Scientific Production

SEARCH

Search

Conference Paper

Incorporating User Feedback Into One-Class Support Vector Machines for Anomaly Detection

Authors: Lesouple Julien and Tourneret Jean-Yves

In Proc. 28th European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands, January 18-22, 2021.

DOWNLOAD DOCUMENT

Machine learning and data-driven algorithms have gained a growth of interest during the past decades due to the computation capability of the computers which has increased and the quantity of data available in various domains. One possible application of machine learning is to perform unsupervised anomaly detection. Indeed, among all available data, the anomalies are supposed to be very sparse and the expert might not have the time to label all the data as nominal or not. Many solutions exist to this unsupervised problem, but are known to provide many false alarms, because some scarce nominal modes might not be included in the training dataset and thus will be detected as anomalies. To tackle this issue, we propose to present an existing iterative algorithm, which presents potential anomaly to the expert at each iteration, and compute a new boundary according to this feedback using One Class Support Vector Machine.

Signal and image processing / Space communication systems

READ MORE

Wing 3D Reconstruction by Constraining the Bundle Adjustment with Mechanical Limitations

Authors: Demoulin Quentin, Lefebvre-Albaret François, Basarab Adrian, Kouamé Denis and Tourneret Jean-Yves

In Proc. 28th European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands, January 18-22, 2021.

DOWNLOAD DOCUMENT

The estimation of wing deformation is part of the certification of an aircraft. Wing deformation can be obtained from 3D reconstructions based on conventional multiview photogrammetry. However, 3D reconstructions are generally degraded by the variable flight environments that degrade the quality of 2D images. This paper addresses this issue by taking benefit from a priori knowledge of the wing mechanical behaviour. Specifically, mechanical limits are considered to regularize the bundle adjustment within the photogrammetry reconstruction. The performance of the proposed approach is evaluated on a real case, using data acquired on an aircraft A350-900.

Signal and image processing / Aeronautical communication systems

READ MORE

PhD Thesis

Routeur embarqué pour les communications critiques aéronautiques en environnement multi liens

Author: Tran N'Guyen Hoang Alexandre

Defended on January 20, 2021.

DOWNLOAD DOCUMENT

Critical aeronautical communications are a major issue for flight safety. For a long time, these have relied solely on voice, which is transmitted via an analog communication system. Given the growth in air traffic, this mean of communication has reached saturation and moreover, it has sometimes shown its limits in terms of understanding voice messages, hence the need to find an alternative method. The development of communication technologies based on digital signals allows text messages to be exchanged over a long distance. Initially reserved for noncritical airline operations, it was quickly adopted for communications between the pilot and the air traffic controller, in order to offload the dedicated radio channel. This is known as Data Link. This system, included in a more global infrastructure called the ATN/OSI, has the double advantage of relieving congestion on the frequencies used, but also of limiting the misunderstanding of certain messages. The next evolutions of this aeronautical communication system based on the IP suite and called ATN/IPS is under development. It will have to solve certain problems by proposing new communication technologies and innovative network solutions that can adapt to the increase in critical air data traffic. In this thesis, we address several issues related to the development of ATN/IPS. The first one concerns the network mobility of the aircraft. Indeed, the ATN/IPS will gather several operators, each providing their own subnetworks composed of one or more access methods. Given the limited range of some of them, an aircraft necessarily needs to use several of them during a flight. A handover is triggered as soon as an aircraft connects to a new ground station, which in some cases requires a change in routing to the aircraft. We propose to combine and adapt two mobility protocols, PMIPv6 and LISP, to guarantee continuity of critical data transmission while minimizing the impact on the avionics architecture and the radio communication channel. Our solution is compared to a standard IP mobility solution in a simulated network environment and specifically developed under OMNeT++. The results show that our approach reduces the handover delay, while lightening the signaling traffic on the radio channel. Moreover, in order to propose the best aircraft connectivity, we propose an automation of the selection of the best links in the multilink and ATN/IPS context. Typically, multilink algorithms (or link selection) are split into three parts : collecting link information, deciding which links to use, and using the new links. As the mobility solution proposed in this thesis is also compatible with multilink, we are interested in the first two steps. We propose to use an active method to probe the links and estimate their quality. This approach has the advantage of being independent of the underlying communication technologies. We then compare three estimation methods based on round trip delay and evaluate the performance of each of them. The first method is based on threshold determination, the second is based on a probabilistic model and the third uses supervised learning. This learning-based method makes it possible to estimate the link over time with good precision. Finally, we propose a link selection algorithm in the case where the primary link no longer meets the quality of service requirements.

Networking / Aeronautical communication systems

READ MORE

Journal Paper

Hypersphere Fitting from Noisy Data Using an EM Algorithm

Authors: Lesouple Julien, Pilastre Barbara, Altmann Yoann and Tourneret Jean-Yves

IEEE Signal Processing Letters, vol. 28, pp. 314-318, January, 2021.

DOWNLOAD DOCUMENT

This letter studies a new expectation maximization (EM) algorithm to solve the problem of circle, sphere and more generally hypersphere fitting. This algorithm relies on the introduction of random latent vectors having a priori independent von Mises-Fisher distributions defined on the hypersphere. This statistical model leads to a complete data likelihood whose expected value, conditioned on the observed data, has a Von Mises-Fisher distribution. As a result, the inference problem can be solved with a simple EM algorithm. The performance of the resulting hypersphere fitting algorithm is evaluated for circle and sphere fitting.

Signal and image processing / Earth observation

READ MORE

GNSS Data Demodulation over Fading Environments: Antipodal and M-ary CSK Modulations

Authors: Ortega Espluga Lorenzo, Vilà-Valls Jordi, Poulliat Charly and Closas Pau

IET Radar, Sonar & Navigation, January, 2021.

DOWNLOAD DOCUMENT

This article investigates new strategies to compute accurate low-complexity Log Likelihood Ratio (LLR) values based on the Bayesian formulation under uncorrelated fading channels for both antipodal and CSK modulations when no Channel State Information (CSI) is available at the receiver. These LLR values are then used as input to modern error correcting schemes used in the data decoding process of last generation GNSS signals. Theoretical analysis based on the maximum achievable rate is presented for the different methods in order to evaluate the performance degradation with respect to the optimal CSI channel. Finally, Frame Error Rate (FER) simulation results are shown, validating the appropriate performance of the proposed LLR approximation methods.

Signal and image processing / Localization and navigation and Space communication systems

READ MORE

PhD Defense Slides

Onboard IP router for critical aeronautical communications in a heterogeneous environment

Author: Tran N'Guyen Hoang Alexandre

Defended on January 20, 2021.

DOWNLOAD DOCUMENT

Critical aeronautical communications are a major issue for flight safety. For a long time, these have relied solely on voice, which is transmitted via an analog communication system. Given the growth in air traffic, this mean of communication has reached saturation and moreover, it has sometimes shown its limits in terms of understanding voice messages, hence the need to find an alternative method. The development of communication technologies based on digital signals allows text messages to be exchanged over a long distance. Initially reserved for noncritical airline operations, it was quickly adopted for communications between the pilot and the air traffic controller, in order to offload the dedicated radio channel. This is known as Data Link. This system, included in a more global infrastructure called the ATN/OSI, has the double advantage of relieving congestion on the frequencies used, but also of limiting the misunderstanding of certain messages. The next evolutions of this aeronautical communication system based on the IP suite and called ATN/IPS is under development. It will have to solve certain problems by proposing new communication technologies and innovative network solutions that can adapt to the increase in critical air data traffic. In this thesis, we address several issues related to the development of ATN/IPS. The first one concerns the network mobility of the aircraft. Indeed, the ATN/IPS will gather several operators, each providing their own subnetworks composed of one or more access methods. Given the limited range of some of them, an aircraft necessarily needs to use several of them during a flight. A handover is triggered as soon as an aircraft connects to a new ground station, which in some cases requires a change in routing to the aircraft. We propose to combine and adapt two mobility protocols, PMIPv6 and LISP, to guarantee continuity of critical data transmission while minimizing the impact on the avionics architecture and the radio communication channel. Our solution is compared to a standard IP mobility solution in a simulated network environment and specifically developed under OMNeT++. The results show that our approach reduces the handover delay, while lightening the signaling traffic on the radio channel. Moreover, in order to propose the best aircraft connectivity, we propose an automation of the selection of the best links in the multilink and ATN/IPS context. Typically, multilink algorithms (or link selection) are split into three parts : collecting link information, deciding which links to use, and using the new links. As the mobility solution proposed in this thesis is also compatible with multilink, we are interested in the first two steps. We propose to use an active method to probe the links and estimate their quality. This approach has the advantage of being independent of the underlying communication technologies. We then compare three estimation methods based on round trip delay and evaluate the performance of each of them. The first method is based on threshold determination, the second is based on a probabilistic model and the third uses supervised learning. This learning-based method makes it possible to estimate the link over time with good precision. Finally, we propose a link selection algorithm in the case where the primary link no longer meets the quality of service requirements.

Networking / Aeronautical communication systems

READ MORE

Conference Paper

Reactivity Enhancement of Cooperative Congestion Control for Satellite Networks

Authors: Thibaud Adrien, Fasson Julien, Arnal Fabrice, Sallantin Renaud, Dubois Emmanuel and Chaput Emmanuel

In Proc. Hot Information-Centric Networking (HotICN), Hefei, Anhui, China, December 12-14, 2020.

DOWNLOAD DOCUMENT

The new paradigm of Information Centric Network (ICN) proposes a shift from the host-centric model to a contentcentric model. This approach, especially well suited to the current Internet’s usage, is promising for Satellite Networks. In particular, Named Data Networking (NDN) architecture seems to be a great candidate: it gathers the benefits of Content Delivery Networks (CDN), Peer-to-Peer networks (P2P) and HTTP in the network layer. In this study, we propose to compare the performances of TCP-like congestion control algorithms and our new Cooperative Congestion Control (CCC) approach. CCC is a pace-based multipath and multi-flow aware congestion control. We evaluate those algorithms with simulations on a topology where we place the satellite link on different positions. We show that CCC outperforms window-based algorithms but has still some drawbacks. We thus proposed an enhancement of CCC that corrects the flaws by increasing its reactivity. Simulations results show that the performances on terrestrial scenarios are also enhanced.

Networking / Other

READ MORE

Journal Paper

Joint Delay-Doppler Estimation Performance in a Dual Source Context

Authors: Lubeigt Corentin, Ortega Espluga Lorenzo, Vilà-Valls Jordi, Lestarquit Laurent and Chaumette Eric

Remote sensing, vol. 12, issue 3, p. 3894, November, 2020.

DOWNLOAD DOCUMENT

Evaluating the time-delay, Doppler effect and carrier phase of a received signal is a challenging estimation problem that was addressed in a large variety of remote sensing applications. This problem becomes more difficult and less understood when the signal is reflected off one or multiple surfaces and interferes with itself at the receiver stage. This phenomenon might deteriorate the overall system performance, as for the multipath effect in Global Navigation Satellite Systems (GNSS), and mitigation strategies must be accounted for. In other applications such as GNSS reflectometry (GNSS-R) it may be interesting to estimate the parameters of the reflected signal to deduce the geometry and the surface characteristics. In either case, a better understanding of this estimation problem is directly brought by the corresponding lower performance bounds. In the high signal-to-noise ratio regime of the Gaussian conditional signal model, the Cramér-Rao bound (CRB) provides an accurate lower bound in the mean square error sense. In this article, we derive a new compact CRB expression for the joint time-delay and Doppler estimation in a dual source context, considering a band-limited signal and its specular reflection. These compact CRBs are expressed in terms of the baseband signal samples, making them especially easy to use whatever the baseband signal considered, therefore being valid for a variety of remote sensors. This extends existing results in the single source context and opens the door to a plethora of usages to be discussed in the article. The proposed CRB expressions are validated in two representative navigation and radar examples.

Signal and image processing / Localization and navigation

READ MORE

Seeing around corners with edge-resolved transient imaging

Authors: Rapp J., Saunders C., Tachella Julian, Murray-Bruce John, Altmann Yoann, Tourneret Jean-Yves, McLaughlin Stephen, Dawson R.M.A., Wong Franco N.C. and Goyal Vivek K.

Nat. Commun., vol. 11, no. 1, pp. 5929, November 23, 2020.

DOWNLOAD DOCUMENT

Non-line-of-sight (NLOS) imaging is a rapidly growing field seeking to form images of objects outside the field of view, with potential applications in autonomous navigation, reconnaissance, and even medical imaging. The critical challenge of NLOS imaging is that diffuse reflections scatter light in all directions, resulting in weak signals and a loss of directional information. To address this problem, we propose a method for seeing around corners that derives angular resolution from vertical edges and longitudinal resolution from the temporal response to a pulsed light source. We introduce an acquisition strategy, scene response model, and reconstruction algorithm that enable the formation of 2.5-dimensional representations—a plan view plus heights—and a 180∘ field of view for large-scale scenes. Our experiments demonstrate accurate reconstructions of hidden rooms up to 3 meters in each dimension despite a small scan aperture (1.5-centimeter radius) and only 45 measurement locations.

Signal and image processing / Other

READ MORE

PhD Thesis

Estimation Parcimonieuse et Apprentissage de Dictionnaires pour la Détection d'Anomalies Multivariées dans des Données Mixtes de Télémesure Satellite

Author:

Defended on November 6, 2020.

La surveillance automatique de systèmes et la prévention des pannes sont des enjeux majeurs dans de nombreux secteurs et l’industrie spatiale ne fait pas exception. Par exemple, le succès des missions des satellites suppose un suivi constant de leur état de santé réalisé à travers la surveillance de la télémesure. Les signaux de télémesure sont des données issues de capteurs embarqués qui sont reçues sous forme de séries temporelles décrivant l’évolution dans le temps de différents paramètres. Chaque paramètre est associé à une grandeur physique telle qu’une température, une tension ou une pression, ou à un équipement dont il reporte le fonctionnement à chaque instant. Alors que les approches classiques de surveillance atteignent leurs limites, les méthodes d’apprentissage automatique (machine learning en anglais) s’imposent afin d’améliorer la surveillance de la télémesure via un apprentissage semi-supervisé : les signaux de télémesure associés à un fonctionnement normal du système sont appris pour construire un modèle de référence auquel sont comparés les signaux de télémesure récemment acquis. Les méthodes récentes proposées dans la littérature ont permis d’améliorer de manière significative le suivi de l’état de santé des satellites mais elles s’intéressent presque exclusivement à la détection d’anomalies univariées pour des paramètres physiques traités indépendamment. L’objectif de cette thèse est de proposer des algorithmes pour la détection d’anomalies multivariées capables de traiter conjointement plusieurs paramètres de télémesure associés à des données de différentes natures (continues/discrètes),et de prendre en compte les corrélations et les relations qui peuvent exister entre eux. L’idée motrice de cette thèse est de supposer que la télémesure fraîchement reçue peut être estimée à partir de peu de données décrivant un fonctionnement normal du satellite. Cette hypothèse justifie l’utilisation de méthodes d’estimation parcimonieuse et d’apprentissage de dictionnaires qui seront étudiées tout au long de cette thèse. Une deuxième forme de parcimonie propre aux anomalies satellites a également motivé ce choix, à savoir la rareté des anomalies satellites qui affectent peu de paramètres en même temps. Dans un premier temps, un algorithme de détection d’anomalies multivariées basé sur un modèle d’estimation parcimonieuse est proposé. Une extension pondérée du modèle permettant d’intégrer de l’information externe est également présentée ainsi qu’une méthode d’estimation d’hyper paramètres qui a été développée pour faciliter la mise en oeuvre de l’algorithme. Dans un deuxième temps, un modèle d’estimation parcimonieuse avec un dictionnaire convolutif est proposé. L’objectif de cette deuxième méthode est de contourner le problème de non-invariance par translation dont souffre le premier algorithme. Les différentes méthodes proposées sont évaluées sur plusieurs cas d’usage industriels associés à de réelles données satellites et sont comparées aux approches de l’état de l’art.

READ MORE

Activity Report

READ MORE

Apply for a PhD in Safran

Codirection by Toulouse INP & ISAE-Supaero

READ MORE

PhD positions available at TeSA

PhD subjects available on the CNES site.
On line application before the 2nd of April.

READ MORE

EUSIPCO 2020

Conference talk of Julien Lesouple at EUSIPCO 2020

READ MORE