Publications

2020

• Asymptotically Good Multiplicative LSSS over Galois Rings and Applications to MPC over Z/pkZ
  
  • Abspoel Mark
  • Cramer Ronald
  • Damgård Ivan
  • Escudero Daniel
  • Rambaud Matthieu
  • Xing Chaoping
  • Yuan Chen
  , 2020, 12493, pp.151-180. (10.1007/978-3-030-64840-4_6)
  DOI : 10.1007/978-3-030-64840-4_6
• A novel BIST for monitoring aging/temperature by self-triggered scheme to improve the reliability of STT-MRAM
  
  • Zhou Y.
  • Cai H.
  • Zhang M.
  • Naviner L.A.B.
  • Yang J.
  Microelectronics Reliability, Elsevier, 2020, 114, pp.113735. This paper proposes a novel methodology to design high reliable STT-MRAM, with self-activated built-in-self-test (BIST) against aging/temperature-induced degradation. During sensing operation, tunneling magnetoresistance (TMR) is monitored, and real-time BIST is activated prior to permanent damage in Magnetic tunnel junction (MTJ) stack. To evaluate the feasibility of the test scheme, the proposed technique was involved in MRAM array implementation using 28-nm CMOS and 40-nm MTJ. HSPICE MOS Reliability Analysis (MOSRA) is used to evaluate the amount of electrical stress to the actual device aging degradation. Compared with previous periodical BIST method, the proposed self-triggered BIST saves ~31.1% cumulative power consumption over 12 years. And the proposed technique can improve reliability in the wear-out failure period. (10.1016/j.microrel.2020.113735)
  DOI : 10.1016/j.microrel.2020.113735
• Privacy as a Service: Anonymisation of NetFlow Traces
  
  • Aloui Ashref
  • Msahli Mounira
  • Abdessalem Talel
  • Mesnager Sihem
  • Bressan Stéphane
  , 2020, pp.561-571. (10.1007/978-3-030-34986-8_39)
  DOI : 10.1007/978-3-030-34986-8_39
• A decentralised self-healing approach for network topology maintenance
  
  • Rodríguez Arles
  • Gómez Jonatan
  • Diaconescu Ada
  Autonomous Agents and Multi-Agent Systems, Springer Verlag, 2020, 35 (6), pp.1-36. In many distributed systems, from cloud to sensor networks, different configurations impact system performance, while strongly depending on the network topology. Hence, topological changes may entail costly reconfiguration and optimisation processes. This paper proposes a multi-agent solution for recovering networks from node failures. To preserve the network topology, the proposed approach relies on local information about the network’s structure, which is collected and disseminated at runtime. The paper studies two strategies for distributing topological data: one based on mobile agents (our proposal) and the other based on Trickle (a reference gossiping protocol from the literature). These two strategies were adapted for our self-healing approach—to collect topological information for recovering the network; and were evaluated in terms of resource overheads. Experimental results show that both variants can recover the network topology, up to a certain node failure rate, which depends on the network topology. At the same time, mobile agents collect less information, focusing on local dissemination, which suffices for network recovery. This entails less bandwidth overheads than when Trickle is used. Still, mobile agents utilise more memory and exchange more messages, during data-collection, than Trickle does. These results validate the viability of the proposed self-healing solution, offering two variant implementations with diverse performance characteristics, which may suit different application domains. (10.1007/s10458-020-09486-3)
  DOI : 10.1007/s10458-020-09486-3
• Parkinson's desease detection by multimodal analysis combining handwriting and speech signals
  
  • Taleb Catherine
  , 2020. Parkinson’s disease (PD) is a neurological disorder caused by a decreased dopamine level on the brain. This disease is characterized by motor and non-motor symptoms that worsen over time. In advanced stages of PD, clinical diagnosis is clear-cut. However, in the early stages, when the symptoms are often incomplete or subtle, the diagnosis becomes difficult and at times, the subject may remain undiagnosed. Furthermore, there are no efficient and reliable methods capable of achieving PD early diagnosis with certainty. The difficulty in early detection is a strong motivation for computer-based assessment tools/decision support tools/test instruments that can aid in the early diagnosing and predicting the progression of PD.Handwriting’s deterioration and vocal impairment may be ones of the earliest indicators for the onset of the illness. According to the reviewed literature, a language independent model to detect PD using multimodal signals has not been enough addressed. The main goal of this thesis is to build a language independent multimodal system for assessment the motor disorders in PD patients at an early stage based on combined handwriting and speech signals, using machine learning techniques. For this purpose and due to the lack of a multimodal and multilingual dataset, such database that is equally distributed between controls and PD patients was first built. The database includes handwriting, speech, and eye movements’ recordings collected from control and PD patients in two phases (“on-state” and “off-state”). In this thesis we focused on handwriting and speech analysis, where PD patients were studied in their “on-state”.Language-independent models for PD detection based on handwriting features were built; where two approaches were considered, studied and compared: a classical feature extraction and classifier approach and a deep learning approach. Approximately 97% classification accuracy was reached with both approaches. A multi-class SVM classifier for stage detection based on handwriting features was built. The achieved performance was non-satisfactory compared to the results obtained for PD detection due to many obstacles faced.Another language and task-independent acoustic feature set for assessing the motor disorders in PD patients was built. We have succeeded to build a language independent SVM model for PD diagnosis through voice analysis with 97.62% accuracy. Finally, a language independent multimodal system for PD detection by combining handwriting and voice signals was built, where both classical SVM model and deep learning models were both analyzed. A classification accuracy of 100% is obtained when handcrafted features from both modalities are combined and applied to the SVM. Despite the encouraging results obtained, there is still some works to do before putting our PD detection multimodal model into clinical use due to some limitations inherent to this thesis.
• SF-UDA$^{3D}$: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection
  
  • Saltori Cristiano
  • Lathuilière Stéphane
  • Sebe Nicu
  • Ricci Elisa
  • Galasso Fabio
  , 2020. 3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due to domain shift. In the case of LiDAR, in fact, domain shift is not only due to changes in the environment and in the object appearances, as for visual data from RGB cameras, but is also related to the geometry of the point clouds (e.g., point density variations). This paper proposes SF-UDA$^{3D}$, the first Source-Free Unsupervised Domain Adaptation (SF-UDA) framework to domain-adapt the state-of-the-art PointRCNN 3D detector to target domains for which we have no annotations (unsupervised), neither we hold images nor annotations of the source domain (source-free). SF-UDA$^{3D}$ is novel on both aspects. Our approach is based on pseudo-annotations, reversible scale-transformations and motion coherency. SF-UDA$^{3D}$ outperforms both previous domain adaptation techniques based on features alignment and state-of-the-art 3D object detection methods which additionally use few-shot target annotations or target annotation statistics. This is demonstrated by extensive experiments on two large-scale datasets, i.e., KITTI and nuScenes.
• Magnetic Tunnel Junction-based Analog-to-Digital Converter using Spin Orbit Torque Mechanism
  
  • Maciel Nilson
  • Marques Elaine
  • Naviner Lirida
  • Cai Hao
  , 2020, pp.1-4. This paper proposes a novel Magnetic Tunnel Junction (MTJ)-based Analog to Digital Converter (ADC). The Spin-Orbit Torque (SOT) mechanism is used to set the MTJ state. The simulations were performed to 3-bit and 4-bit resolution using a 28nm CMOS FDSOI design-kit. The obtained results indicate that the proposed MTJ - based ADC consumes 37.3f J and 66.1f J for 3-bit and 4-bit resolution, respectively outperforming other ADC designs presented in the literature. In addition, the proposed MTJ-based ADC has a independent read port for each MTJ increasing the read reliability. (10.1109/ICECS49266.2020.9294780)
  DOI : 10.1109/ICECS49266.2020.9294780
• Quad-Approx CNNs for Embedded Object Detection Systems
  
  • Yang Xuecan
  • Chaudhuri Sumanta
  • Naviner Lirida
  • Likforman-Sulem Laurence
  , 2020, pp.1-4. Convolutional Neural Networks (CNNs) are computational-intensive and resource-consuming. To build CNNs with low resource requirements of embedded computer vision applications such as object detection, we propose quad-approx networks. Although binarized networks are good for classification tasks they are not adequate for object detection. In quad-approx networks, we first quantize the convolutional layers. Features and weights for convolution are encoded into 3 bits. On top of that, an approximate multiplier for this special quantized network is proposed. Both approximations are back annotated to the training process leading to no loss in overall precision. The hardware simulation and experimental results are presented for quad-approx CNN based on Zynq UltraScale+ MPSoC ZCU102. 5.3x compression of network and 1.20x speedup for calculation are achieved. (10.1109/ICECS49266.2020.9294829)
  DOI : 10.1109/ICECS49266.2020.9294829
• Métamatériaux & Millimétrique
  
  • Begaud Xavier
  , 2020.
• Dynamically Modelling Heterogeneous Higher-Order Interactions for Malicious Behavior Detection in Event Logs
  
  • Larroche Corentin
  • Mazel Johan
  • Clémençon Stéphan
  , 2021, pp.1-11. Anomaly detection in event logs is a promising approach for intrusion detection in enterprise networks. By building a statistical model of usual activity, it aims to detect multiple kinds of malicious behavior, including stealthy tactics, techniques and procedures (TTPs) designed to evade signature-based detection systems. However, finding suitable anomaly detection methods for event logs remains an important challenge. This results from the very complex, multi-faceted nature of the data: event logs are not only combinatorial, but also temporal and heterogeneous data, thus they fit poorly in most theoretical frameworks for anomaly detection. Most previous research focuses on either one of these three aspects, building a simplified representation of the data that can be fed to standard anomaly detection algorithms. In contrast, we propose to simultaneously address all three of these characteristics through a specifically tailored statistical model. We introduce \textsc{Decades}, a \underline{d}ynamic, h\underline{e}terogeneous and \underline{c}ombinatorial model for \underline{a}nomaly \underline{d}etection in \underline{e}vent \underline{s}treams, and we demonstrate its effectiveness at detecting malicious behavior through experiments on a real dataset containing labelled red team activity. In particular, we empirically highlight the importance of handling the multiple characteristics of the data by comparing our model with state-of-the-art baselines relying on various data representations.
• A Concise Bounded Anonymous Broadcast Yielding Combinatorial Trace-and-Revoke Schemes
  
  • Do Xuan Thanh
  • Hieu Phan Duong
  • Yung Moti
  , 2020, 12147, pp.145-164. (10.1007/978-3-030-57878-7_8)
  DOI : 10.1007/978-3-030-57878-7_8
• Convergence Analysis of a Momentum Algorithm with Adaptive Step Size for Non Convex Optimization
  
  • Barakat Anas
  • Bianchi Pascal
  , 2020, 129 (225–240). Although ADAM is a very popular algorithm for optimizing the weights of neural networks, it has been recently shown that it can diverge even in simple convex optimization examples. Several variants of ADAM have been proposed to circumvent this convergence issue. In this work, we study the ADAM algorithm for smooth nonconvex optimization under a boundedness assumption on the adaptive learning rate. The bound on the adaptive step size depends on the Lipschitz constant of the gradient of the objective function and provides safe theoretical adaptive step sizes. Under this boundedness assumption, we show a novel first order convergence rate result in both deterministic and stochastic contexts. Furthermore, we establish convergence rates of the function value sequence using the Kurdyka-Łojasiewicz property.
• Fast Incremental Na\"ıve Bayes with Kalman Filtering
  
  • Ziffer Giacomo
  • Bernardo Alessio
  • Valle Emanuele Della
  • Bifet Albert
  , 2020, pp.883--889. In recent years an increasing number of applications, IoT sensors and websites have produced endless streams of data. These data streams are not only unbounded, but their characteristics dynamically change over time, generating a phenomenon called concept drift. The standard machine learning models do not work properly in this context and new techniques have been developed in order to tackle these challenges. In this paper we present a new Naïve Bayes algorithm that exploits Kalman Filter, namely KalmanNB, to manage automatically concept drift. Furthermore, we want to investigate when this new approach, which directly follows the values of data's attributes, is better than the standard strategy, which monitors the performance of the model in order to detect a drift. Extensive experiments on both artificial and real datasets with concept drifts reveal that KalmanNB is a valid alternative to the state-of-the-art algorithms, outperforming the latter especially in case of recurring concept drifts. (10.1109/ICDMW51313.2020.00126)
  DOI : 10.1109/ICDMW51313.2020.00126
• Transfer Learning and Visualization of Neural Networks for Artistic Images
  
  • Gonthier Nicolas
  • Gousseau Yann
  • Ladjal Saïd
  , 2020. Transfer learning from large-scale natural image datasets, particularly ImageNet, fine-tuning standard deep convolutional neural network models and using the corresponding pre-trained network have become the de facto method for art analysis applications. Nevertheless, there are large differences in dataset sizes, image style and task specifications between natural image classification and the target artistic images, and there is little understanding of the effects of transfer learning. In this work, we explore some properties of transfer learning for artistic images. We compared different ways to obtain an image classifier: fine-tuning, or not, of pre-trained models and training models from scratch. We also use feature visualization techniques in order to understand more precisely what the network learned on those specific artistic datasets. Those visualization of deep neural networks internal representations can help to highlight how neural networks build up their « understanding » of images. We observed that the network could specify some pre-trained filters in order to adapt them to the new modality of images. On the other hand, the network can also learn new, highly structured filters specific to artistic images when the lower-level layers of the initial model are « frozen ». In particular, it is possible to obtain classifiers with equivalent classification performances but with different hidden representations, that can be specific to artistic images or not.
• Incremental Rebalancing Learning on Evolving Data Streams
  
  • Bernardo Alessio
  • Valle Emanuele Della
  • Bifet Albert
  , 2020, pp.844--850. Nowadays, every device connected to the Internet generates an ever-growing (formally, unbounded) stream of data. Machine Learning on data streams is a grand challenge due to its resource constraints. Indeed, standard machine learning techniques are not able to deal with data whose statistics are subject to gradual or sudden changes (formally, concept drift) without any warning. Massive Online Analysis (MOA) is the collective name, as well as a software library, for new learners that can manage data streams. In this paper, we present a research study on streaming rebalancing. Indeed, data streams can be imbalanced as static data, but there is not a method to rebalance them incrementally. For this reason, we propose a new streaming approach able to rebalance data streams online. Our new methodology is evaluated against some synthetically generated datasets using prequential evaluation to demonstrate that it outperforms the existing approaches. (10.1109/ICDMW51313.2020.00121)
  DOI : 10.1109/ICDMW51313.2020.00121
• Joint Europa Mission (JEM) a multi-scale study of Europa to characterize its habitability and search for extant life
  
  • Blanc Michel
  • André Nicolas
  • Prieto-Ballesteros Olga
  • Gómez-Elvira Javier
  • Jones Geraint D.
  • Sterken Veerle
  • Desprats William
  • Gurvits Leonid
  • Khurana Krishan
  • Balmino Georges
  • Blöcker Aljona
  • Broquet Renaud
  • Bunce Emma
  • Cavel Cyril
  • Choblet Gael
  • Colins Geoffrey
  • Coradini Marcello
  • Cooper John
  • Dirkx Dominic
  • Fontaine Dominique
  • Garnier Philippe
  • Gaudin David
  • Hartogh Paul
  • Iess Luciano
  • Jäggi Adrian
  • Kempf Sascha
  • Krupp Norbert
  • Lara Luisa M.
  • Lasue Jérémie
  • Lainey Valéry
  • Leblanc François
  • Lebreton Jean-Pierre
  • Longobardo Andrea
  • Lorenz Ralph
  • Martins Philippe
  • Martins Zita
  • Marty Jean-Charles
  • Masters Adam
  • Mimoun David
  • Palumba Ernesto
  • Regnier Pascal
  • Saur Joachim
  • Schutte Adriaan
  • Sittler Edward
  • Spohn Tilman
  • Stephan Katrin
  • Szegő Károly
  • Tosi Federico
  • Vance Steve
  • Wagner Roland
  • van Hoolst Tim
  • Volwerk Martin
  • Westall Frances
  Planetary and Space Science, Elsevier, 2020, 193, pp.104960. Europa is the closest and probably the most promising target to search for extant life in the Solar System, based on complementary evidence that it may fulfil the key criteria for habitability: the Galileo discovery of a sub-surface ocean; the many indications that the ice shell is active and may be partly permeable to transfer of chemical species, biomolecules and elementary forms of life; the identification of candidate thermal and chemical energy sources necessary to drive a metabolic activity near the ocean floor.In this article we are proposing that ESA collaborates with NASA to design and fly jointly an ambitious and exciting planetary mission, which we call the Joint Europa Mission (JEM), to reach two objectives: perform a full characterization of Europa's habitability with the capabilities of a Europa orbiter, and search for bio-signatures in the environment of Europa (surface, subsurface and exosphere) by the combination of an orbiter and a lander. JEM can build on the advanced understanding of this system which the missions preceding JEM will provide: Juno, JUICE and Europa Clipper, and on the Europa lander concept currently designed by NASA (Maize, report to OPAG, 2019). (10.1016/j.pss.2020.104960)
  DOI : 10.1016/j.pss.2020.104960
• Misalignments of objectives in demand response programs: a look at local energy markets
  
  • Kiedanski Diego
  • Kofman Daniel
  • Maillé Patrick
  • Horta José
  , 2020, pp.1-7. Local energy markets (LEMs) have been proposed to mitigate the variability introduced in power systems by distributed renewable energy resources such as photo-voltaic energy. During the progressive release of LEMs, the decision problem faced by prosumers (consumers that might also produce energy), will differ from the wholesale electricity market's one because there is always the alternative to buy from or sell to the utility company. In this setting, guaranteeing that the aggregated energy consumption will be well behaved depends on the properties of the mechanisms used to implement the market, the alternative tariff offered to participants by their utility and how prosumers interact among themselves. We present a pathological example of a LEM in which the best strategy for the agents results in unnecessary peaks of demand. A decision model for players participating in LEMs is developed to study the existence of undesirable behaviour while using realistic data and number of participants. Through numerical experiments, we identify the key aspects of the player's behaviour, strategy and environment that lead to the aforementioned peaks, all under reasonable circumstances. Simple fixes are discussed to overcome the pitfalls of such markets. (10.1109/SmartGridComm47815.2020.9302939)
  DOI : 10.1109/SmartGridComm47815.2020.9302939
• Combflex: a linear combinatorial auction for local energy markets
  
  • Kiedanski Diego
  • Orda Ariel
  • Kofman Daniel
  , 2020. Local energy markets, platforms in which pro-sumers in the same Low Voltage network can trade energy among themselves, offer a great opportunity to incentivize the consumption of locally generated energy. Unfortunately, traditionally proposed implementations of local energy markets such as simple double auctions and peer to peer exchanges do not fully exploit the available flexibility in these systems. We design a market mechanism that exploits the characteristics of the players, providing them with expressive bids to represent their flexibility, which we assume is due to energy storage. The proposed market is not obviously manipulable and can be cleared by solving a linear programming problem that grows linearly in the number of participants. Using realistic data, we benchmark the proposed mechanism against sequential auctions and peer to peer exchanges often used in the literature. Our numerical results show that the proposed mechanism outperforms traditional implementations.
• Fully automatic CNN-based segmentation of retinal bifurcations in 2D adaptive optics ophthalmoscopy images
  
  • Trimeche Iyed
  • Rossant Florence
  • Bloch Isabelle
  • Pâques Michel
  , 2020. Automated image segmentation is a crucial step to characterize and quantify the morphometry of blood vessels. Adaptive Optics Ophthalmoscopy (AOO) images of eye fundus allow visualizing retinal vessels with a high resolution, especially arterial bifurcations, suitable to morphometric biomarkers measurements. In this paper, we propose a fully automatic hybrid approach based on a modified U-Net convolutional neu-ral network and active contours for segmenting retinal vessel branches and bifurcations with high precision. The obtained segmentation results are within the range of intra-and inter-user variability, and meet the performance of our previous semi-automatic approach in terms of precision and reproducibility, while being obtained in a completely automatic way.
• Semantic image segmentation based on spatial relationships and inexact graph matching
  
  • Chopin Jérémy
  • Fasquel Jean-Baptiste
  • Mouchère Harold
  • Dayot R.
  • Bloch Isabelle
  , 2020. We propose a method for semantic image segmentation, combining a deep neural network and spatial relationships between image regions, encoded in a graph representation of the scene. Our proposal is based on inexact graph matching, formulated as a quadratic assignment problem applied to the output of the neural network. The proposed method is evaluated on a public dataset used for segmentation of images of faces and compared to the U-Net deep neural network that is widely used for semantic segmentation. Preliminary results show that our approach is promising. In terms of Intersection-over-Union of region bounding boxes, the improvement is of 2.4% in average, compared to U-Net, and up to 24.4% for some regions. Further improvements are observed when reducing the size of the training dataset (up to 8.5% in average). (10.1109/IPTA50016.2020.9286611)
  DOI : 10.1109/IPTA50016.2020.9286611
• Convolutional neural networks for change analysis in earth observation images with noisy labels and domain shifts
  
  • Caye Daudt Rodrigo
  , 2020. The analysis of satellite and aerial Earth observation images allows us to obtain precise information over large areas. A multitemporal analysis of such images is necessary to understand the evolution of such areas. In this thesis, convolutional neural networks are used to detect and understand changes using remote sensing images from various sources in supervised and weakly supervised settings. Siamese architectures are used to compare coregistered image pairs and to identify changed pixels. The proposed method is then extended into a multitask network architecture that is used to detect changes and perform land cover mapping simultaneously, which permits a semantic understanding of the detected changes. Then, classification filtering and a novel guided anisotropic diffusion algorithm are used to reduce the effect of biased label noise, which is a concern for automatically generated large-scale datasets. Weakly supervised learning is also achieved to perform pixel-level change detection using only image-level supervision through the usage of class activation maps and a novel spatial attention layer. Finally, a domain adaptation method based on adversarial training is proposed, which succeeds in projecting images from different domains into a common latent space where a given task can be performed. This method is tested not only for domain adaptation for change detection, but also for image classification and semantic segmentation, which proves its versatility.
• Apprentissage à partir de données extrêmes multivariées : application au traitement du langage naturel
  
  • Jalalzai Hamid
  , 2020. Extremes surround us and appear in a large variety of data. Natural data likethe ones related to environmental sciences contain extreme measurements; inhydrology, for instance, extremes may correspond to floods and heavy rainfalls or on the contrary droughts. Data related to human activity can also lead to extreme situations; in the case of bank transactions, the money allocated to a sale may be considerable and exceed common transactions. The analysis of this phenomenon is one of the basis of fraud detection. Another example related to humans is the frequency of encountered words. Some words are ubiquitous while others are rare. No matter the context, extremes which are rare by definition, correspond to uncanny data. These events are of particular concern because of the disastrous impact they may have. Extreme data, however, are less considered in modern statistics and applied machine learning, mainly because they are substantially scarce: these events are out numbered –in an era of so-called ”big data”– by the large amount of classical and non-extreme data that corresponds to the bulk of a distribution. Thus, the wide majority of machine learning tools and literature may not be well-suited or even performant on the distributional tails where extreme observations occur. Through this dissertation, the particular challenges of working with extremes are detailed and methods dedicated to them are proposed. The first part of the thesisis devoted to statistical learning in extreme regions. In Chapter 4, non-asymptotic bounds for the empirical angular measure are studied. Here, a pre-established anomaly detection scheme via minimum volume set on the sphere, is further im-proved. Chapter 5 addresses empirical risk minimization for binary classification of extreme samples. The resulting non-parametric analysis and guarantees are detailed. The approach is particularly well suited to treat new samples falling out of the convex envelop of encountered data. This extrapolation property is key to designing new embeddings achieving label preserving data augmentation. Chapter 6 focuses on the challenge of learning the latter heavy-tailed (and to be precise regularly varying) representation from a given input distribution. Empirical results show that the designed representation allows better classification performanceon extremes and leads to the generation of coherent sentences. Lastly, Chapter7 analyses the dependence structure of multivariate extremes. By noticing that extremes tend to concentrate on particular clusters where features tend to be recurrently large simulatenously, we define an optimization problem that identifies the aformentioned subgroups through weighted means of features.
• Autonomous Systems for Rescue Missions: Design, Architecture and Configuration Validation
  
  • Tanzi Tullio
  • Bertolino Matteo
  Information Systems Frontiers, Springer Verlag, 2020, 23 (5), pp.1189-1202. In the context of disaster management, the intervention of Autonomous Systems brings many benefits to human rescuers. Autonomous Systems can quickly reach regions that may be inaccessible for humans. In addition, they can perform a rapid mapping of the impacted area and therefore enhancing the human knowledge. However, it is necessary to choose the best Autonomous Systems according to (i) mission environment and (ii) mission objectives. In this article, we describe our work on ArcTurius rover, a wheeled Autonomous System in support to disaster management. We validated its design through simulation and formal verification. A first simulation step occurs during the system definition. This allows to formally verify the design choices. A second type of simulation is performed to check the adequacy of the rover with respect to a specific mission. Thus, an Autonomous System can be adapted prior to a real mission to enhance its level of performance. (10.1007/s10796-020-10085-6)
  DOI : 10.1007/s10796-020-10085-6
• Augmented Voting Reality
  
  • Chabanne Hervé
  • Dottax Emmanuelle
  • Dumont Denis
  , 2020.
• Premium Access to Convolutional Neural Networks
  
  • Bringer Julien
  • Chabanne Hervé
  • Guiga Linda
  , 2020.