Gérard Dreyfus

• PhD
• Professor Emeritus at École Supérieure de Physique et de Chimie Industrielles (ESPCI Paris - PSL)

In the organic laboratory, the 13C nuclear magnetic resonance (NMR) spectrum of a newly synthesized compound remains an essential step in elucidating its structure. For the chemist, the interpretation of such a spectrum, which is a set of chemical-shift values, is made easier if he/she has a tool capable of predicting with sufficient accuracy the c...

NMR spectroscopy, which is based on the phenomenon of nuclear magnetic resonance, has been widely popularized by its application in medical imaging under the name of MRI. In the organic laboratory, the 13C NMR spectrum of a newly synthetized compound remains an essential step in elucidating its structure. For the chemist, the interpretation of such...

Background: Electroencephalography (EEG) stands as a pivotal non-invasive tool, capturing brain signals with millisecond precision and enabling real-time monitoring of individuals' mental states. Using appropriate biomarkers extracted from these EEG signals and presenting them back in a neurofeedback loop offers a unique avenue for promoting neural...

Background Though not originally developed for this purpose, the Healthy Aging Brain Care Monitor (HABC-M) seems a valuable instrument for assessing anosognosia in Alzheimer’s disease (AD). Objectives Our study aimed at 1) investigating the validity of the HABC-M (31 items), and its cognitive, psychological, and functional subscales, in discrimina...

Unawareness of memory deficits is an early manifestation in patients with Alzheimer's disease (AD), which often delays diagnosis. This intriguing behavior constitutes a form of anosognosia, whose neural mechanisms remain largely unknown. We hypothesized that anosognosia may depend on a critical synaptic failure in the error-monitoring system, which...

Background Electroencephalography (EEG) is a non-invasive method that records the brain signals with time resolution in the millisecond range, thereby allowing the monitoring of subjects’ mental states in real time. Using appropriate biomarkers extracted from these EEG signals and presenting them back in a neurofeedback loop can foster neural compe...

Enhanced body awareness has been suggested as one of the cognitive mechanisms that characterize mindfulness. Yet neuroscience literature still lacks strong empirical evidence to support this claim. Body awareness contributes to postural control during quiet standing; in particular, it may be argued that body awareness is more strongly engaged when...

Unawareness of memory deficits is an early manifestation in patients with Alzheimer’s disease (AD). This intriguing behavior constitutes a form of anosognosia and has neural mechanisms that remain largely unknown. Here, we hypothesized that it may result from a failure in the error-monitoring system, which would prevent AD patients from being aware...

Anosognosia, or the lack of awareness of one's own impairment, is frequent for memory deficits in patients with Alzheimer's disease (AD). Although often related to frontal dysfunctions, the neural mechanisms of anosognosia remain largely unknown. We hypothesized that anosognosia in AD may result from a failure in the error-monitoring system, thus p...

Background Alzheimer’s disease (AD) patients are often unaware of their memory deficits even at early stage of disease. Anosognosia has been related to frontal dysfunction although its underlying neural mechanism is still unknown. We hypothesized that it may result from an inability to monitor ongoing behavior due to a failure in the error‐monitori...

EEG-based passive brain-computer interfaces (BCIs) estimate the subjects’ mental states in real time, using appropriate biomarkers extracted from electroencephalographic signals. These BCIs, when present in a neurofeedback loop, make it possible to apply neurophysiological regulation to foster neural compensation mechanisms by teaching subjects to...

Introduction Tout apprentissage repose sur la capacité de prendre conscience de l’erreur. Cependant, les mécanismes d’apprentissage peuvent être altérés par une charge cognitive trop élevée. Ce concept fait notamment référence à la capacité limitée de la mémoire de travail. Objectifs Nous faisons l’hypothèse qu’une charge cognitive élevée serait s...

We developed a brain–computer interface (BCI) able to continuously monitor working memory (WM) load in real-time (considering the last 2.5 s of brain activity). The BCI is based on biomarkers derived from spectral properties of non-invasive electroencephalography (EEG), subsequently classified by a linear discriminant analysis classifier. The BCI w...

The COVID-19 epidemic is confronting the healthcare community with an unprecedented situation; in particular, patient triage requires physicians to make hard decisions. There is a clear need for decision support systems in clinical medicine during epidemics, and we believe that Machine Learning might be of particular interest in this context.

The viscosities of pure liquids are estimated at 25 °C, from their molecular structure, using three modeling approaches, namely, group contributions, COSMO-RS σ-moment-based neural networks, and graph machines. The last two are machine-learning methods, whereby models are designed and trained from a database of viscosities of 300 molecules, at 25 °...

We developed a framework to study brain dynamics under cognition. In particular, we investigated the spatiotemporal properties of brain state switches under cognition. The lack of electroencephalography stationarity is exploited as one of the signatures of the metastability of brain states. We correlated power law exponents in the variables that we...

We introduce a cognitive brain–computer interface based on a continuous performance task for the monitoring of variations of visual sustained attention, i.e. the self-directed maintenance of cognitive focus in non-arousing conditions while possibly ignoring distractors and avoiding mind wandering. We introduce a visual sustained attention continuou...

This study addresses the problem of Alzheimer’s disease (AD) diagnosis with Electroencephalography (EEG). The use of EEG as a tool for AD diagnosis has been widely studied by comparing EEG signals of AD patients only to those of healthy subjects. By contrast, we perform automated EEG diagnosis in a differential diagnosis context using a new databas...

Steady state visual evoked potentials (SSVEPs) have been identified as an effective solution for brain computer interface (BCI) systems as well as for neurocognitive investigations. SSVEPs can be observed in the scalp-based recordings of electroencephalogram signals, and are one component buried amongst the normal brain signals and complex noise. W...

The efficiency of four modeling approaches, namely group contributions, corresponding-states principle, σ-moment-based neural networks, and graph machines, are compared for the estimation of the surface tension (ST) of 269 pure liquid compounds at 25 °C from their molecular structure. This study focuses on liquids containing only carbon, oxygen, hy...

We present our preliminary developments on a biofeedback interface for Western operatic style training, combining performance and result biofeedback. Electromyographic performance feedbacks, as well as formant-tuning result feedbacks are displayed visually, using continuously scrolling displays, or discrete post-trial evaluations. Our final aim is...

Significant progress was made in devices and software for recording and analyzing bio-physiological signals (EEG, MEG, EMG, …). This poster presents a description of our new open-source Matlab-based toolbox, designed in order to help with EEG data processing. Named SIGMAbox for “SIGnal processing and MAchine Learning”. SIGMAbox gathers several pre-...

During the past few years, significant progress was made in devices and softwarefor recording and analyzing bio-physiological signals. This short paper presents a generaldescription of our current project: a new open-source Matlab-based toolbox, designed in orderto help with biosignal data processing. SIGMAbox (SIGnal processing and MAchine Learnin...

Understanding the neurocognitive mechanisms involved in feedback-based learning is a central question for bio/neurofeedback paradigms. We propose incorporating electrophysiological measurements of brain activity into a standard biofeedback approach of control of vocal performance, in order to investigate mechanisms of feedback-based learning. The i...

This article describes the development of a platform designed to visualize the 3D motion of the tongue using ultrasound image sequences. An overview of the system design is given and promising results are presented. Compared to the analysis of motion in 2D image sequences, such a system can provide additional visual information and a quantitative d...

A new contour-tracking algorithm is presented for ultrasound tongue image sequences, which can follow the motion of tongue contours over long durations with good robustness. To cope with missing segments caused by noise, or by the tongue midsagittal surface being parallel to the direction of ultrasound wave propagation, active contours with a conto...

The article presents an easy to implement approach for indoor localization and navigation that combines Bayesian filtering with support vector machine classifiers to associate high-dimensionality cellular telephone network received signal strength fingerprints to distinct spatial regions. The technique employs a “space sampling” and a “time samplin...

We investigate the neural correlates of visual working memory using electroencephalography (EEG). Our objective is to develop a cognitive Brain-Computer Interface (BCI) able to monitor visual working memory load in real-time. A system with these properties would eventually have different applications, such as training, rehabilitation, or safety whi...

We investigate the neural correlates of visual working memory using electroencephalography (EEG). Our objective is to develop a cognitive Brain-Computer Interface (BCI) able to monitor visual working memory load in real-time. A system with these properties would eventually have different applications, such as training, rehabilitation, or safety whi...

In this paper, we introduce a novel entropy measure, termed epoch-based entropy. This measure quantifies disorder of EEG signals both at the time level and spatial level, using local density estimation by a Hidden Markov Model on inter-channel stationary epochs. The investigation is led on a multi-centric EEG database recorded from patients at an e...

Studying tongue motion during speech using ultrasound is a standard procedure, but automatic ultrasound image labelling remains a challenge, as standard tongue shape extraction methods typically require human intervention. This article presents a method based on deep neural networks to automatically extract tongue contour from ultrasound images on...

Ultra-Wideband technology provides accurate localization in indoor environments using time-of-arrival based ranging techniques; however, the positioning accuracy is degraded by non-line-of-sight conditions. In this work, the relation between the non-line-of-sight path length error and the obstacles on the path from transmitter to receiver is used a...

Development of brain-computer interfaces interacting with cognitive functions is a hot topic in neural engineering since it may lead to innovative and powerful diagnosis, rehabilitation, and training methods. This paper addresses the problem of measuring sustained visual attention using electroencephalography and presents an experiment inspired by...

A 13-command Brain-Computer Interface (BCI) based on Steady-State Visual Evoked Potentials (SSVEP) is assessed. The SSVEPs are simulated from VEP sequences recorded by electroencephalography (EEG) on the same subjects. SSVEP features extracted in the time domain are averaged over all channels of the occipital region. Most subjects achieved satisfac...

Steady state visual evoked potentials (SSVEP) have been identified as a highly viable solution for brain computer interface (BCI) systems. The SSVEP is observed in the scalp-based recordings of electroencephalogram (EEG) signals, and is one component buried amongst the normal brain signals and complex noise. By taking advantage of sample diversity,...

Steady state visual evoked potentials (SSVEP) have been identified as a highly viable solution for brain computer interface (BCI) systems. The SSVEP is observed in the scalp-based recordings of electroencephalogram (EEG) signals, and is one component buried amongst the normal brain signals and complex noise. By taking advantage of sample diversity,...

This paper deals with new capturing technologies to safeguard and transmit endangered intangible cultural heritage including Corsican multipart singing technique. The described work, part of the European FP7 i-Treasures project, aims at increasing our knowledge on rare singing techniques. This paper includes (i) a presentation of our light hyper-he...

Gadolinium(III) complexes constitute the largest class of compounds used as contrast agents for Magnetic Resonance Imaging (MRI). A quantitative structure-property relationship (QSPR) machine-learning based method is applied to predict the thermodynamic stability constants of these complexes (log KGdL), a property commonly associated with the toxic...

This paper presents an early version of an open extendable research and educational platform to support users in learning and mastering the different types of rare-singing. The platform is interfaced with a portable helmet to synchronously capture multiple signals during singing in a non-laboratory environment. Collected signals reflect articulator...

We investigate a prospective path to processing 'big data' in the field of computer-aided drug design, motivated by the expected increase of the size of available databases. We argue that graph machines, which exempt the designer of a predictive model from handcrafting, selecting and computing ad hoc molecular descriptors, may open a way toward eff...

The article presents an indoor localization scheme for mobile devices based on GSM Received Signal Strength fingerprints combined with embedded sensor information and an area site map. Displacements of a mobile user are first estimated using a sensor dead-reckoning approach that adapts stride length to different users and environments, and a dynami...

Steady-state visual evoked potentials (SSVEPs) are widely used in the design of brain-computer interfaces (BCIs). A lot of effort has therefore been devoted to find a fast and reliable way to detect SSVEPs. We study the link between transient and steady-state VEPs and show that it is possible to predict the spectral content of a subject's SSVEPs by...

In this paper, we address the problem of detecting steady-state visual evoked potentials (SSVEPs) in EEG signals by using a set of simulated trains of VEPs instead of the sine-waves basis typically used in Fourier Transform. The detection algorithm is calibrated using the subject's brain response to visual stimulation. The original contribution of...

Although noninvasive brain-computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over the recent decades, their performance is still limited in two important aspects. First, the difficulty of performing a reliable detection of BCI commands increases when EEG epoch length decreases, which makes high...

Blind source separation (BSS) is an effective and powerful tool for signal processing and artifact removal in electroencephalographic signals. For real-time applications such as brain–computer interfaces, cognitive neuroscience or clinical neuromonitoring, it is of prime importance that BSS is effectively performed in real time. In order to improv...

The purpose of this study is to optimize the selection of prophylactic cardioverter defibrillator implantation candidates. Currently, the main criterion for implantation is a low Left Ventricular Ejection Fraction (LVEF) whose specificity is relatively poor. We designed two classifiers aimed to predict, from long term ECG recordings (Holter), wheth...

The article proposes a real-time technique for visualizing tongue motion driven by ultrasound image sequences. Local feature description is used to follow characteristic speckle patterns in a set of mid-sagittal contour points in an ultrasound image sequence, which are then used as markers for describing movements of the tongue. A 3D tongue model i...

Résumé long de la communication visible au lien suivant: http://www.qmu.ac.uk/casl/conf/ultrafest%5F2013/docs/AJaumard-Hakoun_1_Ultrafest.pdf

We present a new machine learning approach to flash flood forecasting in the absence of rainfall forecasts, based on the agglomerative hierarchical clustering of flood events. Each cluster contains events whose models have similar behaviors. Specific Support Vector Regression models are then trained from each cluster. The test results show that a s...

Several studies showed that EEG signal of Alzheimer's disease patients is less complex than that of healthy subjects. In this article, we propose to characterize the complexity of the EEG signal by an entropy measure based on local density estimation by a Hidden Markov Model. We first show that this measure leads to consistent results qualitatively...

The article presents a simple, practical approach for indoor localization using Received Signal Strength fingerprints from the GSM network, including an analysis of the relationship between signal strength and location, and the evolution of localization performance over time. Support Vector Machine regression applied to very high dimensional finger...

The article describes a system that uses real time measurements of the vocal tract to drive a voice-replacement system for post-laryngectomy patients. Based on a thermoformed acquisition helmet, miniature ultrasound machine, and video camera, and incorporating Hidden Markov Model speech recognition, the device has been tested on three speakers, one...

Oxidative stress is involved in chronic and acute pathologies: cardiovascular, neurodegenerative, neoplastic, inflammatory and infectious diseases. Clinical trials focused on prevention of cardiovascular and neoplastic diseases involving antioxidant supplementation have however provided predominantly negative obserations in large-scale studies. Scr...

Steady-state visually evoked potentials (SSVEP) can be elicited by a large variety of stimuli. To the best of our knowledge, the size and shape effect of stimuli has never been investigated in the literature. We study the relationship between the visual parameters (size and shape) of the stimulation and the resulting brain response. A tentative phy...

Accurately localizing users in indoor environments remains an important and challenging task. The article presents new results on room-level indoor localization, using cellular Received Signal Strength fingerprints collected with a standard cellular handset programmed to perform fast scans of the 900 and 1800 Megahertz GSM bands as a user explores...

A Brain Computer Interface (BCI) is a system where a direct connection is established between the brain and a computer, providing a subject with a new communication channel. Unfortunately, BCI have many drawbacks: signal recording is problematic, brain signatures are non reproducible from individual to individual, etc. A dependent-BCI prototype, th...

“Cévenol flash floods” are famous in the field of hydrology, because they are archetypical of flash floods that occur in populated areas, thereby causing heavy damages and casualties. As a consequence, their prediction has become a stimulating challenge to designers of mathematical models, whether physics based or machine learning based. Because cu...

The development of a continuous visual speech recognizer for a silent speech interface has been investigated using a visual speech corpus of ultrasound and video images of the tongue and lips. By using high-speed visual data and tied-state cross-word triphone HMMs, and including syntactic information via domain-specific language models, word-level...

A new approach to indoor localization is presented, based upon the use of Received Signal Strength (RSS) fingerprints containing data from very large numbers of cellular base stations--up to the entire GSM band of over 500 channels. Machine learning techniques are employed to extract good quality location information from these high-dimensionality...

The work presents advances in the implementation of an ultrasound based silent speech interface system. Use of a portable acquisition device, a visual speech recognizer system with a language model, and real time tests with the Julius system are described. Experiments with two types of visual feature extraction are also presented. Results show that...

The article presents the results of tests of a portable post-laryngectomy voice replacement system that allows a silently articulating speaker to select and play back short phrases contained in a 60-phrase phrasebook. Such a system could be a useful communication tool for post-laryngectomy patients unable to use tracheo-oesophageal speech. Experime...

In the context of Silent Speech Communication (SSC) development after total laryngectomy rehabilitation, tongue and lip movements were recorded with a portable ultrasound transducer and a CCD video camera respectively. A list of 60 French minimal-pairs and a list of 50 most frequent French words were pronounced in vocalized and silent mode by one s...

Intégralité des actes de cette conférence disponible au lien suivant: http://www.issp2011.uqam.ca/upload/files/proceedings.pdf

Arrhythmia classification remains a major challenge for appropriate therapy delivery in implantable cardioverter defibrillators (ICDs). The purpose of this paper is to present a new algorithm for arrhythmia discrimination based on a statistical classification by support vector machines of a novel 2-D representation of electrograms (EGMs) named spat...

Electroencephalographic (EEG) signals are generally non-stationary, however, nearly stationary brain responses, such as steady-state visually evoked potentials (SSVEP), can be recorded in response to repetitive stimuli. Although Fourier transform has precise resolution with long time windows (5 or 10 s for instance) to extract SSVEP response (1-100...

Implantable Cardioverter Defibrillators (ICD) are widely used for sudden cardiac death prevention. In most ICD algorithms, decision making includes a morphological analysis of the unipolar and/or bipolar electrograms (EGM). The principle of such algorithms is to create a "normal" template by averaging normal sinus rhythm heartbeats, for comparison...

A new technique developed at ESPCI ParisTech should allow cellular received signal strength fingerprints to play an important role in localization systems for regions which are not well covered by GPS. The article describes the ARPEGEO project, initiated to evaluate the impact of full-band GSM fingerprints analyzed with modern machine learning tech...

A study is made of subsets of relevant GSM carriers for an indoor localization problem. A database was created containing power measurement scans of all available GSM carriers in 5 of 8 rooms of a second storey laboratory in central Paris, France, and a statistical learning algorithm developed to discriminate between rooms based on these carrier st...

This article presents a segmental vocoder driven by ultrasound and optical images (standard CCD camera) of the tongue and lips for a “silent speech interface” application, usable either by a laryngectomized patient or for silent communication. The system is built around an audio–visual dictionary which associates visual to acoustic observations for...

Introduction The aim of the study was to assess the time course effect of IKr blockade on ECG biomarkers of ventricular repolarization and to evaluate the accuracy of a fully automatic approach for QT duration evaluation. Methods 12-lead digital ECG Holter were recorded in 38 healthy subjects (27 males, mean age=27.4±8.0 years) on baseline conditio...

The aim of the study was to assess the time course effect of IKr blockade on ECG biomarkers of ventricular repolarization and to evaluate the accuracy of a fully automatic approach for QT duration evaluation. Twelve-lead digital ECG Holter was recorded in 38 healthy subjects (27 males, mean age = 27.4 + or - 8.0 years) on baseline conditions (day 0...

For a number of patients eligible for ICD implantation, a single chamber (VR) model is sufficient. But to improve performances in arrhythmias classification, a dual chamber (DR) ICD could be preferred. However, to use DR algorithms with VR systems, atrial sensing is missing. This study uses a machine learning technique (Independent Component Analys...

Discrimination of Ventricular Tachycardia (VT) from Supra-Ventricular Tachycardia (SVT) remains a major challenge for appropriate therapy delivery in ICDs. Historically, only time intervals extracted from electrograms (EGMs) were used for diagnosis. Morphology algorithms were added to improve performances. We propose a new discrimination algorithm...

Indoor handset localization in an urban apartment setting is studied using GSM trace mobile measurements. Nearest-neighbor, Support Vector Machine, Multilayer Perceptron, and Gaussian Process classifiers are compared. The linear Support Vector Machine provides mean room classification accuracy of almost 98% when all GSM carriers are used. To our kn...

For the problem that recurrence leads to the difficulty in finding a solution to partial differential equations in recurrent least square support vector machines regression(RLSSVM), analytical method is proposed to solve the equations, in which recurrence is taken into consideration, so that a complete recurrent least square support vector machines...

We describe a new algorithm for the estimation of Cycle Lengths (CL) in the atria. In the spirit of wavelet transforms, the algorithm correlates the electrogram (EGM) signal to a set of functions that are specifically designed to extract the cycle length present in the signal on a given time window. This provides a CL vs time map, which is a highly...

We propose a new approach to fully automatic ECG wave extraction and morphology tracking. It is based on Generalized Orthogonal Forward Regression (GOFR), which allows decomposing a one-dimensional signal into a set of appropriate parameterized functions. Two applications of GOFR to ECG modeling are presented. First, in order to delineate ECG chara...

Discrimination of Ventricular Tachycardia (VT) from Supra-Ventricular Tachycardia (SVT) remains a major challenge for appropriate therapy delivery in Implantable Cardioverter Defibrillators (ICDs), especially in single chamber devices. We propose here a new discrimination algorithm that analyzes, with a machine learning approach, the morphology of...

Recent improvements are presented for phonetic decoding of continuous-speech from ultrasound and optical observations of the tongue and lips in a silent speech interface application. In a new approach to this critical step, the visual streams are modeled by context-dependent multi-stream Hidden Markov Models (CD-MSHMM). Results are compared to a ba...

Support vector machines are widely used for classification and regression tasks. They provide reliable static models, but their extension to the training of dynamic models is still an open problem. In the present paper, we describe regularized recurrent support vector machines, which, in contrast to previous recurrent support vector machine, models...

GSM trace mobile measurements are used to study indoor handset localization in an urban apartment setting. Nearest-neighbor, support vector machine (SVM), and Gaussian process classifiers are compared. A linear SVM is found to provide mean room-level classification efficiency near 100%, but only when the full set of GSM carriers is used. To our kno...