Laurent Oudre

Laurent Oudre
Ecole Normale Supérieure Paris-Saclay · Machine Learning and Massive Data Analysis (MLMDA)

PhD

About

78
Publications
35,129
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
796
Citations
Introduction
Signal processing Machine learning Pattern recognition Bioengineering Gait analysis Change-point detection Dictionary learning Graph Signal Processing Video processing

Publications

Publications (78)
Article
Full-text available
In the past few years, light, affordable wearable inertial measurement units have been providing to clinicians and researchers the possibility to quantitatively study motor degeneracy by comparing gait trials from patients and/or healthy subjects. To do so, standard gait features can be used but they fail to detect subtle changes in several patholo...
Article
Au cours de la dernière décennie, l’intelligence artificielle est devenue non seulement une réalité, mais aussi un sujet de débat dans la société. L’objectif de cet exposé est de déconstruire certaines idées sur l’IA, entre mythes et réalités, en passant en revue l’histoire du domaine et ses principales avancées. La présentation détaillera les prin...
Preprint
We show we can control an epidemic reaction-diffusion on a directed, and heterogeneous, network by redirecting the flows, thanks to the optimisation of well-designed loss functions, in particular the basic reproduction number of the model. We provide a final size relation linking the basic reproduction number to the epidemic final sizes, for diffus...
Article
We consider the problem of signal interpolation on graphs, i.e. recovering one or multiple graph signal values from incomplete measurements. We propose a review of the graph signal interpolation methods, which enlightens the restrictive underlying hypothesis of signal smoothness over the graph. We formulate a new interpolation framework based on a...
Article
Full-text available
Measuring the quality of movement is a need and a challenge for clinicians. Jerk, defined as the quantity of acceleration variation, is a kinematic parameter used to assess the smoothness of movement. We aimed to assess and compare jerk metrics in asymptomatic participants for 3 important movement characteristics that are considered by clinicians d...
Article
In this paper, we propose an extension of the standard CDL problem with tensor representation, where each activation is constrained to be ‘'low-rank’' through a Canonical Polyadic decomposition. We show that this important additional constraint increases the robustness of the CDL with respect to strong noise and improve the interpretability of the...
Article
Full-text available
Postural control is often quantified by recording the trajectory of the center of pressure (COP)—also called stabilogram—during human quiet standing. This quantification has many important applications, such as the early detection of balance degradation to prevent falls, a crucial task whose relevance increases with the aging of the population. Due...
Conference Paper
This paper presents an innovative method to analyze inertial signals recorded in a semi-controlled environment. It uses an adaptive and supervised change point detection procedure to decompose the signals into homogeneous segments, allowing a refined analysis of the successive phases within a gait protocol. Thanks to a training procedure, the algor...
Conference Paper
In this paper, we propose to learn a spatial filter directly from Electroencephalography (EEG) signals using graph signal processing tools. We combine a graph learning algorithm with a high-pass graph filter to remove spatially large signals from the raw data. This approach increases topographical localization, and attenuates volume-conducted featu...
Article
Full-text available
Assessing the depth of anesthesia (DoA) is a daily challenge for anesthesiologists. The best assessment of the depth of anesthesia is commonly thought to be the one made by the doctor in charge of the patient. This evaluation is based on the integration of several parameters including epidemiological, pharmacological and physiological data. By deve...
Article
Full-text available
In this paper, we consider the problem of learning a graph structure from multivariate signals, known as graph signals. Such signals are multivariate observations carrying measurements corresponding to the nodes of an unknown graph, which we desire to infer. They are assumed to enjoy a sparse representation in the graph spectral domain, a feature w...
Preprint
We study the network reconstruction problem for an epidemic reaction-diffusion. These models are an extension of deterministic, compartmental models to a graph setting, where the reactions within the nodes are coupled by a diffusion. We study the influence of the diffusion rate, and the network topology, on the reconstruction and prediction problem...
Article
Full-text available
Video Stabilization (VS) has been an active area of research in the last two decades. Many approaches have been successfully proposed and it is time to take a step back and offer a glimpse and a critical look to this hot topic. Among the questions that should be answered : ”is VS a solved problem”?. Is there still room for further improvement and a...
Preprint
Full-text available
The analysis of the Nystagmus waveforms from eye-tracking records is crucial for the clinicial interpretation of this pathological movement. A major issue to automatize this analysis is the presence of natural eye movements and eye blink artefacts that are mixed with the signal of interest. We propose a method based on Convolutional Dictionary Lear...
Article
Full-text available
This article presents an overview of fifty-eight articles dedicated to the evaluation of physical activity in free-living conditions using wearable motion sensors. This review provides a comprehensive summary of the technical aspects linked to sensors (types, number, body positions, and technical characteristics) as well as a deep discussion on the...
Article
Introduction Le traumatisme crânien léger (TCL) est une pathologie fréquente à risque évolutif vers le syndrome post-commotionnel (SPC) comprenant des plaintes somatiques, cognitives, émotionnelles et comportementales. Ce syndrome est souvent difficile à objectiver mais il existe des outils innovants pour quantifier l’examen neurologique. L’objecti...
Article
Full-text available
The increasing number of frail elderly people in our aging society is becoming problematic: about 11% of community‐dwelling older persons are frail and another 42% are pre‐frail. Consequently, a major challenge in the coming years will be to test people over the age of 60 years to detect pre‐frailty at the earliest stage and to return them to robus...
Preprint
Full-text available
Meta-analysis is a data aggregation method that establishes an overall and objective level of evidence based on the results of several studies. It is necessary to maintain a high level of homogeneity in the aggregation of data collected from a systematic literature review. However, the current tools do not allow a cross-referencing of the experimen...
Preprint
Recently, there has been growing interest in the analysis of spectrograms of ElectroEncephaloGram (EEG), particularly to study the neural correlates of (un)-consciousness during General Anesthesia (GA). Indeed, it has been shown that order three tensors (channels x frequencies x times) are a natural and useful representation of these signals. Howev...
Conference Paper
Full-text available
The analysis of the Nystagmus waveforms from eye-tracking records is crucial for the clinical interpretation of this pathological movement. A major issue to automatize this analysis is the presence of natural eye movements and eye blink artefacts that are mixed with the signal of interest. We propose a method based on Convolutional Dictionary Learn...
Article
Humans exhibit various motor styles that reflect their intra and inter-individual variability when implementing sensorimotor transformations. This opens important questions; such as, at what point should they be readjusted to maintain optimal motor control? Do changes in motor style reveal the onset of a pathological process and can these changes h...
Article
Full-text available
Background: Objective gait assessment is key for the follow-up of patients with progressive multiple sclerosis (pMS). Inertial measurement units (IMUs) provide reliable and yet easy quantitative gait assessment in routine clinical settings. However, to the best of our knowledge, no automated step-detection algorithm performs well in detecting sever...
Article
Full-text available
The automatic detection of gait events (i.e., Initial Contact (IC) and Final Contact (FC)) is crucial for the characterisation of gait from Inertial Measurements Units. In this article, we present a method for detecting steps (i.e., IC and FC) from signals of gait sequences of individuals recorded with a gyrometer. The proposed approach combines th...
Article
Congrès Fragilité du Sujet Agé. Le Vieillissement en Santé. Prévention de la Perte d'Autonomie, Toulouse, FRA, 09-/03/2020 - 10/03/2020
Article
Full-text available
We consider the problem of detecting abrupt changes in the underlying stochastic structure of multivariate signals. A novel non-parametric and model-free off-line change-point detection method based on a kernel mapping is presented. This approach is sequential and alternates between two steps: a greedy detection to estimate a new breakpoint and a p...
Article
Full-text available
Objective: In this paper, we present an original decision support algorithm to assist the anesthesiologists delivery of drugs to maintain the optimal Depth of Anesthesia (DoA). Methods: Derived from a Transform Predictive State Representation algorithm (TPSR), our model learned by observing anesthesiologists in practice. This framework, known as...
Preprint
Full-text available
In this paper, we consider the problem of learning a graph structure from multivariate signals, known as graph signals. Such signals are multivariate observations carrying measurements corresponding to the nodes of an unknown graph, which we desire to infer. They are assumed to enjoy a sparse representation in the graph spectral domain, a feature w...
Article
Full-text available
This article presents a selective survey of algorithms for the offline detection of multiple change points in multivariate time series. A general yet structuring methodological strategy is adopted to organize this vast body of work. More precisely, detection algorithms considered in this review are characterized by three elements: a cost function,...
Conference Paper
Full-text available
This article presents a new approach for processing and subsampling multivariate time-vertex graph signals. The main idea is to model the relationships within each dimension (time, space, feature space) with different graphs and to merge these structures. A new technique based on tensor formalism is provided, which aims to identify the frequency su...
Preprint
Full-text available
This paper introduces a new multivariate convolutional sparse coding based on tensor algebra with a general model enforcing both element-wise sparsity and low-rankness of the activations tensors. By using the CP decomposition, this model achieves a significantly more efficient encoding of the multivariate signal-particularly in the high order/ dime...
Article
Full-text available
Gait assessment and quantification have received an increased interest in recent years. Embedded technologies and low-cost sensors can be used for the longitudinal follow-up of various populations (neurological diseases, elderly, etc.). However, the comparison of two gait trials remains a tricky question as standard gait features may prove to be in...
Conference Paper
Full-text available
In this paper, we present a method for learning an underlying graph topology using observed graph signals as training data. The novelty of our method lies on the combination of two assumptions that are imposed as constraints to the graph learning process: i) the standard assumption used in the literature that signals are smooth with respect to grap...
Article
Introduction Le demi-tour est évalué en routine par le nombre de pas extérieurs et sa durée, ce qui ne rend pas compte de sa cinématique complexe. Nous proposons ici une méthode quantitative d’étude et de représentation du demi-tour (le rotagramme), mesuré avec des capteurs inertiels (IMU). Méthode Trente-sept patients droitiers hémiparétiques apr...
Article
Full-text available
This article presents a method for step detection from accelerometer and gyrometer signals recorded with Inertial Measurement Units (IMUs). The principle of our step detection algorithm is to recognize the start and end times of the steps in the signal thanks to a predefined library of templates. The algorithm is tested on a database of 1020 record...
Article
Full-text available
This article proposes an implementation and a study of the paper “Adaptive Interpolation of Discrete-Time Signals That Can Be Modeled as Autoregressive Processes” by Janssen et al. The algorithm presented in this paper allows one to reconstruct an audio signal which presents localized degradations by interpolating the missing samples. This method a...
Preprint
Full-text available
In this work, methods to detect one or several change points in multivariate time series are reviewed. They include retrospective (off-line) procedure such as maximum likelihood estimation, regression, kernel methods, etc. In this large area of research, applications are numerous and diverse; many different models and operational constraints (on pr...
Preprint
Full-text available
ruptures is a Python library for offline change point detection. This package provides methods for the analysis and segmentation of non-stationary signals. Implemented algorithms include exact and approximate detection for various parametric and non-parametric models. ruptures focuses on ease of use by providing a well-documented and consistent int...
Article
Introduction Motor and sensitive disabilities deeply modify the gait pattern in progressive multiple sclerosis (MS); head–and thus cephalic sensory system- stabilization during walking is therefore a key issue for maintaining dynamic stability. This study aims at assessing the feasibility of constraining the gaze on a target while walking to limit...
Conference Paper
Full-text available
In this paper, we present a method for the creation of a library of inertial signals based on Dynamic Time Warping (DTW) for step characterization, with preliminary results in control subjects and patients with neurological diseases. Subjects performed a protocol including a 10 m straight walking, then turn back and walking for additional 10 m. The...
Conference Paper
Full-text available
We consider the problem of building shift-invariant representations for long signals in the context of distributed processing. We propose an asynchronous algorithm based on coordinate descent called DICOD to efficiently solve the $\ell_1$-minimization problems involved in convolutional sparse coding. This algorithm leverages the weak temporal depen...
Article
Full-text available
Objective We analyzed spontaneous 180° turning strategies in poststroke hemiparetic patients by using inertial measurement units (IMUs) and the association of turning strategies with risk of falls. Methods We included right paretic (RP) and left paretic (LP) post-stroke patients, and healthy controls (HCs) from a physical and rehabilitation depart...
Article
Introduction Le demi-tour est évalué en routine à l’aide du nombre de pas extérieurs et de sa durée. Ces deux paramètres ne rendent pas compte de toute la cinématique du demi-tour ce que pourraient permettre en routine les capteurs inertiels (IMUs). Nous avons : – comparé les stratégies de demi-tour spontanées des sujets hémiparétiques droits (HD)...
Article
Full-text available
For diagnosis and follow up, it is important to be able to quantify limp in an objective, and precise way adapted to daily clinical consultation. The purpose of this exploratory study was to determine if an inertial sensor-based method could provide simple features that correlate with the severity of lower limb osteoarthritis evaluated by the WOMAC...
Data
Lower limb osteoarthritis severity group, WOMAC score, BMI, age, walking velocity and the 60 parameters for the 12 control subjects and the 48 patients. Each parameter is defined by: a sensor = {head, lower back, ipsilateral foot, contralateral foot}; a frame = {sensor, office}; an axis = {AP,ML,V} if the frame is the sensor-linked frame or an axis...
Article
Objective Fall is a common complication in post-stroke populations and more likely occurs in left paretic (LP) than in right paretic patients (RP). Since kinematic characteristics of post-stroke patients’ turn have not been clearly established, the goal of this study was to analyze with inertial measurement units (IMUs) spontaneous and constraint 1...
Article
Full-text available
This article presents a method for restoring audio signals corrupted by impulsive noise such as clicks, bursts or scratches. The algorithm takes as input a degraded audio signal and automatically detects the locations of the degraded samples and replaces them with more appropriate values. Both steps (detection and interpolation) are based on the as...
Article
Full-text available
Introduction La faible qualité des acquisitions réalisées par la Wii Board Balance est souvent mise en avant comme le principal obstacle à son utilisation comme plate-forme de force pour l’évaluation de l’équilibre. Une nouvelle approche est proposée, utilisant des méthodes de traitement du signal avancée afin d’améliorer la qualité des enregistrem...
Article
Introduction L’extraction automatique des caractéristiques de la marche est utile pour quantifier objectivement les troubles de la locomotion et étudier l’évolution de diverses maladies ORL, neurologiques ou orthopédiques. On utilise pour cela des centrales inertielles sans fil enregistrant les accélérations et les vitesses angulaires. Le but est d...
Article
Introduction Le suivi longitudinal des patients atteints d’arthrose de hanche et de genou necessite des methodes de quantification de la boiterie utilisables en consultation clinique. Le but etait de realiser une etude exploratoire afin de determiner si une mesure de la boiterie a partir de capteurs inertiels et une analyse de bas niveau du signal...
Article
Full-text available
This paper presents a method for adapting the cost function in the Monge-Kantorovich Problem (MKP) to a classification task. More specifically, we introduce a criterion that allows to learn a cost function which tends to produce large distance values for elements belonging to different classes and small distance values for elements belonging to the...
Article
Physical activity (PA) level is a key element in the prevention and the treatment of several chronic diseases. In adults, low PA levels and sedentary behaviors are linked to higher risks of developing cardiovascular diseases (e.g. high blood pressure), type 2 diabetes and several types of cancers. In addition, PA is an essential component for the t...
Conference Paper
Full-text available
With the journal Image Processing On Line (IPOL), we propose to promote software to the status of regular research material and subject it to the same treatment as research papers: it must be reviewed, it must be reusable and verifiable by the research community, it must follow style and quality guidelines. In IPOL, algorithms are published with th...
Article
Full-text available
In this paper, we introduce a novel nonparametric classification technique based on the use of the Wasserstein distance. The proposed scheme is applied in a biomedical context for the analysis of recorded accelerometer data: the aim is to retrieve three types of periodic activities (walking, biking, and running) from a time-frequency representation...
Article
Full-text available
This paper describes a probabilistic approach to template-based chord recognition in music signals. The algorithm only takes chromagram data and a user-defined dictionary of chord templates as input data. No training or musical information such as key, rhythm, or chord transition models is required. The chord occurrences are treated as probabilisti...
Article
Full-text available
This paper describes a method for segmentation of triaxial accelerometer signals recorded during continuous treadmill walking. More specifically, we aim at detecting changes in speed and in incline by analyzing the accelerometer sig-nals recorded on the shin or the waist of the walker. The raw accelerometer signals are transformed either in the tim...
Conference Paper
Full-text available