Publications

2019

• Statistical model of the human RF exposure in small cell environment
  
  • Chobineh A.
  • Huang Y.
  • Mazloum T.
  • Conil E.
  • Wiart J.
  Annals of Telecommunications - annales des télécommunications, Springer, 2019, 74 (1-2), pp.103-112. (10.1007/s12243-018-0677-9)
  DOI : 10.1007/s12243-018-0677-9
• Multi-objective exploration of architectural designs by composition of model transformations
  
  • Rahmoun Smail
  • Mehiaoui-Hamitou Asma
  • Borde Etienne
  • Pautet Laurent
  • Soubiran Elie
  Software and Systems Modeling, Springer Verlag, 2019, 18 (1), pp.107–127. Designing software architectures and optimizing them based on extra-functional properties (EFPs) require to identify appropriate design decisions and to apply them on valid architectural elements. Software designers have to check whether the resulting architecture fulfills the requirements and how it positively improves (possibly conflicting) EFPs. In practice, they apply well-known solutions such as design patterns manually. This is time-consuming, error-prone, and possibly sub-optimal. Well-established approaches automate the search of the design space for an optimal solution. They are based model-driven engineering techniques that formalized design decisions as model transformations and architectural elements as components. Using multi-objective optimizations techniques, they explore the design space by randomly selecting a set of components and applying to them variation operators that include a fixed set of predefined design decisions. In this work, we claim that the design space exploration requires to reason on both architectural components as well as model transformations. More specifically, we focus on possible instantiations of model transformations materialized as the application of model transformation alternatives on a set of architectural components. This approach was prototyped in RAMSES, a model transformation and code generation framework. Experimental results show the capability of our approach (i) to combine evolutionary algorithms and model transformation techniques to explore efficiently a set of architectural alternatives with conflicting EFPs, (ii) to instantiate, and select transformation instances that generate architectures satisfying stringent structural constraints, and (iii) to explore design spaces by chaining more than one transformation. In particular, we evaluated our approach on EFPs, architectures, and design alternatives inspired from the railway industry by chaining model transformations dedicated to implement safety design patterns and software components allocation on a multi-processor hardware platform. (10.1007/s10270-017-0580-2)
  DOI : 10.1007/s10270-017-0580-2
• General stochastic reverberation model
  
  • Badeau Roland
  , 2019. In a recent research paper, we proposed a common mathematical framework for stochastic reverberation models, that aimed to unify several well-known results regarding the statistical properties of reverberation, in the spatial, spectral and temporal domains. This model was dedicated to diffuse (i.e. isotropic and uniform) acoustic fields, omnidirectional sources and microphones, and constant attenuation coefficients w.r.t. the frequency. In this technical report, we introduce several extensions of this model, that aim to model reverberation more realistically, by considering anisotropic and non-uniform acoustic fields, directive sources and microphones, and frequency-varying attenuation coefficients.
• Interchange Fees and Innovation in Payment Systems
  
  • Bourreau Marc
  • Verdier Marianne
  Review of Industrial Organization, Springer US, 2019, 54 (1), pp.129-158. (10.1007/s11151-018-9648-6)
  DOI : 10.1007/s11151-018-9648-6
• Brain SAR of average male Korean child to adult models for mobile phone exposure assessment
  
  • Lee Ae-Kyoung
  • Park Jin Seo
  • Hong Seon-Eui
  • Taki Masao
  • Wake Kanako
  • Wiart Joe
  • Choi Hyung-Do
  Physics in Medicine and Biology, IOP Publishing, 2019, 64 (4), pp.045004. (10.1088/1361-6560/aafcdc)
  DOI : 10.1088/1361-6560/aafcdc
• Translation of ATL to AGT and application to a code generator for Simulink
  
  • Richa Elie
  • Borde Etienne
  • Pautet Laurent
  Software and Systems Modeling, Springer Verlag, 2019, 18 (1), pp.321-344. (10.1007/s10270-017-0607-8)
  DOI : 10.1007/s10270-017-0607-8
• Reconstruction of Internal Field of Dielectric Objects for Noninvasive SAR Measurement Using Boundary Integral Equation
  
  • Omi Shuntaro
  • Uno Toru
  • Arima Takuji
  • Wiart Joe
  IEEE Transactions on Electromagnetic Compatibility, Institute of Electrical and Electronics Engineers, 2019, 61 (1), pp.48-56. Reconstruction of the electromagnetic (EM) fields inside a dielectric object is investigated in order to develop a noninvasive specific absorption rate measurement. The proposed reconstruction method is based on the boundary integral equation (BIE) derived from the surface equivalence theorem that relates the equivalent EM currents on the surface enclosing the primary source to the radiated external fields. The EM currents are reconstructed by solving the discretized BIE using the field data sampled on the surface surrounding all of the target objects that consist of the dielectric phantom and radiating antenna. The field distribution inside the dielectric object is obtained from the reconstructed currents. A probe correction technique is also proposed to enable the application of this method to practical probe measurements. As the first step to the practical applications, the validity and usefulness of the proposed method are demonstrated numerically and experimentally using lossless and lossy homogeneous dielectric objects located near a dipole antenna, respectively. It is shown that the accuracy tends to deteriorate in the case of the lossy phantom, but this can easily be improved without significant modification of the proposed method. (10.1109/TEMC.2018.2813398)
  DOI : 10.1109/TEMC.2018.2813398
• 3D segmentation of pelvic structures in pediatric MRI for surgical planning applications
  
  • Virzì Alessio
  , 2019. Surgical planning relies on the patient’s anatomy, and it is often based on medical images acquired before the surgery. This is in particular the case for pelvic surgery on children, for various indications such as malformations or tumors. In this particular anatomical region, due to its high vascularization and innervation, a good surgical planning is extremely important to avoid potential functional damages to the patient’s organs that could strongly affect their quality of life. In clinical practice the standard procedure is still to visually analyze, slice by slice, the images of the pelvic region. This task, even if quite easily performed by the expert radiologists, is difficult and tedious for the surgeons due to the complexity and variability of the anatomical structures and hence their images. Moreover, due to specific anatomy depending on the age of the patient, all the difficulties of the surgical planning are emphasized in the case of children, and a clear anatomical understanding is even more important than for the adults. For these reasons, it is very important and challenging to provide the surgeons with patient-specific 3D reconstructions, obtained from the segmentation of MRI images. In this work we propose a set of segmentation tools for pelvic MRI images of pediatric patients. In particular, we focus on three important pelvic structures: the pelvic bones, the pelvic vessels and the urinary bladder. For pelvic bones, we propose a semi-automatic approach based on template registration and deformable models. The main contribution of the proposed method is the introduction of a set of bones templates for different age ranges, which allows us to take into account the bones variability during growth. For vessels segmentation, we propose a patch-based deep learning approach using transfer learning, thus requiring few training data. The main contribution of this work is the design of a semi-automatic strategy for patches extraction, which allows the user to focus only on the vessels of interest for surgical planning. For bladder segmentation, we propose to use a deformable model approach that is particularly robust to image inhomogeneities and partial volume effects, which are often present in pediatric MRI images. All the developed segmentation methods are integrated in an open-source platform for medical imaging, delivering powerful tools and user-friendly GUIs to the surgeons. Furthermore, we set up a processing and portability workflow for visualization of the 3D patient specific models, allowing surgeons to generate, visualize and share within the hospital the patient specific 3D models. Finally, the results obtained with the proposed methods are quantitatively and qualitatively evaluated by pediatric surgeons, which demonstrates their potentials for clinical use in surgical planning procedures.
• Memory aware physically enhanced polynomial model for PAs
  
  • Soleiman Elias
  • Germain Pham Dang-Kièn
  • Jabbour Chadi
  • Desgreys Patricia
  • Kamarei Mahmoud
  IET Microwaves Antennas and Propagation, Institution of Engineering and Technology, 2019. (10.1049/iet-map.2018.5411)
  DOI : 10.1049/iet-map.2018.5411
• Deployment of mixed criticality and data driven systems on multi-cores architectures
  
  • Medina Roberto
  , 2019. Nowadays, the design of modern Safety-critical systems is pushing towards the integration of multiple system components onto a single shared computation platform. Mixed-Criticality Systems in particular allow critical components with a high degree of confidence (i.e. low probability of failure) to share computation resources with less/non-critical components without requiring software isolation mechanisms (as opposed to partitioned systems).Traditionally, safety-critical systems have been conceived using models of computations like data-flow graphs and real-time scheduling to obtain logical and temporal correctness. Nonetheless, resources given to data-flow representations and real-time scheduling techniques are based on worst-case analysis which often leads to an under-utilization of the computation capacity. The allocated resources are not always completely used. This under-utilization becomes more notorious for multi-core architectures where the difference between best and worst-case performance is more significant.The mixed-criticality execution model proposes a solution to the abovementioned problem. To efficiently allocate resources while ensuring safe execution of the most critical components, resources are allocated in function of the operational mode the system is in. As long as sufficient processing capabilities are available to respect deadlines, the system remains in a ‘low-criticality’ operational mode. Nonetheless, if the system demand increases, critical components are prioritized to meet their deadlines, their computation resources are increased and less/non-critical components are potentially penalized. The system is said to transition to a ‘high-criticality’ operational mode.Yet, the incorporation of mixed-criticality aspects into the data-flow model of computation is a very difficult problem as it requires to define new scheduling methods capable of handling precedence constraints and variations in timing budgets.Although mixed-criticality scheduling has been well studied for single and multi-core platforms, the problem of data-dependencies in multi-core platforms has been rarely considered. Existing methods lead to poor resource usage which contradicts the main purpose of mixed-criticality. For this reason, our first objective focuses on designing new efficient scheduling methods for data-driven mixed-criticality systems. We define a meta-heuristic producing scheduling tables for all operational modes of the system. These tables are proven to be correct, i.e. when the system demand increases, critical components will never miss a deadline. Two implementations based on existing preemptive global algorithms were developed to gain in schedulability and resource usage. In some cases these implementations schedule more than 60% of systems compared to existing approaches.While the mixed-criticality model claims that critical and non-critical components can share the same computation platform, the interruption of non-critical components degrades their availability significantly. This is a problem since non-critical components need to deliver a minimum service guarantee. In fact, recent works in mixed-criticality have recognized this limitation. For this reason, we define methods to evaluate the availability of non-critical components. To our knowledge, our evaluations are the first ones capable of quantifying availability. We also propose enhancements compatible with our scheduling methods, limiting the impact that critical components have on non-critical ones. These enhancements are evaluated thanks to probabilistic automata and have shown a considerable improvement in availability, e.g. improvements of over 2% in a context where 10-9 increases are significant.Our contributions have been integrated into an open-source framework. This tool also provides an unbiased generator used to perform evaluations of scheduling methods for data-driven mixed-criticality systems.
• On Fair Cost Sharing Games in Machine Learning
  
  • Redko Ievgen
  • Laclau Charlotte
  , 2019, 33 (01), pp.4790-4797. Machine learning and game theory are known to exhibit a very strong link as they mutually provide each other with solutions and models allowing to study and analyze the optimal behaviour of a set of agents. In this paper, we take a closer look at a special class of games, known as fair cost sharing games, from a machine learning perspective. We show that this particular kind of games, where agents can choose between selfish behaviour and cooperation with shared costs, has a natural link to several machine learning scenarios including collaborative learning with homogeneous and heterogeneous sources of data. We further demonstrate how the game-theoretical results bounding the ratio between the best Nash equilibrium (or its approximate counterpart) and the optimal solution of a given game can be used to provide the upper bound of the gain achievable by the collaborative learning expressed as the expected risk and the sample complexity for homogeneous and heterogeneous cases, respectively. We believe that the established link can spur many possible future implications for other learning scenarios as well, with privacy-aware learning being among the most noticeable examples . (10.1609/aaai.v33i01.33014790)
  DOI : 10.1609/aaai.v33i01.33014790
• Querying Attributed DL-Lite Ontologies Using Provenance Semirings
  
  • Bourgaux Camille
  • Ozaki Ana
  , 2019. Attributed description logic is a recently proposed formalism, targeted for graph-based representation formats, which enriches description logic concepts and roles with finite sets of attribute-value pairs, called annotations. One of the most important uses of annotations is to record provenance information. In this work, we first investigate the complexity of satisfiability and query answering for attributed DL-LiteR ontologies. We then propose a new semantics, based on prove-nance semirings, for integrating provenance information with query answering. Finally, we establish complexity results for satisfiability and query answering under this semantics.
• HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews
  
  • Hemamou Léo
  • Felhi Ghazi
  • Vandenbussche Vincent
  • Martin Jean-Claude
  • Clavel Chloé
  , 2019, 33, pp.573-581. New technologies drastically change recruitment techniques. Some research projects aim at designing interactive systems that help candidates practice job interviews. Other studies aim at the automatic detection of social signals (e.g. smile, turn of speech, etc...) in videos of job interviews. These studies are limited with respect to the number of interviews they process, but also by the fact that they only analyze simulated job interviews (e.g. students pretending to apply for a fake position). Asynchronous video interviewing tools have become mature products on the human resources market, and thus, a popular step in the recruitment process. As part of a project to help recruiters, we collected a corpus of more than 7000 candidates having asynchronous video job interviews for real positions and recording videos of themselves answering a set of questions. We propose a new hierarchical attention model called HireNet that aims at predicting the hirability of the candidates as evaluated by recruiters. In HireNet, an interview is considered as a sequence of questions and answers containing salient socials signals. Two contextual sources of information are modeled in HireNet: the words contained in the question and in the job position. Our model achieves better F1-scores than previous approaches for each modality (verbal content, audio and video). Results from early and late multimodal fusion suggest that more sophisticated fusion schemes are needed to improve on the monomodal results. Finally, some examples of moments captured by the attention mechanisms suggest our model could potentially be used to help finding key moments in an asynchronous job interview. (10.1609/aaai.v33i01.3301573)
  DOI : 10.1609/aaai.v33i01.3301573
• Millimeter wave multi-RAT small cells for heterogeneous mobile services : performance analysis and optimization
  
  • Ghatak Gourab
  , 2019. Future wireless applications anticipate an explosion in the plethora of use-cases and services, which cannot be sustained by incremental improvements on the existing communication schemes. For this, two research directions are particularly attractive: network densification using small cells and millimeter wave (mm-wave) wave communications. In this thesis, we model and evaluate cellular networks consisting of multi-radio access technique (RAT) mm-wave small cells deployed on top of the legacy macro-architecture. First, we mathematically model a homogeneous deployment of multi-RAT small cells and characterize the user and network performance in terms of signal to interference plus noise ratio (SINR) coverage probability, downlink throughput, and the cell overloading probability. Then, we study users association to different tiers and optimal selection of different RATs, so as to optimize these performance metrics. Generally, cellular network models that assume homogeneous deployments of small cells fail to take into account the nuances of urban blockage characteristics. To address this, we model the small cell locations along the roads of a city, and subsequently, we take into consideration the signal blockages due to buildings or moving vehicles on the roads. In this network, we assume that the operator supports three types of services v.i.z., ultra-reliable low-latency communications (URLLC), massive machine-type communications (mMTC), and enhanced mobile broadband (eMBB) with different requirements. Consequently, we study the optimal RAT selection for these services with varying vehicular blockages. Finally, based on the on-road deployment model of mm-wave small cells, we study a network designed to support positioning and data services simultaneously. We characterize the positioning accuracy based on the localization bounds and then study optimal resource partitioning and beamwidth selection strategies to address varied positioning and data-rate requirements.
• On the use of U-Net for dominant melody estimation in polyphonic music
  
  • Doras Guillaume
  • Esling Philippe
  • Peeters Geoffroy
  , 2019. Estimation of dominant melody in polyphonic music remains a difficult task, even though promising breakthroughs have been done recently with the introduction of the Harmonic CQT and the use of fully convolutional networks. In this paper, we build upon this idea and describe how U-Net-a neural network originally designed for medical image segmentation-can be used to estimate the dominant melody in polyphonic audio. We propose in particular the use of an original layer-by-layer sequential training method, and show that this method used along with careful training data conditioning improve the results compared to plain convolutional networks.
• Security of Distance-Bounding: A Survey
  
  • Avoine Gildas
  • Munilla Jorge
  • Peinado Alberto
  • Rasmussen Kasper Bonne
  • Singelee Dave
  • Tchamkerten Aslan
  • Trujillo-Rasua Rolando
  • Vaudenay Serge
  • Bingöl Muhammed Ali
  • Boureanu Ioana
  • Čapkun Srdjan
  • Hancke Gerhard
  • Kardaş Süleyman
  • Kim Chong Hee
  • Lauradoux Cédric
  • Martin Benjamin
  ACM Computing Surveys, Association for Computing Machinery, 2019, 51 (5), pp.1-33. (10.1145/3264628)
  DOI : 10.1145/3264628
• Enabling Relevant Dialogue between Users and Autonomic Systems: a Design for Explainable AI for the Smart Home
  
  • Houzé Etienne
  • Diaconescu Ada
  • Dessalles Jean-Louis
  • Menga David
  , 2019.
• C-ITS PKI protocol: Performance Evaluation in a Real Environment
  
  • Haidar Farah
  • Kaiser Arnaud
  • Lonc Brigitte
  • Urien Pascal
  , 2019. In the near future, vehicles and roadside units (RSU) will communicate and cooperate by broadcasting V2X messages over the vehicular network (IEEE 802.11p). These messages are used by safety applications to improve road safety and traffic efficiency. However, those messages could also be used in a malicious way to track vehicles. Therefore, to guarantee drivers privacy, vehicles use pseudonym identities (or certificates) provided by a Public Key Infrastructure (PKI). During a trip, vehicles frequently change of certificates to make tracking much more difficult. They thus need to reload their certificates pool by requesting new ones to the PKI. In this paper, we evaluate the performance of the PKI protocol regarding the reloading of certificates. We ran several tests while driving in order to quantify the number of certificates that can be reloaded from the PKI at different speeds. The obtained results show that 1) the end-to-end latency between a requesting vehicle and the PKI is non-negligible and 2) as speed increases, the number of successfully reloaded certificates decreases.
• Modeling and Virtual Prototyping for Embedded Systems on Mixed-Signal Multicores
  
  • Cortés Porto Rodrigo
  • Genius Daniela
  • Apvrille Ludovic
  , 2019. This paper presents a tool for the virtual prototyping of analog and mixed-signal embedded (AMS) systems. The application and platform are modeled on a high (SysML-like) level, while the prototype is simulated on cycle-bit accurate level. In order to run software, we combine the AMS part with a multicore platform, which acts as initiator and controls the AMS part. The synchronization between these different Models of Computation (MoC) can be validated before the generation of the virtual prototype. We present a larger case study to illustrate our approach. (10.1145/3300189.3300193)
  DOI : 10.1145/3300189.3300193
• Multitemporal SAR images denoising and change detection : applications to Sentinel-1 data
  
  • Zhao Weiying
  , 2019. The inherent speckle which is attached to any coherent imaging system affects the analysis and interpretation of synthetic aperture radar (SAR) images. To take advantage of well-registered multi-temporal SAR images, we improve the adaptive nonlocal temporal filter with state-of-the-art adaptive denoising methods and propose a patch based adaptive temporal filter. To address the bias problem of the denoising results, we propose a fast and efficient multitemporal despeckling method. The key idea of the proposed approach is the use of the ratio image, provided by the ratio between an image and the temporal mean of the stack. This ratio image is easier to denoise than a single image thanks to its improved stationarity. Besides, temporally stable thin structures are well-preserved thanks to the multi-temporal mean. Without reference image, we propose to use a patch-based auto-covariance residual evaluation method to examine the residual image and look for possible remaining structural contents. With speckle reduction images, we propose to use simplified generalized likelihood ratio method to detect the change area, change magnitude and change times in long series of well-registered images. Based on spectral clustering, we apply the simplified generalized likelihood ratio to detect the time series change types. Then, jet colormap and HSV colorization may be used to vividly visualize the detection results. These methods have been successfully applied to monitor farmland area, urban area, harbor region, and flooding area changes.
• Hyper-parameter optimization in deep learning and transfer learning : applications to medical imaging
  
  • Bertrand Hadrien
  , 2019. In the last few years, deep learning has changed irrevocably the field of computer vision. Faster, giving better results, and requiring a lower degree of expertise to use than traditional computer vision methods, deep learning has become ubiquitous in every imaging application. This includes medical imaging applications. At the beginning of this thesis, there was still a strong lack of tools and understanding of how to build efficient neural networks for specific tasks. Thus this thesis first focused on the topic of hyper-parameter optimization for deep neural networks, i.e. methods for automatically finding efficient neural networks on specific tasks. The thesis includes a comparison of different methods, a performance improvement of one of these methods, Bayesian optimization, and the proposal of a new method of hyper-parameter optimization by combining two existing methods: Bayesian optimization and Hyperband.From there, we used these methods for medical imaging applications such as the classification of field-of-view in MRI, and the segmentation of the kidney in 3D ultrasound images across two populations of patients. This last task required the development of a new transfer learning method based on the modification of the source network by adding new geometric and intensity transformation layers.Finally this thesis loops back to older computer vision methods, and we propose a new segmentation algorithm combining template deformation and deep learning. We show how to use a neural network to predict global and local transformations without requiring the ground-truth of these transformations. The method is validated on the task of kidney segmentation in 3D US images.
• Designing Attacks Against Automotive Control Area Network Bus and Electronic Control Units
  
  • Urien Pascal
  , 2019, pp.1-4. (10.1109/CCNC.2019.8651708)
  DOI : 10.1109/CCNC.2019.8651708
• Crypto Terminal Based On Secure Element For Consumer Trusted Blockchain Transactions
  
  • Urien Pascal
  , 2019, pp.1-2. (10.1109/CCNC.2019.8651788)
  DOI : 10.1109/CCNC.2019.8651788
• Framework to Relate / Combine Modeling Languages and Techniques
  
  • Al-Ali Rima
  • Amrani Moussa
  • Bandyopadhyay Soumyadip
  • Barisic Ankica
  • Barros Fernando
  • Blouin Dominique
  • Erata Ferhat
  • Giese Holger
  • Iacono Mauro
  • Klikovits Stefan
  • Navarro Eva
  • Pelliccione Patrizio
  • Taveter Kuldar
  • Tekinerdogan Bedir
  • Vanherpen Ken
  , 2019.
• A Coordinate Descent Primal-Dual Algorithm with Large Step Size and Possibly Non Separable Functions
  
  • Fercoq Olivier
  • Bianchi Pascal
  SIAM Journal on Optimization, Society for Industrial and Applied Mathematics, 2019, 29 (1), pp.100-134. This paper introduces a coordinate descent version of the Vu-Condat algorithm. By coordinate descent, we mean that only a subset of the coordinates of the primal and dual iterates is updated at each iteration, the other coordinates being maintained to their past value. Our method allows us to solve optimization problems with a combination of differentiable functions, constraints as well as non-separable and non-differentiable regularizers. We show that the sequences generated by our algorithm converge to a saddle point of the problem at stake, for a wider range of parameter values than previous methods. In particular, the condition on the step-sizes depends on the coordinate-wise Lipschitz constant of the differentiable function's gradient, which is a major feature allowing classical coordinate descent to perform so well when it is applicable. We illustrate the performances of the algorithm on a total-variation regularized least squares regression problem and on large scale support vector machine problems.