an approach to reduce uncertainty of LCC prediction models. The main objective of the proposed approach is to apply a sensitivity analysis method, based on belief function theory, to determine parameters and structures that have a high contribution in the variability of the predictions of the LCC model. Our approach is applied to four common LCC models (i.e., DINAMICA, SLEUTH, CA-MARKOV, and LCM). Results show that uncertainty of the model parameters and structure has meaningful impacts on the final decisions of LCC models. Ignoring this uncertainty can lead to erroneous decision about land changes. Therefore, the presented approach is very useful to identify the most relevant uncertainty sources that need to be processed to improve the accuracy of LCC models. The applicability and effectiveness of the proposed approach are demonstrated through a case study based on the Cairo region. Results show that 13% of the agriculture and 3.8% of the desert lands in 2014 would be converted to urban areas in 2025.

International audience; The standard IEEE 802.11p was proposed to support the rapid exchange of data between the vehicles themselves and between the vehicles and the RSU (Road Side Unit). Besides, the Medium Access Control (MAC) protocols in Vehicular Ad-hoc Network (VANET), presented in the literature, have many weaknesses in supporting real time traffic. Indeed, some of them combine the advantage of TDMA with CSMA/CA to organize the channel access, therefore collisions may occur when safety messages are transmitted. In the context of hard real time, meeting deadlines requires prior knowledge of the possible communications between vehicles. Thus, we introduce an extension of the Enhanced Distributed Channel Access (EDCA) defined in IEEE 802.11p combined with TDMA, called Qos-aware Centralized Hybrid MAC protocol (QCHMAC). To evaluate our proposed protocol, we implemented it in ns-3 and we used the simulator SUMO to generate vehicular mobility traces. The simulation results reveal that QCH-MAC significantly outperforms pure TDMA in terms of transmission delay, packet loss rate and network throughput

International audience; Leishmania (L.) infantum-infected dogs may present with a large range of clinical signs, from apparently healthy with no or few (asymptomatic dogs, AD) to several clinical signs indicators of active infection (symptomatic dogs, SD). The present study is justified by the conflicting reports describing that either L. infantum-specific IgG1 or IgG2 antibodies may be used as isotype marker of the asymptomatic infection status and by the lack, to our knowledge, of previous analysis of the IgG sub-classes autoantibody repertoires of Leishmania-infected dogs. On the basis of clinical evaluation and laboratory testing (IFAT, parasitological examination of Giemsa-stained lymph node smears, L. infantum antigens-ELISA of total (Tot) IgG), 131 dogs were categorized as SD, asymptomatic seronegative (AND) or seropositive dogs (APD) from surrounding areas, and as negative control dogs (CTD). ELISA based on leishmanial native antigens or recombinant LACK and LeIF proteins showed that SD produce higher levels of specific Tot IgG, IgG1 and IgG2 antibodies than APD, and that for both clinical stages, the antibody titers of IgG2 isotype were constantly higher than those of the IgG1. The seroprevalences of Tot IgG, IgG2 did not differ between APD and SD groups (97 and 97% in SD; 100 and 96% in APD, respectively) whereas that of IgG1 was slightly lower in SD (88% of APD versus 82% of SD). The autoantibody repertoires were analyzed by ELISA using HEp-2 extracts, ds-DNA, human albumin and transferrin as self-antigens and by Western blot using HEp-2 proteins. ELISA results' indicated that APD develop higher levels of IgG1 autoantibodies, and higher seroprevalence (50% and 26% in APD and SD, respectively), contrasting with lower levels and seroprevalences of Tot IgG and IgG2 (43 and 68% for APD; 100 and 74% for SD). Interestingly, SD showed a stronger IgG1 and particularly IgG2 reactivity with transferrin, an iron-binding protein, than APD and AND. Western blotting experiments produced heterogeneous IgG1 and IgG2 inter- and intra-groups reactivity profiles towards HEp-2 proteins, to identify a specific antigenic profile. Generated data from competitive HEp-2-ELISA using leishmanial antigens as inhibitors were in favor that IgG1 antibodies are predominantly autoantibodies to self-antigens in APD whereas they are mainly cross-reactive (Leishmania/self-antigens) in SD.

National audience; Dans une grammaire formelle, le lien entre l’information sémantique et sa structure syntaxique correspondante peut être établi en utilisant une interface syntaxe/sémantique qui permettra la construction du sens de la phrase. L'étiquetage de rôles sémantiques aide à réaliser cette tâche en associant automatiquement des rôles sémantiques à chaque argument du prédicat d’une phrase. Dans ce papier, nous présentons une nouvelle approche qui permet la construction d’une telle interface pour une grammaire d’arbres adjoints de l’arabe. Cette grammaire a été générée semi automatiquement à partir d’une méta-grammaire. Nous détaillons le processus d’interfaçage entre le niveau syntaxique et le niveau sémantique moyennant la sémantique des cadres et comment avons-nous procédé à l’étiquetage de rôles sémantiques en utilisant la ressource lexicale ArabicVerbNet.

International audience; Hyperspectral imagery is widely used for the identification and monitoring of earth surface, which in turn need good classification performances. However, the high spectral dimensionality of hyperspectral images degrades classification accuracy and increases computational complexity. To overcome these issues, dimensionality reduction has become an essential preprocessing step in order to enhance classifiers performances using hyperspectral images. Dimensionality reduction tackles the problem of the high dimensionality, but also the high correlation between the spectral bands of hyperspectral images. In this paper, we first review the main dimensionality reduction approaches and compare their performances when used for the classification task using the Support Vector Machines classifier. We also propose a combination of feature extraction and band selection for classification. We report the performances of all these methods using real hyperspectral images and show their efficiency for hyperspectral image classification.

International audience; Today's sensors are like eyes in the sky, thanks to the growth of satellite remote sensing technologies. Therefore, we see a steady evolution of the usage of different types of sensor, from airborne and satellites platforms which are generating large quantities of remote sensing image for divers applications such as; smart city, disaster management, military intelligence and others. As a result, the rate of growth in the amount of data by satellite is increasing dramatically. The velocity has exceeded 1TB per day and it will certainly increase in the future. However, it becomes crucial for these huge volume data to be stored. So, how to store and manage it efficiently becomes a real challenge because traditional ways have intensive issues; they are expensive and difficult to extend. Therefore, we need some scalable and parallel models for remote sensing data storage and processing. In this paper, we describe a scalable and distributed architecture for massive remote sensing data storage based on three No SQL databases (Apache Cassandra, Apache HBase, MongoBD). Also, a Hadoop-based framework is proposed to manage the big remote sensing data in a distributed and parallel manner.

International audience; Providing a mechanism for modeling and reasoning about the dynamics of geographic spatio-temporal objects is a challenge issue and main problem due to the complex characteristics describing these objects. A spatio-temporal geographical entity is defined as a set composed by spatial, temporal and semantic (thematic) dimensions, of which various types of relationships can be specified. Changes in the state of each component are the result of geographic events and processes that may occur. Remotely sensed images provide measurements and observations that can be used for the interpretation of dynamic spatio-temporal objects. The observed proprieties are used to classify geographic objects and monitor change that occurs in such object. The intended paper focuses to model the dynamics of spatio-temporal object from a remote sensing observation viewpoint. Dynamic, here, is represented in term of events such as reduction and expansion, split and merging, etc. and in term of geographic processes such as deforestation and urbanization. To achieve this purpose, we exploit the description logic extended to a semantic spatio-temporal concrete domain as a mechanism for semantic-spatio-temporal reasoning and dynamic representation.

International audience; Hyperspectral imagery (HSI) is widely used for several fields of remote sensing such as agriculture, land cover monitoring, and deforestation. However, the HSI classification is a challenge task due to the large number of spectral bands, unavailability of training samples, and the high correlation inter-bands. To address these challenges, we propose in this work a semantic reduction dimensionality approach based on the principal component analysis (PCA) and mutual information-based band selection (MI). Firstly, we project the original HSI using PCA to obtain a novel subspace with lower dimensions. Using the obtained components, a set of rules can be generated to find the relevant spectral bands based on score contribution coefficient. Moreover, the mutual information (MI) is used to select the spectral bands that contain a higher information based on the entropy criterion. We propose then to exploit the selected bands for HSI classification using SVM technique. Experiment results demonstrate that our proposed approach is effective and perform for HSI classification compared to other dimensionality reduction approaches.

International audience; Arabic is a challenging language when it comes to grammar production and parsing. It combines complex linguistic phenomena with a rich morphology that make its processing particularly ambiguous. This leaded us to choose the Tree-Adjoining Grammar (TAG) formalism. Indeed, TAG provides sufficient constraints for handling diverse linguistic phenomena and seems to be adequate to represent Arabic syntactic structures. In this paper, we present a semi-automatically generated TAG for modern standard Arabic using a compiler and a metagrammatical description language called XMG (eXtensible MetaGrammar). We focus on the linguistic coverage of our grammar, and show how we used TAG and XMG’s properties to define in an expressive and concise way different linguistic phenomena. To check the coverage of our grammar, we have set up a development environment including a parser and using a test corpus of linguistic phenomena gathering both grammatical and ungrammatical sentences.

An online reinforcement learning algorithm is anytime if it does not need to know in advance the horizon T of the experiment. A well-known technique to obtain an anytime algorithm from any non-anytime algorithm is the "Doubling Trick". In the context of adversarial or stochastic multi-armed bandits, the performance of an algorithm is measured by its regret, and we study two families of sequences of growing horizons (geometric and exponential) to generalize previously known results that certain doubling tricks can be used to conserve certain regret bounds. In a broad setting, we prove that a geometric doubling trick can be used to conserve (minimax) bounds in $R_T = O(\sqrt{T})$ but cannot conserve (distribution-dependent) bounds in $R_T = O(\log T)$. We give insights as to why exponential doubling tricks may be better, as they conserve bounds in $R_T = O(\log T)$, and are close to conserving bounds in $R_T = O(\sqrt{T})$.; Un algorithme en ligne d'apprentissage par renforcement est dit "à tout moment" (anytime) s'il n'a pas besoin de connaître à l'avance l'horizon T de l'expérience. Une technique bien connue pour obtenir un algorithme à tout moment à partir d'un algorithme qui ne l'est pas est "l'astuce de doublement" (Doubling Trick). Dans le contexte des bandits multi-bras adverses ou stochastiques, la performance d'un algorithme est mesurée par son regret, et nous étudions deux familles de séquences d'horizons croissants (géométrique et exponentielle), pour généraliser des résultats précédemment connus que certaines astuces de doublement peuvent être utilisées pour conserver certaines limites de regret. Dans un cadre très générique, nous prouvons qu'une astuce géométrique de doublement peut être utilisée pour conserver les bornes (minimax) en $R_T = O(\sqrt{T})$ mais ne peut pas conserver les bornes (dépendantes de la distribution) en $R_T = O(\log T)$. Nous donnons un aperçu des raisons pour lesquelles les astuces de doublage exponentiel peuvent être meilleures, car elles conservent les bornes en $R_T = O(\log T)$, et sont proches de conserver les bornes en $R_T = O(\sqrt{T}$).

An online reinforcement learning algorithm is anytime if it does not need to know in advance the horizon T of the experiment. A well-known technique to obtain an anytime algorithm from any non-anytime algorithm is the "Doubling Trick". In the context of adversarial or stochastic multi-armed bandits, the performance of an algorithm is measured by its regret, and we study two families of sequences of growing horizons (geometric and exponential) to generalize previously known results that certain doubling tricks can be used to conserve certain regret bounds. In a broad setting, we prove that a geometric doubling trick can be used to conserve (minimax) bounds in $R_T = O(\sqrt{T})$ but cannot conserve (distribution-dependent) bounds in $R_T = O(\log T)$. We give insights as to why exponential doubling tricks may be better, as they conserve bounds in $R_T = O(\log T)$, and are close to conserving bounds in $R_T = O(\sqrt{T})$.; Un algorithme en ligne d'apprentissage par renforcement est dit "à tout moment" (anytime) s'il n'a pas besoin de connaître à l'avance l'horizon T de l'expérience. Une technique bien connue pour obtenir un algorithme à tout moment à partir d'un algorithme qui ne l'est pas est "l'astuce de doublement" (Doubling Trick). Dans le contexte des bandits multi-bras adverses ou stochastiques, la performance d'un algorithme est mesurée par son regret, et nous étudions deux familles de séquences d'horizons croissants (géométrique et exponentielle), pour généraliser des résultats précédemment connus que certaines astuces de doublement peuvent être utilisées pour conserver certaines limites de regret. Dans un cadre très générique, nous prouvons qu'une astuce géométrique de doublement peut être utilisée pour conserver les bornes (minimax) en $R_T = O(\sqrt{T})$ mais ne peut pas conserver les bornes (dépendantes de la distribution) en $R_T = O(\log T)$. Nous donnons un aperçu des raisons pour lesquelles les astuces de doublage exponentiel peuvent être meilleures, car elles conservent les bornes en $R_T = O(\log T)$, et sont proches de conserver les bornes en $R_T = O(\sqrt{T}$).

International audience; Hybrid clouds are increasingly used to outsource non-critical applications to public clouds. However, the main challenge within such environments, is to ensure a cost-efficient distribution of the systems between the resources that are on/off premises. For Multi Agent Systems (MAS), this challenge is deepened due to irregular workload progress and intensive communication between the agents, which may result in high computing and data transfer costs. Thus, in this paper we propose a generic framework for adaptive cost-efficient deployment of MAS with a special focus on hybrid clouds. The framework is based mainly on the use of a performance evaluation process that consists of simulating various partitioning options to estimate and optimize the overall deployment costs. Further, to cope with the irregular workload changes within a MAS and dynamically adapt its initial deployment, we propose an extended version of the Fiduccia-Mattheyses algorithm (E-FM). The experimental results highlight the efficiency of E-FM and show that an efficient MAS deployment to hybrid clouds depends on various factors such as the cloud providers and their different cost-models, the network state, the used partitioning algorithm, and the initial deployment.

International audience; A fundamental objective of remote sensing imagery is to spread out the knowledge about our environment and to facilitate the interpretation of different phenomena affecting the Earth's surface. The main goal of this chapter is to understand and interpret possible changes in order to define subsequently strategies and adequate decision-making for a better soil management and protection. Consequently, the semantic interpretation of remote sensing data, which consists of extracting useful information from image date for attaching semantics to the observed phenomenon, allows easy understanding and interpretation of such occurring changes. However, performing change interpretation task is not only based on the perceptual information derived from data but also based on additional knowledge sources such as a prior and contextual. This knowledge needs to be encoded in an appropriate way for being used as a guide in the interpretation process. On the other hand, interpretation may take place at several levels of complexity from the simple recognition of objects on the analyzed scene to the inference of site conditions and to change interpretation. This chapter presents semantic scenes analysis for change interpretation strategy in remote sensing imagery. The presented strategy is composed of different levels of interpretation. For each level, information elements such as data, information, and knowledge need to be represented and characterized. This chapter highlights the importance of ontologies exploiting for encoding the domain knowledge and for using it as a guide in the semantic scene interpretation task.

International audience; In this paper, we define a cluster based scheduling algorithm for Cognitive Radio Sensor Networks (CRSNs). To avoid inter-clusters collision, we assign fixed channels only to nodes having one-hop neighbors out of their clusters. We denote these nodes as specific nodes. Previous studies assign distinct channels to whole neighbor clusters to avoid inter-clusters collision. Our objective is to optimize the spatial reuse and to increase the network throughput while saving sensors energy. We start by assigning channels only to the specific nodes. Once the problem of inter-clusters collision is solved, each cluster head (CH) schedules the transmissions in its cluster independently. For the cluster members that are specific nodes, the CH assigns only time slots because the channel assignment is already done. For other cluster members (CMs) (not specific nodes), the CH assigns the pair (channel, slot). Two solutions are proposed in this paper to schedule the CMs: The Frame Intra Cluster Multichannel Scheduling algorithm denoted Frame-ICMS and the Slot Intra Cluster Multichannel Scheduling algorithm denoted Slot-ICMS. We evaluate the performance of these algorithms in case of accurate PUs activity detection and in case of bad PUs activity estimation. We prove that our proposals outperform an existing one especially in terms of energy saving.

Extended version of a paper presented at ACIT 2017. Full text available at https://iajit.org/portal/PDF/Special%20Issue%202018,%20No.%203A/17414.pdf; International audience; Syntactic and semantic resources play an important role for various Natural Language Processing (NLP) tasks by providing information about the correct structural representations of the sentences and their meaning. To date, there is not a wide-coverage electronic grammar for the Arabic language. In this context, we present a new approach for building a tree adjoining grammar to represent the syntax and the semantic of modern standard Arabic. This grammar is produced semi-automatically with the XMG (eXtensible MetaGrammar) description language. First the syntax of Arabic is described using the defined Arab-XMG meta-grammar. Then semantic information is added by introducing semantic frame-based dimension into the meta-grammar. This is achieved by exploiting lexical resources such as Arabic VerbNet. Finally, the link between semantic and syntax is established using a syntax-semantic interface that allows the construction of sentence meaning through semantic role labeling. Experiments were performed to check grammar coverage as well as the syntactic-semantic analysis. The results showed that the generated grammar can cover the basic syntactic structures of Arabic sentences and the different phrasal structures with a precision rate of about 92%. Moreover, it confirms the effectiveness of the proposed approach as we were able to parse semantically a set of sentences and build their semantic representations with a precision rate of about 72%.