Publications

2019

• Test Sequence Generation From Formally Verified SysML Models
  
  • de Saqui-Sannes Pierre
  • Apvrille Ludovic
  , 2019. Test generation has been acknowledged as a cost-prone activity reducing productivity and time to market. The expected benefits of Model Based Systems Engineering include automated generation of test sequences from models. The paper proposes verification solutions for the System Modeling Language (SysML). In particular, the paper shows how to link test generation to formal verification. The proposed algorithms are implemented by the free software TTool. Two case studies support discussion on conformance and interoperability testing, respectively.
• Structural tomographic approaches for urban area analysis using high resolution SAR tomography : TomoSAR
  
  • Rambour Clément
  , 2019. SAR tomography consists in exploiting multiple images from the same area acquired from a slightly different angle to retrieve the 3-D distribution of the complex reflectivity on the ground. As the transmitted waves are coherent, the desired spatial information (along with the vertical axis) is coded in the phase of the pixels. Many methods have been proposed to retrieve this information in the past years. However, the natural redundancies of the scene are generally not exploited to improve the tomographic estimation step. This Ph.D. presents new approaches to regularize the estimated reflectivity density obtained through SAR tomography by exploiting the urban geometrical structures.
• Strategy-proof local energy market with sequential stochastic decision process for battery control
  
  • Kiedanski Diego
  • Kofman Daniel
  • Horta José
  • Menga David
  , 2019. Low voltage distribution networks were not designed to support massive deployment of distributed energy resources (DER) such as solar panels, which is currently hindering the Energy Transition. Recent research contributions have shown that local energy markets improve the capacity of distribution grids to host DER. In parallel, distributed models were created to deal with the control of batteries in presence of stochastic demand and production, as well as variable electricity prices. The combination of the two techniques has received little attention until now, from both the literature and the industry. In this paper we extend the traditional approach to sequential stochastic decision processes by also modeling the interaction with the neighborhood in addition to the utility. The model is then solved using reinforcement learning techniques. For the local energy market we use MUDA: a strategy-proof multi-unit double auction. The performance of the proposed system is evaluated through simulations, demonstrating its capacity to effectively decrease the overall exchange of energy with the grid and the monetary cost for users.
• Constant step stochastic approximations involving differential inclusions: stability, long-run convergence and applications
  
  • Bianchi Pascal
  • Hachem Walid
  • Salim Adil
  Stochastics: An International Journal of Probability and Stochastic Processes, Taylor & Francis: STM, Behavioural Science and Public Health Titles, 2019, 91 (2), pp.288-320. We consider a Markov chain (xn) whose kernel is indexed by a scaling parameter γ > 0, referred to as the step size. The aim is to analyze the behavior of the Markov chain in the doubly asymptotic regime where n → ∞ then γ → 0. First, under mild assumptions on the so-called drift of the Markov chain, we show that the interpolated process converges narrowly to the solutions of a Differential Inclusion (DI) involving an upper semicontinuous set-valued map with closed and convex values. Second, we provide verifiable conditions which ensure the stability of the iterates. Third, by putting the above results together, we establish the long run convergence of the iterates as γ → 0, to the Birkhoff center of the DI. The ergodic behavior of the iterates is also provided. Application examples are investigated. We apply our findings to 1) the problem of nonconvex proximal stochastic optimization and 2) a fluid model of parallel queues. (10.1080/17442508.2018.1539086)
  DOI : 10.1080/17442508.2018.1539086
• Development of the Unified Security Requirements of PUFs During the Standardization Process
  
  • Bruneau Nicolas
  • Danger Jean-Luc
  • Facon Adrien
  • Guilley Sylvain
  • Hamaguchi Soshi
  • Hori Yohei
  • Kang Yousung
  • Schaub Alexander
  , 2019, LNCS (11359), pp.314-330. This paper accounts for some scientific aspects related to the international standardization process about physically unclonable functions (PUFs), through the drafting of ISO/IEC 20897 project. The primary motivation for this standard project is to structure and expand the market of PUFs, as solutions for non-tamperable electronic chips identifiers. While drafting the documents and discussing with international experts, the topic of PUF also gained much maturity. This article accounts how scientific structuration of the PUF as a field of embedded systems security has been emerging as a byproduct. First, the standardization has allowed to merge two redundant security requirements (namely diffuseness and unpredictability) into one (namely randomness), which in addition better suits all kinds of PUFs. As another contribution, the standardization process made it possible to match unambiguous and consistent tests with the security requirements. Furthermore, the process revealed that tests can be seen as estimators from their theoretic expressions, the so-called stochastic models. (10.1007/978-3-030-12942-2_24)
  DOI : 10.1007/978-3-030-12942-2_24
• Towards more scalability and flexibility for distributed storage systems
  
  • Ruty Guillaume
  , 2019. The exponentially growing demand for storage puts a huge stress on traditionnal distributed storage systems. While storage devices' performance have caught up with network devices in the last decade, their capacity do not grow as fast as the rate of data growth, especially with the rise of cloud big data applications. Furthermore, the performance balance between storage, network and compute devices has shifted and the assumptions that are the foundation for most distributed storage systems are not true anymore. This dissertation explains how several aspects of such storage systems can be modified and rethought to make a more efficient use of the resource at their disposal. It presents an original architecture that uses a distributed layer of metadata to provide flexible and scalable object-level storage, then proposes a scheduling algorithm improving how a generic storage system handles concurrent requests. Finally, it describes how to improve legacy filesystem-level caching for erasure-code-based distributed storage systems, before presenting a few other contributions made in the context of short research projects.
• De Fourier à la reconnaissance musicale
  
  • Richard Gael
  • Fenet Sébastien
  • Grenier Yves
  Interstices, INRIA, 2019.
• Smooth Minimization of Nonsmooth Functions with Parallel Coordinate Descent Methods
  
  • Fercoq Olivier
  • Richtárik Peter
  , 2019, pp.57-96. We study the performance of a family of randomized parallel coordinate descent methods for minimizing the sum of a nonsmooth and separable convex functions. The problem class includes as a special case L1-regularized L1 regression and the minimization of the exponential loss ("AdaBoost problem"). We assume the input data defining the loss function is contained in a sparse $m\times n$ matrix $A$ with at most $\omega$ nonzeros in each row. Our methods need $O(n \beta/\tau)$ iterations to find an approximate solution with high probability, where $\tau$ is the number of processors and $\beta = 1 + (\omega-1)(\tau-1)/(n-1)$ for the fastest variant. The notation hides dependence on quantities such as the required accuracy and confidence levels and the distance of the starting iterate from an optimal point. Since $\beta/\tau$ is a decreasing function of $\tau$, the method needs fewer iterations when more processors are used. Certain variants of our algorithms perform on average only $O(\nnz(A)/n)$ arithmetic operations during a single iteration per processor and, because $\beta$ decreases when $\omega$ does, fewer iterations are needed for sparser problems. (10.1007/978-3-030-12119-8_4)
  DOI : 10.1007/978-3-030-12119-8_4
• Context-aware recommender systems for real-world applications
  
  • Al-Ghossein Marie
  , 2019. Recommender systems have proven to be valuable tools to help users overcome the information overload, and significant advances have been made in the field over the last two decades. In particular, contextual information has been leveraged to model the dynamics occurring within users and items. Context is a complex notion and its traditional definition, which is adopted in most recommender systems, fails to cope with several issues occurring in real-world applications. In this thesis, we address the problems of partially observable and unobservable contexts in two particular applications, hotel recommendation and online recommendation, challenging several aspects of the traditional definition of context, including accessibility, relevance, acquisition, and modeling.The first part of the thesis investigates the problem of hotel recommendation which suffers from the continuous cold-start issue, limiting the performance of classical approaches for recommendation. Traveling is not a frequent activity and users tend to have multifaceted behaviors depending on their specific situation. Following an analysis of the user behavior in this domain, we propose novel recommendation approaches integrating partially observable context affecting users and we show how it contributes in improving the recommendation quality.The second part of the thesis addresses the problem of online adaptive recommendation in streaming environments where data is continuously generated. Users and items may depend on some unobservable context and can evolve in different ways and at different rates. We propose to perform online recommendation by actively detecting drifts and updating models accordingly in real-time. We design novel methods adapting to changes occurring in user preferences, item perceptions, and item descriptions, and show the importance of online adaptive recommendation to ensure a good performance over time.
• Transportation proofs of Rényi entropy power inequalities
  
  • Rioul Olivier
  , 2019. A framework for deriving Rényi entropy-power inequalities (EPIs) is presented that uses linearization and an inequality of Dembo, Cover, and Thomas. Simple arguments are given to recover the previously known Rényi EPIs and derive new ones, by unifying a multiplicative form with con- stant c and a modification with exponent α of previous works. An information-theoretic proof of the Dembo-Cover-Thomas inequality—equivalent to Young’s convolutional inequality with optimal constants—is provided, based on properties of Rényi conditional and relative entropies and using transportation ar- guments from Gaussian densities. For log-concave densities, a transportation proof of a sharp varentropy bound is presented.
• Des intelligences Très artificielles
  
  • Dessalles Jean-Louis
  , 2019. Si vous marchez à reculons, les traces de pas que vous voyez devant vous sont les vôtres. Aucun robot, aucune intelligence artificielle (IA) ne sait ce genre de choses, sauf si l'on a pensé à les lui dire. Les IA sont-elles si intelligentes que cela ? À bien y regarder, elles apparaissent très intelligentes et très stupides à la fois. Pour quelle raison ? En sera-t-il toujours ainsi ? Dans ce livre, Jean-Louis Dessalles aborde ces questions d'une manière précise et accessible à tous. Chaque lecteur trouvera dans ce livre de quoi le surprendre. Il nous parle du passé, du présent et du futur des IA. Il évoque même ce qui, selon lui, leur manque pour devenir... intelligentes.
• An Adaptive Quantizer for High Dynamic Range Content: Application to Video Coding
  
  • Liu Yi
  • Sidaty Naty
  • Hamidouche Wassim
  • Deforges Olivier
  • Valenzise Giuseppe
  • Zerman Emin
  IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical and Electronics Engineers, 2019, 29 (2), pp.531-545. In this paper, we propose an adaptive perceptual quantization method to convert the representation of High Dynamic Range (HDR) content from the floating point data type to integer, which is compatible with the current image/video coding and display systems. The proposed method considers the luminance distribution of the HDR content, as well as the detectable contrast threshold of the Human Visual System (HVS), in order to preserve more contrast information than the Perceptual Quantizer (PQ) in integer representation. Aiming to demonstrate the effectiveness of this quantizer for HDR video compression, we implemented it in a mapping function on the top of the HDR video coding system based on High Efficiency Video Coding (HEVC) standard. Moreover, a comparison function is also introduced to decrease the additional bit-rate of side information, generated by the mapping function. Objective quality measurements and subjective tests have been conducted in order to evaluate the quality of the reconstructed HDR videos. Subjective test results have shown that the proposed method can improve, in a significant manner, the perceived quality of some reconstructed HDR videos. In the objective assessment, the proposed method achieves improvements over PQ in term of the average bit-rate gain for metrics used in the measurement. (10.1109/TCSVT.2017.2786746)
  DOI : 10.1109/TCSVT.2017.2786746
• Accounting for channel constraints in joint source-channel video coding schemes
  
  • Zheng Shuo
  , 2019. SoftCast based Linear Video Coding (LVC) schemes have been emerged in the last decade as a quasi analog joint-source-channel alternative to classical video coding schemes. Theoretical analyses have shown that analog coding is better than digital coding in a multicast scenario when the channel signal-to-noise ratios (C-SNR) differ among receivers. LVC schemes provide in such context a decoded video quality at different receivers proportional to their C-SNR.This thesis considers first the channel precoding and decoding matrix design problem for LVC schemes under a per-subchannel power constraint. Such constraint is found, e.g., on Power Line Telecommunication (PLT) channels and is similar to per-antenna power constraints in multi-antenna transmission system. An optimal design approach is proposed, involving a multi-level water filling algorithm and the solution of a structured Hermitian Inverse Eigenvalue problem. Three lower-complexity alternative suboptimal algorithms are also proposed. Extensive experiments show that the suboptimal algorithms perform closely to the optimal one and can reduce significantly the complexity. The precoding matrix design in multicast situations also has been considered.A second main contribution consists in an impulse noise mitigation approach for LVC schemes. Impulse noise identification and correction can be formulated as a sparse vector recovery problem. A Fast Bayesian Matching Pursuit (FBMP) algorithm is adapted to LVC schemes. Subchannels provisioning for impulse noise mitigation is necessary, leading to a nominal video quality decrease in absence of impulse noise. A phenomenological model (PM) is proposed to describe the impulse noise correction residual. Using the PM model, an algorithm to evaluate the optimal number of subchannels to provision is proposed. Simulation results show that the proposed algorithms significantly improve the video quality when transmitted over channels prone to impulse noise.
• Improving Evolutionary Strategies with Generative Neural Networks
  
  • Faury Louis
  • Calauzènes Clément
  • Fercoq Olivier
  • Krichen Syrine
  , 2019. Evolutionary Strategies (ES) are a popular family of black-box zeroth-order optimization algorithms which rely on search distributions to efficiently optimize a large variety of objective functions. This paper investigates the potential benefits of using highly flexible search distributions in classical ES algorithms, in contrast to standard ones (typically Gaussians). We model such distributions with Generative Neural Networks (GNNs) and introduce a new training algorithm that leverages their expressiveness to accelerate the ES procedure. We show that this tailored algorithm can readily incorporate existing ES algorithms, and outperforms the state-of-the-art on diverse objective functions.
• Tailoring modal properties of inhibited-coupling guiding fibers by cladding modification
  
  • Jonas Osorio
  • Chafer Matthieu
  • Debord Benoît
  • Giovanardi Fabio
  • Cordier Martin
  • Maurel Martin
  • Delahaye Frédéric
  • Amrani Fouad
  • Vincetti Luca
  • Gérôme Frédéric
  • Benabid Fetah
  Scientific Reports, Nature Publishing Group, 2019, 9 (1376). Understanding cladding properties is crucial for designing microstructured optical fibers. This is particularly acute for Inhibited-Coupling guiding fibers because of the reliance of their core guidance on the core and cladding mode-field overlap integral. Consequently, careful planning of the fiber cladding parameters allows obtaining fibers with optimized characteristics such as low loss and broad transmission bandwidth. In this manuscript, we report on how one can tailor the modal properties of hollow-core photonic crystal fibers by adequately modifying the fiber cladding. We show that the alteration of the position of the tubular fibers cladding tubes can alter the loss hierarchy of the modes in these fibers, and exhibit salient polarization propriety. In this context, we present two fibers with different cladding structures which favor propagation of higher order core modes-namely LP 11 and Lp 21 modes. Additionally, we provide discussions on mode transformations in these fibers and show that one can obtain uncommon intensity and polarization profiles at the fiber output. This allows the fiber to act as a mode intensity and polarization shaper. We envisage this novel concept can be useful for a variety of applications such as hollow core fiber based atom optics, atom-surface physics, sensing and nonlinear optics. (10.1038/s41598-018-37948-y)
  DOI : 10.1038/s41598-018-37948-y
• Optimal mini-batch and step sizes for SAGA
  
  • Gazagnadou Nidham
  • Gower Robert M.
  • Salmon Joseph
  , 2019. Recently it has been shown that the step sizes of a family of variance reduced gradient methods called the JacSketch methods depend on the expected smoothness constant. In particular, if this expected smoothness constant could be calculated a priori, then one could safely set much larger step sizes which would result in a much faster convergence rate. We fill in this gap, and provide simple closed form expressions for the expected smoothness constant and careful numerical experiments verifying these bounds. Using these bounds, and since the SAGA algorithm is part of this JacSketch family, we suggest a new standard practice for setting the step sizes and mini-batch size for SAGA that are competitive with a numerical grid search. Furthermore, we can now show that the total complexity of the SAGA algorithm decreases linearly in the mini-batch size up to a pre-defined value: the optimal mini-batch size. This is a rare result in the stochastic variance reduced literature, only previously shown for the Katyusha algorithm. Finally we conjecture that this is the case for many other stochastic variance reduced methods and that our bounds and analysis of the expected smoothness constant is key to extending these results.
• kW pulsed nanosecond TDFL with direct modulation
  
  • Romano Clément
  • Jaouën Yves
  • Tench Robert E
  • Delavaux Jean-Marc
  , 2019, pp.7. (10.1117/12.2506828)
  DOI : 10.1117/12.2506828
• Thermally insensitive determination of the chirp parameter of InAs/GaAs quantum dot lasers epitaxially grown onto silicon
  
  • Duan Jianan
  • Huang Heming
  • Dong Bozhang
  • Jung Daehwan
  • Zhang Zeyu
  • Norman Justin C
  • Bowers John E
  • Grillot Frederic
  , 2019, pp.27. A common way of extracting the chirp parameter (i.e., the α-factor) of semiconductor lasers is usually performed by extracting the net modal gain and the wavelength from the amplified spontaneous emission (ASE) spectrum. Although this method is straightforward, it remains sensitive to the thermal effects hence leading to a clear underestimation of the α-factor. In this work, we investigate the chirp parameter of InAs/GaAs quantum dot (QD) lasers epitaxially grown on silicon with a measurement technique evaluating the gain and wavelength changes of the suppressed side modes by optical injection locking. Given that the method is thermally insensitive, the presented results confirm our initial measurements conducted with the ASE i.e. the α-factor of the QD lasers directly grown on silicon is as low as 0.15 hence resulting from the low threading dislocation density and high material gain of the active region. These conclusions make such lasers very promising for future integrated photonics where narrow linewidth, feedback resistant and low-chirp on-chip transmitters are required. (10.1117/12.2509698)
  DOI : 10.1117/12.2509698
• Quantum Key Distribution (QKD); Device and Communication Channel Parameters for QKD Deployment GROUP SPECIFICATION
  
  • Alleaume Romain
  , 2019.
• Children exposure to femtocell in indoor environments estimated by sparse low-rank tensor approximations
  
  • Chiaramello Emma
  • Parazzini Marta
  • Fiocchi Serena
  • Bonato Marta
  • Ravazzani Paolo
  • Wiart Joe
  Annals of Telecommunications - annales des télécommunications, Springer, 2019, 74 (1-2), pp.113-121. (10.1007/s12243-018-0681-0)
  DOI : 10.1007/s12243-018-0681-0
• Efficient Data-Flow Analysis of UML/SysML Diagrams for Optimized Model Compilation of Hardware-Software Systems
  
  • Enrici Andrea
  • Apvrille Ludovic
  • Pacalet Renaud
  , 2019. Growing needs in terms of latency, throughput and flexibility are driving the architectures of tomorrow’s Ra- dio Access Networks towards more centralized configurations that rely on cloud-computing paradigms. In these new architectures, digital signals are processed on a large variety of hardware units (e.g., CPUs, Field Programmable Gate Arrays, Graphical Processing Units). Optimizing model compilers that target these archi- tectures must rely on efficient analysis techniques to optimally generate software for signal-processing appli- cations. In this paper, we present a blocking combination of the iterative and worklist algorithms to perform static data-flow analysis on functional views denoted with UML Activity and SysML Block diagrams. We demonstrate the effectiveness of the blocking mechanism with reaching definition analysis of UML/SysML models for a 5G channel decoder (receiver side) and a Software Defined Radio system. We show that sig- nificant reductions in the number of unnecessary visits of the models’ control-flow graphs are achieved, with respect to a non-blocking combination of the iterative and worklist algorithms. (10.5220/0007377900840095)
  DOI : 10.5220/0007377900840095
• Dynamic guest memory resizing – paravirtualized approach
  
  • Bielski Maciej
  • Pacalet Renaud
  • Rigo Alvise
  , 2019. Nowadays cloud-computing systems take a great advantage of virtualization for the benefits of workload iso- lation and flexible resources partitioning. It is expected that the same functionalities will be available also on disaggregated architectures, proposed recently as next generation approach for building data-centers. In this publication, we are presenting the design and prototype of an enhanced virtualization layer, enabling runtime memory balancing between virtual machines on a section granularity. Guests’ RAM is backed by isolated chunks of host memory, coming from independent physical banks, not necessarily a local one. It can be dynamically resized without requiring any support for the ACPI emulation in the virtualization framework, as we exemplified by implementing the prototype on ARMv8 platform. (10.1109/PDP.2019.00032)
  DOI : 10.1109/PDP.2019.00032
• LSDSAR, a Markovian a contrario framework for line segment detection in SAR images
  
  • Liu Chenguang
  • Abergel Rémy
  • Gousseau Yann
  • Tupin Florence
  Pattern Recognition, Elsevier, 2019, 98. In this paper, we propose a generic method for the detection of line segments in SAR images. The approach relies on an a contrario framework and is inspired by the state-of-the art LSD detector. As with all a contrario approaches, false detections are controlled through the use of a background model, whose development is especially challenging in the framework of SAR images. Indeed, statistical characteristics of SAR images strongly differ from those of optical images, making the use of existing background models intrinsically inadequate. In order to circumvent this problem, we proceed in two steps. First, the building blocks of the detector, namely the local orientations, are computed carefully to avoid any spatial bias. Second, we propose a new background model, in which the spatial dependency between local orientations are modeled with a Markov chain. This is in strong contrast with most existing a contrario methods who heavily rely on independence assumptions. We provide a complete and detailed algorithm for our line segment detector, and perform experiments on synthetic and real images demonstrating its efficiency. The source code of LSDSAR can be found in https://github.com/ChenguangTelecom/LSDSAR (10.1016/j.patcog.2019.107034)
  DOI : 10.1016/j.patcog.2019.107034
• 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