S. Boudaoud

Université de Technologie de Compiègne, Génie Biologique Et Médical, Faculty Member

Followers

Following

Co-author

Public Views

Related Authors

Fouaz Ayachi

McGill University

Mariam Harrach

Roberto Merletti

Politecnico di Torino

Fábio Lanferdini

Miriam Vollenbroek-hutten

University of Twente

Universitat Autònoma de Barcelona

Mikael Forsman

Interests

Uploads

Papers by S. Boudaoud

Evaluation of muscle force classification using shape analysis of the sEMG probability density function: a simulation study

Medical & biological engineering & computing, 2014

In this work, we propose to classify, by simulation, the shape variability (or non-Gaussianity) o... more In this work, we propose to classify, by simulation, the shape variability (or non-Gaussianity) of the surface electromyogram (sEMG) amplitude probability density function (PDF), according to contraction level, using high-order statistics (HOS) and a recent functional formalism, the core shape modeling (CSM). According to recent studies, based on simulated and/or experimental conditions, the sEMG PDF shape seems to be modified by many factors as: contraction level, fatigue state, muscle anatomy, used instrumentation, and also motor control parameters. For sensitivity evaluation against these several sources (physiological, instrumental, and neural control) of variability, a large-scale simulation (25 muscle anatomies, ten parameter configurations, three electrode arrangements) is performed, by using a recent sEMG-force model and parallel computing, to classify sEMG data from three contraction levels (20, 50, and 80% MVC). A shape clustering algorithm is then launched using five comb...

DownloadEdit

CCA-EMD method applied to denoise monopolar sEMG recordings

The surface electromyogram (sEMG) is often corrupted by electronic and electromagnetic noise. The... more The surface electromyogram (sEMG) is often corrupted by electronic and electromagnetic noise. The interfering signals have often spectra overlapping with the sEMG signals rendering classical filtering ineffective. In the absence of efficient methods for denoising the monopolar sEMG signal, bipolar configuration is usually used. Although it is well known that a higher order electrode montage (bipolar...etc) can be used to denoise the monopolar sEMG signal but give a restricted overview of muscle activity. In this paper, we propose the use of a combination of Blind Source Separation method using Canonical Correlation Analysis (BSS_CCA) and Empirical Mode Decomposition (EMD) methods to denoise multi-channel monopolar sEMG recordings. We first extract the muscle activities by using BSS_CCA then residual noise is removed by EMD. By simulation, the proposed method successfully removed noise with muscle activity conservation even in presence of a low SNR (2 dB).

DownloadEdit

PHYSIOLOGICAL AND BIOMECHANICAL APPROACH FOR HUMAN FINGER MOVEMENT: MODELING, SIMULATION AND EXPERIMENTAL VALIDATION

The work presented in this paper deals with the description of an analytic modeling of the neurom... more The work presented in this paper deals with the description of an analytic modeling of the neuromusculoskeletal system responsible for the finger movement. This simulation task is complex due to the interacting processes (physiological and biomechanical) represented by muscles, joints and bones. In this study, we focused on the presentation of a complete model for the finger motion decomposed in quasi-static positions. In fact, this model can be considered as a preliminary step before dynamic modeling. The proposed model is composed of several compartments: biomechanical finger model, mechanical muscle model and muscle/neural activation model. The main objective of this study is to estimate, by inverse procedure, the muscle forces, muscle activations and neural activations that are responsible for generating a given finger movement decomposed in successive quasi-static positions. The anatomical model contains six muscles which control the decomposed movement of the three joints of the system. To estimate the model unknowns, an optimization technique is proposed for improving robustness to initial conditions and physiological reliability. After, an experimental protocol for recording surface electromyogram (sEMG) data, from three extrinsic muscles, according to specific finger positions is applied on five subjects to evaluate the model reliability.

DownloadEdit

Ensemble Spontaneous Activity Alterations Detected by CISA Approach

by S. Boudaoud and Hervé H Rix

2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007

In this paper, we propose a method for detecting alterations in the Ensemble Spontaneous Activity... more In this paper, we propose a method for detecting alterations in the Ensemble Spontaneous Activity (ESA), a random signal representing the composite spontaneous contribution of the auditory nerve recorded on the round window. The proposed method is based on shape analysis of the ESA amplitude histogram. For this task, we use a recent approach, the Corrected Integral Shape Averaging (CISA). Using this approach, a shape clustering algorithm is proposed to classify healthy and pathological ESA signals generated by a recent ESA model. This model allows a precise simulation of neural mechanisms occurring in the auditory nerve. The obtained results demonstrate that this shape analysis is very sensitive for detecting a small number of fibers with correlated firing, supposed to occur during a particular type of tinnitus. In comparison, the classical spectral index fails in this detection.

Edit

P-wave shape changes observed in the surface electrocardiogram of subjects with obstructive sleep apnoea

by Hervé H Rix and S. Boudaoud

Computers in Cardiology, 2005, 2005

Automated detection of sleep apnoea from the surface ECG is a challenge with potentially signific... more Automated detection of sleep apnoea from the surface ECG is a challenge with potentially significant clinical benefit. The objective of this study is to explore a possible relation between P-wave shape changes and the presence of Obstructive Sleep Apnoea (OSA) episodes in ECG records. Our working hypothesis is that apnoea-related phenomena (e.g., hypoxia, changes in intra-thoracic pressure) influence the depolarisation dynamics of the atria, and hence lead to detectable shape changes in the surface P-wave. For this purpose, a P-wave shape clustering algorithm is proposed. It uses the k-means method, an unsupervised classifier, coupled with a shape metric, the CISA (Corrected Integral Shape Averaging) distance, to distinguish apnoeic and non-apnoeic epochs. The method was applied to perform two-clustering on Pwave shapes extracted from ECG segments. The results obtained indicate that shape information from the ECG can be used in a classification approach for OSA detection. The study also raises the question of elucidating the mechanisms of how OSA may alter Pwave shape.

DownloadEdit

S. Boudaoud

Uploads

Papers by S. Boudaoud

Log In