Jean-Marc Girault
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jean-Marc Girault has a total of 120 co-authors. Here are the top co-authors by number of shared publications:
- Sebastien Menigot
ESEO Group,Angers,France
23 shared publications - Abdeldjalil Ouahabi
UMR 1253, iBrain, Université de Tours, Inserm, 37000 Tours, France
9 shared publications Jamal Charara
Laboratoire Signaux et Images, Université Libanaise, Al Hadath, Liban
9 shared publicationsD. Kouame
8 shared publicationsIulian Voicu
Signal & Imaging Group, University François Rabelais of Tours
8 shared publicationsI. Voicu
7 shared publications
Latest Publications
- Open Access
Symmetry in Signals: A New Insight
Symmetry is a fundamental property of many natural systems, which is observable through signals. In most out-of-equilibrium complex dynamic systems, the observed signals are asymmetric. However, for certain operating modes, some systems have demonstrated a resurgence of symmetry in their signals. Research has naturally focused on examining time invariance to quantify this symmetry. Measures based on the statistical and harmonic properties of signals have been proposed, but most of them focused on harmonic distortion without explicitly measuring symmetry. This paper introduces a new mathematical framework based on group theory for analyzing signal symmetry beyond time invariance. It presents new indicators to evaluate different types of symmetry in non-stochastic symmetric signals. Both periodic and non-periodic symmetric signals are analyzed to formalize the problem. The study raises critical questions about the completeness of symmetry in signals and proposes a new classification for periodic and non-periodic signals that goes beyond the traditional classification based on Fourier coefficients. Furthermore, new measures such as “symmetrometry” and “distorsymmetry” are introduced to quantify symmetry. These measures outperform traditional indicators like Total Harmonic Distortion (THD) and provide a more accurate measurement of symmetry in complex signals from applications where duty cycle plays a major role.
Open AccessSymmetry in Signals: A New Insight
Symmetry is a fundamental property of many natural systems, which is observable through signals. In most out-of-equilibrium complex dynamic systems, the observed signals are asymmetric. However, for certain operating modes, some systems have demonstrated a resurgence of symmetry in their signals. Research has naturally focused on examining time invariance to quantify this symmetry. Measures based on the statistical and harmonic properties of signals have been proposed, but most of them focused on harmonic distortion without explicitly measuring symmetry. This paper introduces a new mathematical framework based on group theory for analyzing signal symmetry beyond time invariance. It presents new indicators to evaluate different types of symmetry in non-stochastic symmetric signals. Both periodic and non-periodic symmetric signals are analyzed to formalize the problem. The study raises critical questions about the completeness of symmetry in signals and proposes a new classification for periodic and non-periodic signals that goes beyond the traditional classification based on Fourier coefficients. Furthermore, new measures such as “symmetrometry” and “distorsymmetry” are introduced to quantify symmetry. These measures outperform traditional indicators like Total Harmonic Distortion (THD) and provide a more accurate measurement of symmetry in complex signals from applications where duty cycle plays a major role.
- 18 April 2023
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 42 (9) , 5453-5477
Orthogonal Signal Generation: An Analytical Approach
- 18 April 2023
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 42 (9) , 5453-5477
Orthogonal Signal Generation: An Analytical Approach
- Open Access
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 133468-133478
A Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea
Cardiovascular (CV) disorders and obstructive sleep apnea (OSA) are very prevalent diseases worldwide. Multiple studies have demonstrated that OSA is associated with increased CV risk. Clinicians need to assess the CV risk to select the proper OSA treatment. A growing number of research have employed machine learning to predict CV risk by integrating clinical and sleep features. In this paper, a multiple input deep learning model was proposed to directly use sleep signals combined with clinical features. Data from 5,506 patients from the Pays de la Loire Sleep Cohort, without a history of major adverse cardiovascular events (MACE), investigated for OSA, were used. After a median follow-up of 6.0 years, 613 patients had been diagnosed with MACE according to the French national health system. Following an architecture selection, deep survival convolutional neural networks were computed to assess the MACE risk score. A custom loss function was integrated to consider the follow-up time of each patient. Based on the weights of each model input, a method for interpreting the model was also proposed to show the contribution of signals compared to clinical features. Sleep signals were extracted from a home sleep apnea test. The best results were obtained with the autonomic manifestation signal. An area under the ROC curve of 0.823 was reached. After interpretation of the models, consideration of sleep appeared to be more important in women and in those under 60. This method may help improve OSA patient care by estimating their risk of MACE during sleep diagnosis.
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 133468-133478
Open AccessA Deep Survival Learning Approach for Cardiovascular Risk Estimation in Patients With Sleep Apnea
Cardiovascular (CV) disorders and obstructive sleep apnea (OSA) are very prevalent diseases worldwide. Multiple studies have demonstrated that OSA is associated with increased CV risk. Clinicians need to assess the CV risk to select the proper OSA treatment. A growing number of research have employed machine learning to predict CV risk by integrating clinical and sleep features. In this paper, a multiple input deep learning model was proposed to directly use sleep signals combined with clinical features. Data from 5,506 patients from the Pays de la Loire Sleep Cohort, without a history of major adverse cardiovascular events (MACE), investigated for OSA, were used. After a median follow-up of 6.0 years, 613 patients had been diagnosed with MACE according to the French national health system. Following an architecture selection, deep survival convolutional neural networks were computed to assess the MACE risk score. A custom loss function was integrated to consider the follow-up time of each patient. Based on the weights of each model input, a method for interpreting the model was also proposed to show the contribution of signals compared to clinical features. Sleep signals were extracted from a home sleep apnea test. The best results were obtained with the autonomic manifestation signal. An area under the ROC curve of 0.823 was reached. After interpretation of the models, consideration of sleep appeared to be more important in women and in those under 60. This method may help improve OSA patient care by estimating their risk of MACE during sleep diagnosis.
- Open Access
Palindromic Vectors, Symmetropy and Symmentropy as Symmetry Descriptors of Binary Data
Today, the palindromic analysis of biological sequences, based exclusively on the study of “mirror” symmetry properties, is almost unavoidable. However, other types of symmetry, such as those present in friezes, could allow us to analyze binary sequences from another point of view. New tools, such as symmetropy and symmentropy, based on new types of palindromes allow us to discriminate binarized noise sequences better than Lempel–Ziv complexity. These new palindromes with new types of symmetry also allow for better discrimination of binarized DNA sequences. A relative error of of symmetropy is obtained from the HUMHBB and YEAST1 DNA sequences. A factor of 4 between the slopes obtained from the linear fits of the local symmentropies for the two DNA sequences shows the discriminative capacity of the local symmentropy. Moreover, it is highlighted that a certain number of these new palindromes of sizes greater than 30 bits are more discriminating than those of smaller sizes assimilated to those from an independent and identically distributed random variable.Open AccessPalindromic Vectors, Symmetropy and Symmentropy as Symmetry Descriptors of Binary Data
Today, the palindromic analysis of biological sequences, based exclusively on the study of “mirror” symmetry properties, is almost unavoidable. However, other types of symmetry, such as those present in friezes, could allow us to analyze binary sequences from another point of view. New tools, such as symmetropy and symmentropy, based on new types of palindromes allow us to discriminate binarized noise sequences better than Lempel–Ziv complexity. These new palindromes with new types of symmetry also allow for better discrimination of binarized DNA sequences. A relative error of of symmetropy is obtained from the HUMHBB and YEAST1 DNA sequences. A factor of 4 between the slopes obtained from the linear fits of the local symmentropies for the two DNA sequences shows the discriminative capacity of the local symmentropy. Moreover, it is highlighted that a certain number of these new palindromes of sizes greater than 30 bits are more discriminating than those of smaller sizes assimilated to those from an independent and identically distributed random variable. - 19 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 69 (3) , 1225-1236
A New Sleep Staging System for Type III Sleep Studies Equipped With a Tracheal Sound Sensor
Type III sleep studies record cardio-respiratory channels only. Compared with polysomnography, which also records electrophysiological channels, they present many advantages: they are less expensive, less time-consuming, and more likely to be performed at home. However, their accuracy is limited by missing sleep information. That is why many studies present specific cardio-respiratory parameters to assess the causal effects of sleep stages upon cardiac or respiratory activities. For this paper, we gathered many parameters proposed in literature, leading to 1,111 features. The pulse oximeter, the PneaVoX sensor (recording tracheal sounds), respiratory inductance plethysmography belts, the nasal cannula and the actimeter provided the 112 worthiest ones for automatic sleep scoring. Then, a 3-step model was implemented: classification with a multi-layer perceptron, sleep transition rules corrections (from the AASM guidelines), and sequence corrections using a Viterbi hidden Markov model. The whole process was trained and tested using 300 and 100 independent recordings provided from patients suspected of having sleep breathing disorders. Results indicated that the system achieves substantial agreement with manual scoring for classifications into 2 stages (wake vs. sleep: mean Cohen's Kappa of 0.63 and accuracy rate Acc of 87.8%) and 3 stages (wake vs. R stage vs. NREM stage: mean of 0.60 and Acc of 78.5%). It indicates that the method could provide information to help specialists while diagnosing sleep. The presented model had promising results and may enhance clinical diagnosis.
- 19 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 69 (3) , 1225-1236
A New Sleep Staging System for Type III Sleep Studies Equipped With a Tracheal Sound Sensor
Type III sleep studies record cardio-respiratory channels only. Compared with polysomnography, which also records electrophysiological channels, they present many advantages: they are less expensive, less time-consuming, and more likely to be performed at home. However, their accuracy is limited by missing sleep information. That is why many studies present specific cardio-respiratory parameters to assess the causal effects of sleep stages upon cardiac or respiratory activities. For this paper, we gathered many parameters proposed in literature, leading to 1,111 features. The pulse oximeter, the PneaVoX sensor (recording tracheal sounds), respiratory inductance plethysmography belts, the nasal cannula and the actimeter provided the 112 worthiest ones for automatic sleep scoring. Then, a 3-step model was implemented: classification with a multi-layer perceptron, sleep transition rules corrections (from the AASM guidelines), and sequence corrections using a Viterbi hidden Markov model. The whole process was trained and tested using 300 and 100 independent recordings provided from patients suspected of having sleep breathing disorders. Results indicated that the system achieves substantial agreement with manual scoring for classifications into 2 stages (wake vs. sleep: mean Cohen's Kappa of 0.63 and accuracy rate Acc of 87.8%) and 3 stages (wake vs. R stage vs. NREM stage: mean of 0.60 and Acc of 78.5%). It indicates that the method could provide information to help specialists while diagnosing sleep. The presented model had promising results and may enhance clinical diagnosis.
- 1 June 2021
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 92, 107450
Prediction of protein structural class based on symmetrical recurrence quantification analysis
- 1 June 2021
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 92, 107450
Prediction of protein structural class based on symmetrical recurrence quantification analysis
- 12 June 2019
- Published by Elsevier in Applied Acoustics
- Vol. 155, 222-231
Optimal pump excitation frequency for improvement of damage detection by nonlinear vibro acoustic modulation method in a multiple scattering sample
- 12 June 2019
- Published by Elsevier in Applied Acoustics
- Vol. 155, 222-231
Optimal pump excitation frequency for improvement of damage detection by nonlinear vibro acoustic modulation method in a multiple scattering sample
- Open Access
Centered and Averaged Fuzzy Entropy to Improve Fuzzy Entropy Precision
Several entropy measures are now widely used to analyze real-world time series. Among them, we can cite approximate entropy, sample entropy and fuzzy entropy (FuzzyEn), the latter one being probably the most efficient among the three. However, FuzzyEn precision depends on the number of samples in the data under study. The longer the signal, the better it is. Nevertheless, long signals are often difficult to obtain in real applications. This is why we herein propose a new FuzzyEn that presents better precision than the standard FuzzyEn. This is performed by increasing the number of samples used in the computation of the entropy measure, without changing the length of the time series. Thus, for the comparisons of the patterns, the mean value is no longer a constraint. Moreover, translated patterns are not the only ones considered: reflected, inversed, and glide-reflected patterns are also taken into account. The new measure (so-called centered and averaged FuzzyEn) is applied to synthetic and biomedical signals. The results show that the centered and averaged FuzzyEn leads to more precise results than the standard FuzzyEn: the relative percentile range is reduced compared to the standard sample entropy and fuzzy entropy measures. The centered and averaged FuzzyEn could now be used in other applications to compare its performances to those of other already-existing entropy measures.
Open AccessCentered and Averaged Fuzzy Entropy to Improve Fuzzy Entropy Precision
Several entropy measures are now widely used to analyze real-world time series. Among them, we can cite approximate entropy, sample entropy and fuzzy entropy (FuzzyEn), the latter one being probably the most efficient among the three. However, FuzzyEn precision depends on the number of samples in the data under study. The longer the signal, the better it is. Nevertheless, long signals are often difficult to obtain in real applications. This is why we herein propose a new FuzzyEn that presents better precision than the standard FuzzyEn. This is performed by increasing the number of samples used in the computation of the entropy measure, without changing the length of the time series. Thus, for the comparisons of the patterns, the mean value is no longer a constraint. Moreover, translated patterns are not the only ones considered: reflected, inversed, and glide-reflected patterns are also taken into account. The new measure (so-called centered and averaged FuzzyEn) is applied to synthetic and biomedical signals. The results show that the centered and averaged FuzzyEn leads to more precise results than the standard FuzzyEn: the relative percentile range is reduced compared to the standard sample entropy and fuzzy entropy measures. The centered and averaged FuzzyEn could now be used in other applications to compare its performances to those of other already-existing entropy measures.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1166-1169
Restoration of ultrasonic images using non-linear system identification and deconvolution
This paper studies a new ultrasound image restoration method based on a non-linear forward model. A Hammerstein polynomial-based non-linear image formation model is considered to identify the system impulse response in baseband and around the second harmonic. The identification process is followed by a joint deconvolution technique minimizing an appropriate cost function. This cost function is constructed from two data fidelity terms exploiting the linear and non-linear model components, penalized by an additive-norm regularization enforcing sparsity of the solution. An alternating optimization approach is considered to minimize the penalized cost function, allowing the tissue reflectivity function to be estimated. Results on synthetic ultrasound images are finally presented to evaluate the algorithm performance.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1166-1169
Restoration of ultrasonic images using non-linear system identification and deconvolution
This paper studies a new ultrasound image restoration method based on a non-linear forward model. A Hammerstein polynomial-based non-linear image formation model is considered to identify the system impulse response in baseband and around the second harmonic. The identification process is followed by a joint deconvolution technique minimizing an appropriate cost function. This cost function is constructed from two data fidelity terms exploiting the linear and non-linear model components, penalized by an additive-norm regularization enforcing sparsity of the solution. An alternating optimization approach is considered to minimize the penalized cost function, allowing the tissue reflectivity function to be estimated. Results on synthetic ultrasound images are finally presented to evaluate the algorithm performance.
- Open Access
- 14 December 2016
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2016, 1-8
Detection of Doppler Microembolic Signals Using High Order Statistics
Robust detection of the smallest circulating cerebral microemboli is an efficient way of preventing strokes, which is second cause of mortality worldwide. Transcranial Doppler ultrasound is widely considered the most convenient system for the detection of microemboli. The most common standard detection is achieved through the Doppler energy signal and depends on an empirically set constant threshold. On the other hand, in the past few years, higher order statistics have been an extensive field of research as they represent descriptive statistics that can be used to detect signal outliers. In this study, we propose new types of microembolic detectors based on the windowed calculation of the third moment skewness and fourth moment kurtosis of the energy signal. During energy embolus-free periods the distribution of the energy is not altered and the skewness and kurtosis signals do not exhibit any peak values. In the presence of emboli, the energy distribution is distorted and the skewness and kurtosis signals exhibit peaks, corresponding to the latter emboli. Applied on real signals, the detection of microemboli through the skewness and kurtosis signals outperformed the detection through standard methods. The sensitivities and specificities reached 78% and 91% and 80% and 90% for the skewness and kurtosis detectors, respectively.
- 14 December 2016
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2016, 1-8
Open AccessDetection of Doppler Microembolic Signals Using High Order Statistics
Robust detection of the smallest circulating cerebral microemboli is an efficient way of preventing strokes, which is second cause of mortality worldwide. Transcranial Doppler ultrasound is widely considered the most convenient system for the detection of microemboli. The most common standard detection is achieved through the Doppler energy signal and depends on an empirically set constant threshold. On the other hand, in the past few years, higher order statistics have been an extensive field of research as they represent descriptive statistics that can be used to detect signal outliers. In this study, we propose new types of microembolic detectors based on the windowed calculation of the third moment skewness and fourth moment kurtosis of the energy signal. During energy embolus-free periods the distribution of the energy is not altered and the skewness and kurtosis signals do not exhibit any peak values. In the presence of emboli, the energy distribution is distorted and the skewness and kurtosis signals exhibit peaks, corresponding to the latter emboli. Applied on real signals, the detection of microemboli through the skewness and kurtosis signals outperformed the detection through standard methods. The sensitivities and specificities reached 78% and 91% and 80% and 90% for the skewness and kurtosis detectors, respectively.