Publications

2020

• Matrix Factorization for High Frequency Non Intrusive Load Monitoring
  
  • Henriet Simon
  • Fuentes Benoît
  • Şimşekli Umut
  • Richard Gael
  , 2020, pp.20-24. Non Intrusive Load Monitoring has been introduced 30 years ago in order to monitor the electric consumption of specific equipments inside a building without the need of installing multiples sensors. During three decades, researchers and industrials have described the NILM problems according to the electric data available, the desired quantity to be monitored and the application it was used for. As a consequence of the multitude of choices, a lot of different formulations can be found in the literature. This diversity makes it difficult for researchers from general domains such as machine learning to tackle the NILM problem. In this paper we aim at defining the NILM problem as a Matrix Factorization task using high frequency measurements and also to review methods to solve this problem. We start by defining the general concepts driving the NILM problem and then show how to cast high frequency NILM into a Matrix Factorization problem. Once casted as a machine learning problem, we will review general purposes algorithms applicable to this problem such as Independent Component Analysis, Sparse Coding or Semi Non-negative Matrix Factorization and specific NILM methods such as BOLT and IVMF. (10.1145/3427771.3427847)
  DOI : 10.1145/3427771.3427847
• On the boomerang uniformity of quadratic permutations
  
  • Mesnager Sihem
  • Tang C.
  • Xiong M.
  Journal of Designs, Codes, and Cryptography, 2020.
• GAME-ON: A Multimodal Dataset for Cohesion and Group Analysis
  
  • Maman Lucien
  • Ceccaldi Eleonora
  • Lehmann-Willenbrock Nale
  • Likforman-Sulem Laurence
  • Chetouani Mohamed
  • Volpe Gualtiero
  • Varni Giovanna
  IEEE Access, IEEE, 2020, 8, pp.124185-124203. (10.1109/ACCESS.2020.3005719)
  DOI : 10.1109/ACCESS.2020.3005719
• Degrees-of-Freedom in Multi-Cloud Based Sectored Cellular Networks
  
  • Gelincik Samet
  • Rekaya-Ben Othman Ghaya
  Entropy, MDPI, 2020.
• Space-Time Coding Performance Analysis for CDL-impaired Multi-Core Fiber Transmission
  
  • Abouseif Akram
  • Rekaya-Ben Othman Ghaya
  • Jaouën Yves
  , 2020.
• Combined Vector Perturbation for Adaptive Modulation in MU-MIMO
  
  • Askri Aymen
  • Rekaya-Ben Othman Ghaya
  , 2020.
• Stein's method for rough paths
  
  • Coutin Laure
  • Decreusefond Laurent
  Potential Analysis, Springer Verlag, 2020, 53, pp.387--406. The original Donsker theorem says that a standard random walk converges in distribution to a Brownian motion in the space of continuous functions. It has recently been extended to enriched random walks and enriched Brownian motion. We use the Stein-Dirichlet method to precise the rate of this convergence in the topology of fractional Sobolev spaces. (10.1007/s11118-019-09773-z)
  DOI : 10.1007/s11118-019-09773-z
• Anticanonical codes from del Pezzo surfaces with Picard rank one
  
  • Blache Régis
  • Couvreur Alain
  • Hallouin Emmanuel
  • Madore David
  • Nardi Jade
  • Rambaud Matthieu
  • Randriambololona Hugues
  Transactions of the American Mathematical Society, American Mathematical Society, 2020. We construct algebraic geometric codes from del Pezzo surfaces and focus on the ones having Picard rank one and the codes associated to the anticanonical class. We give explicit constructions of del Pezzo surfaces of degree 4, 5 and 6, compute the parameters of the associated anticanonical codes and study their isomorphisms arising from the automorphisms of the surface. We obtain codes with excellent parameters and some of them turn out to beat the best known codes listed on the database codetable. (10.1090/tran/8119)
  DOI : 10.1090/tran/8119
• Delayed labelling evaluation for data streams
  
  • Grzenda Maciej
  • Gomes Heitor Murilo
  • Bifet Albert
  Data Mining and Knowledge Discovery, Springer, 2020, 34 (5), pp.1237--1266. A large portion of the stream mining studies on classification rely on the availability of true labels immediately after making predictions. This approach is well exemplified by the test-then-train evaluation, where predictions immediately precede true label arrival. However, in many real scenarios, labels arrive with non-negligible latency. This raises the question of how to evaluate classifiers trained in such circumstances. This question is of particular importance when stream mining models are expected to refine their predictions between acquiring instance data and receiving its true label. In this work, we propose a novel evaluation methodology for data streams when verification latency takes place, namely continuous re-evaluation. It is applied to reference data streams and it is used to differentiate between stream mining techniques in terms of their ability to refine predictions based on newly arriving instances. Our study points out, discusses and shows empirically the importance of considering the delay of instance labels when evaluating classifiers for data streams. (10.1007/S10618-019-00654-Y)
  DOI : 10.1007/S10618-019-00654-Y
• On the Menezes-Teske-Weng conjecture
  
  • Mesnager Sihem
  • Kim K. H.
  • Choe J.
  • Tang C.
  Cryptography and Communications–Discrete Structures, Boolean Functions, and Sequences, 2020.
• A class of narrow-sense BCH codes over $\mathbb{F}_q$ of length $\frac{q^m-1}{2}$
  
  • Ling X.
  • Mesnager Sihem
  • Qi Y.
  • Tang C.
  Journal of Designs, Codes, and Cryptography, 2020.
• Méthodes et dispositifs de codage et de décodage de données
  
  • Baccouch Hana
  • Boukhatem Nadia
  , 2020.
• Approximating morphological operators with part-based representations learned by asymmetric auto-encoders
  
  • Blusseau Samy
  • Ponchon Bastien
  • Velasco-Forero Santiago
  • Angulo Jesus
  • Bloch Isabelle
  Mathematical Morphology - Theory and Applications, De Gruyter, 2020, 4 (1), pp.64 - 86. This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and explainable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder, where the encoder is deep (for accuracy) and the decoder shallow (for explainability). This method compares favorably to the state-of-the-art online methods on two benchmark datasets (MNIST and Fashion MNIST) and on a hyperspectral image, according to classical evaluation measures and to a new one we introduce, based on the equivariance of the representation to morphological operators. (10.1515/mathm-2020-0102)
  DOI : 10.1515/mathm-2020-0102
• Age of Information Aware Cache Updating with File-and Age-Dependent Update Durations
  
  • Tang Haoyue
  • Ciblat Philippe
  • Wang Jintao
  • Wigger Michèle
  • Yates Roy
  , 2020. We consider a system consisting of a library of time-varying files, a server that at all times observes the current version of all files, and a cache that at the beginning stores the current versions of all files but afterwards has to update these files from the server. Unlike previous works, the update duration is not constant but depends on the file and its Age of Information (AoI), i.e., of the time elapsed since it was last updated. The goal of this work is to design an update policy that minimizes the average AoI of all files with respect to a given popularity distribution. Actually a relaxed problem, close to the original optimization problem, is solved and a practical update policy is derived. The update policy relies on the file popularity and on the functions that characterize the update durations of the files depending on their AoI. Numerical simulations show a significant improvement of this new update policy compared to the so-called square-root policy that is optimal under file-independent and constant update durations.
• Separation of Alpha-Stable Random Vectors
  
  • Fontaine Mathieu
  • Badeau Roland
  • Liutkus Antoine
  Signal Processing, Elsevier, 2020, pp.107465. Source separation aims at decomposing a vector into additive components. This is often done by first estimating source parameters before feeding them into a filtering method, often based on ratios of covariances. The whole pipeline is traditionally rooted in some probabilistic framework providing both the likelihood for parameter estimation and the separation method. While Gaussians are ubiquitous for this purpose, many studies showed the benefit of heavy-tailed models for estimation. However, there is no counterpart filtering method to date exploiting such formalism, so that related studies revert to covariance-based filtering after estimation is finished. Here, we introduce a new multivariate separation technique, that fully exploits the flexibility of α-stable heavy-tailed distributions. We show how a spatial representation can be exploited, which decomposes the observation as an infinite sum of contributions originating from all directions. Two methods for separation are derived. The first one is non-linear and similar to a beamforming technique, while the second one is linear, but minimizes a covariation criterion, which is the counterpart of the covariance for α-stable vectors. We evaluate the proposed techniques in a large number of challenging and adverse situations on synthetic experiments, demonstrating their performance for the extraction of signals from strong interferences. (10.1016/j.sigpro.2020.107465)
  DOI : 10.1016/j.sigpro.2020.107465
• Construction and Random Generation of Hypergraphs with Prescribed Degree and Dimension Sequences
  
  • Arafat Naheed Anjum
  • Basu Debabrota
  • Decreusefond Laurent
  • Bressan Stéphane
  , 2020. We propose algorithms for construction and random generation of hy-pergraphs without loops and with prescribed degree and dimension sequences. The objective is to provide a starting point for as well as an alternative to Markov chain Monte Carlo approaches. Our algorithms leverage the transposition of properties and algorithms devised for matrices constituted of zeros and ones with prescribed row-and column-sums to hypergraphs. The construction algorithm extends the applicability of Markov chain Monte Carlo approaches when the initial hypergraph is not provided. The random generation algorithm allows the development of a self-normalised importance sampling estimator for hypergraph properties such as the average clustering coefficient. We prove the correctness of the proposed algorithms. We also prove that the random generation algorithm generates any hypergraph following the prescribed degree and dimension sequences with a non-zero probability. We empirically and comparatively evaluate the effectiveness and efficiency of the random generation algorithm. Experiments show that the random generation algorithm provides stable and accurate estimates of average clustering coefficient, and also demonstrates a better effective sample size in comparison with the Markov chain Monte Carlo approaches.
• Extracting Complex Information from Natural Language Text: A Survey
  
  • Mechket Emna
  • Suchanek Fabian
  CEUR Workshop Proceedings, CEUR-WS.org, 2020. Information Extraction is the art of extracting structured information from natural language text, and it has come a long way in recent years. Many systems focus on binary relationships between two entities-a subject and an object. However, most natural language text contains complex information such as beliefs, causality, anteriority, or relationships that span several sentences. In this paper, we survey existing approaches at this frontier, and outline promising directions of future work.
• Algorithmes : Biais, Discrimination et Équité
  
  • Bertail Patrice
  • Bounie David
  • Clémençon Stéphan
  • Waelbroeck Patrick
  HR Today, ALMA Medien SA, 2020 (58). Les algorithmes s’immiscent de plus en plus dans notre quotidien à l’image des algorithmes d’aide à la décision (algorithme de recommandation ou de scoring), ou bien des algorithmes autonomes embarqués dans des machines intelligentes (véhicules autonomes). Déployés dans de nombreux secteurs et industries pour leur efficacité, leurs résultats sont de plus en plus discutés et contestés. En particulier, ils sont accusés d’être des boites noires et de conduire à des pratiques discriminatoires liées au genre ou à l’origine ethnique. L’objectif de cet article est de décrire les biais liés aux algorithmes et d’esquisser des pistes pour y remédier. Nous nous intéressons en particulier aux résultats des algorithmes en rapport avec des objectifs d’équité, et à leurs conséquences en termes de discrimination. Trois questions motivent cet article : Par quels mécanismes les biais des algorithmes peuvent-ils se produire ? Peut-on les éviter ? Et, enfin, peut-on les corriger ou bien les limiter ? Dans une première partie, nous décrivons comment fonctionne un algorithme d’apprentissage statistique. Dans une deuxième partie nous nous intéressons à l’origine de ces biais qui peuvent être de nature cognitive, statistique ou économique. Dans une troisième partie, nous présentons quelques approches statistiques ou algorithmiques prometteuses qui permettent de corriger les biais. Nous concluons l’article en discutant des principaux enjeux de société soulevés par les algorithmes d’apprentissage statistique tels que l’interprétabilité, l’explicabilité, la transparence, et la responsabilité.
• Training CNNs on speckled optical dataset for edge detection in SAR images
  
  • Liu Chenguang
  • Tupin Florence
  • Gousseau Yann
  ISPRS Journal of Photogrammetry and Remote Sensing, Elsevier, 2020. Edge detection in SAR images is a difficult task due to the strong multiplicative noise. Many researches have been dedicated to edge detection in SAR images but very few try to address the most challenging 1-look situations. Motivated by the success of CNNs for the analysis of natural images, we develop a CNN edge detector for 1-look SAR images. We propose to simulate a SAR dataset using the optical dataset BSDS500 to avoid the tedious job of edge labeling, and we propose a framework, a hand-crafted layer followed by learnable layers, to enable the model trained on simulated SAR images to work in real SAR images. The hypothesis behind these two propositions is that both optical and SAR images can be divided into piecewise constant areas and edges are boundaries between two homogeneous areas. The hand-crafted layer, which is defined by a ratio based gradient computation method, helps to tackle the gap between training and testing images, because the gradient distribution will not be influenced by the mean intensity values of homogeneous areas. The gradient computation step is done by Gradient by Ratio (GR) and the learnable layers are identical to those in HED. The proposed edge detector, GRHED, outperforms concurrent approaches in all our simulations especially in two 1-look real SAR images. The source code of GRHED is available at https://github.com/ChenguangTelecom/GRHED .
• An Indirect Determination of the Polarization Anisotropy in a Quantum Cascade Laser Under Strong Cross-Polarization Feedback
  
  • Spitz O
  • Herdt A
  • Carras M
  • Maisons G
  • Elsässer W
  • Grillot F
  , 2020. This work demonstrates that a non TM-polarized wave can be generated by a quantum cascade laser subjected to strong cross-polarization optical feedback. This finding is used to determine the anisotropy between the two existing polarizations Acknowledgments: this work is supported by the French Defense Agency (DGA), the French ANR program under grant ANR-17-ASMA-0006
• From formal test objectives to TTCN-3 for verifying ETCS complex software control systems
  
  • Ameur-Boulifa Rabéa
  • Cavalli Ana R
  • Maag Stephane
  , 2020, 1250, pp.156-178. The design of a practical but accurate software methodology to guarantee systems correctness and safety is still a big challenge. Where test coverage is dissatisfying, formal analysis grants much higher potential to discover errors or safety vulnerabilities during the design phase of a system. However, formal verification methods often require a strong technical background that limits their usage. In this paper, we present a framework based on testing and verification to ensure the correctness and safety of complex distributed software systems. As a result of the application of our methodology we obtain a more reliable system, in terms of functionality, safety and robustness and a reduction of the time necessary for verification. In order to show the applicability of our solution we applied it on a real industrial case study, that is the European Train Control System (ETCS) [14]. We specify the system using the SDL language [24], and we use a test generation tool to generate abstract test cases in TTCN-3. Based on these standardized tests, we verify using model-checking, some critical properties of the system, in particular these regarding safety requirements. We analyse a real train accident and we demonstrate how the accident could have been avoided if the ETCS system was used. (10.1007/978-3-030-52991-8_8)
  DOI : 10.1007/978-3-030-52991-8_8
• Lattice Codes for C-RAN Based Sectored Cellular Networks
  
  • Gelincik Samet
  • Rekaya-Ben Othman Ghaya
  , 2020.
• Precoding in Massive MU-MIMO Systems Based on New CSI Accuracy Indicator Reporting
  
  • Askri Aymen
  • Rekaya-Ben Othman Ghaya
  , 2020.
• Processing Simple Geometric Attributes with Autoencoders
  
  • Newson Alasdair
  • Almansa Andrés
  • Gousseau Yann
  • Ladjal Saïd
  Journal of Mathematical Imaging and Vision, Springer Verlag, 2020, 62 (3), pp.293-312. Image synthesis is a core problem in modern deep learning, and many recent architectures such as autoencoders and Generative Adversarial networks produce spectacular results on highly complex data, such as images of faces or landscapes. While these results open up a wide range of new, advanced synthesis applications, there is also a severe lack of theoretical understanding of how these networks work. This results in a wide range of practical problems, such as difficulties in training, the tendency to sample images with little or no variability, and generalisation problems. In this paper, we propose to analyse the ability of the simplest generative network, the autoencoder, to encode and decode two simple geometric attributes : size and position. We believe that, in order to understand more complicated tasks, it is necessary to first understand how these networks process simple attributes. For the first property, we analyse the case of images of centred disks with variable radii. We explain how the autoencoder projects these images to and from a latent space of smallest possible dimension, a scalar. In particular, we describe a closed-form solution to the decoding training problem in a network without biases, and show that during training, the network indeed finds this solution. We then investigate the best regularisation approaches which yield networks that generalise well. For the second property, position, we look at the encoding and decoding of Dirac delta functions, also known as `one-hot' vectors. We describe a hand-crafted filter that achieves encoding perfectly, and show that the network naturally finds this filter during training. We also show experimentally that the decoding can be achieved if the dataset is sampled in an appropriate manner. (10.1007/s10851-019-00924-w)
  DOI : 10.1007/s10851-019-00924-w
• La mathématique migrante
  
  • Zayana Karim
  • Jadiba Sami
  • Kraiem Selma
  • Fayala Abdelwahid
  Les Cahiers Pédagogiques, 2020, 558. La route de l'inconnu(e) : histoire de quelques concepts mathématiques à travers les grandes migrations en méditerranée