A5070686427- EEG and Brain-Computer Interfaces
- Neurological disorders and treatments
- Blind Source Separation Techniques
- ECG Monitoring and Analysis
- Neuroscience and Neural Engineering
- Fault Detection and Control Systems
- Sleep and Wakefulness Research
- Transcranial Magnetic Stimulation Studies
- Time Series Analysis and Forecasting
- Vestibular and auditory disorders
- Advanced Chemical Sensor Technologies
- Neural Networks and Applications
- Machine Fault Diagnosis Techniques
- Gaze Tracking and Assistive Technology
- Context-Aware Activity Recognition Systems
- Obstructive Sleep Apnea Research
- Neural dynamics and brain function
- Anomaly Detection Techniques and Applications
- Functional Brain Connectivity Studies
- Industrial Vision Systems and Defect Detection
- Advanced Memory and Neural Computing
- Data Quality and Management
- Mitochondrial Function and Pathology
- Spectroscopy and Chemometric Analyses
- Assistive Technology in Communication and Mobility
University of Anbar
2024
UniLaSalle Amiens (ESIEE-Amiens)
2005-2019
Université Gustave Eiffel
2004-2019
ESIEE Paris
2004-2019
ESIEA University
2008-2016
Université de Versailles Saint-Quentin-en-Yvelines
2007-2016
Université Paris-Est Créteil
2015-2016
Laboratoire Spécification et Vérification
2010-2015
Laboratoire d'Ingénierie des Systèmes de Versailles
2010-2015
Institut Lavoisier de Versailles
2010
Background In the last few years, transcranial direct current stimulation (tDCS) has emerged as an appealing therapeutic option to improve brain functions. Promising data support role of prefrontal tDCS in augmenting cognitive performance and ameliorating several neuropsychiatric symptoms, namely pain, fatigue, mood disturbances, attentional impairment. Such symptoms are commonly encountered patients with multiple sclerosis (MS). Objective The main objective work was evaluate effects over...
Purpose: Pain and cognitive impairment are frequent symptoms in patients with multiple sclerosis (MS). Neglecting experimental pain paying attention to demanding tasks is reported decrease the intensity. Little known about interaction between chronic neuropathic attentio n disorders MS. Recently, transcranial direct current stimulation (tDCS) was used modulate various motor We aimed study effects of random noise (tRNS), a form electric stimulation, over left dorsolateral prefrontal cortex...
The main drive force in apnea current diagnostic is to reduce overwhelming number of sleep disorders candidates by means very simple-to-use, comfortable and cheap methodology. proposed framework based only on automatic analysis electrocardiogram signal. feature extraction stage was performed using methods Heart Rate Variability Detrended Fluctuation analysis. Feature-spaces formed these two were used as input a Long Short-Term Memory Artificial Neural Network chosen for its capability find...
Electrooculographic (EOG) artefacts are one of the most common causes Electroencephalogram (EEG) distortion. In this paper, we propose a method for EOG Blinking Artefacts (BAs) detection and removal from EEG. Normalized Correlation Coefficient (NCC), based on predetermined BA template library was used detecting BA. Ensemble Empirical Mode Decomposition (EEMD) applied to contaminated region statistical algorithm determined which Intrinsic Functions (IMFs) correspond The proposed in simulated...
In this work, a pilot study of on-line automatic detection human activity in home using wavelet and hidden Markov models Scilab toolkits was carried out. The collected raw data are provided by biaxial accelerometer ADXL202E attached to the person. Several activities were simulated researchers (walking slowly , walking quickly, sitting down-getting up, fall during walking, from position upright, ...). feature vectors these then used build different with persons. built employed for online...
Obstructive sleep apnoea syndrome (OSA) is a very common disorder in breathing during sleep. OSA considered as clinically relevant when the breath stops more than 10 seconds and occurs five times per hour. In this work, we investigate noninvasive automatic approach to classify events based on power spectral analysis for feature extraction of ECG records hidden Markov models (HMMs). Based Bayesian inference criterion (BIC), proposed HMM training algorithm able select optimal number states...
The alternating among sleep-wake stages gives information related to the sleep quality and quantity since this pattern is highly affected during disorders. analysis of in humans usually made on periods (epochs) 30-s length according original Rechtschaffen Kales scoring manual. In paper, we propose a new phase space-based algorithm (mainly based Poincaré plot) for automatic classification states using EEG data gathered over relatively short-time periods. effectiveness our approach...
The aim of this paper is to investigate a nonlinear approach for feature extraction Electroencephalogram (EEG) signals in order classify motor imagery Brain Computer Interface (BCI). This consists combining the Empirical Mode Decomposition (EMD) and band power (BP). Considering non-stationary characteristics EEG, EMD method proposed decompose EEG signal into set stationary time series called Intrinsic Functions (IMF). These IMFs are analyzed with bandpower (BP) detect caracteristics...
This paper reports on preliminary work the use of hidden Markov models (HMMs) approach for tasks classification in P300-based brain-computer interface (BCI) system. Every HMM is trained a set electroencephalogram (EEG) records issued from different sessions corresponding to same task. The HMMs that has been built take into account variability EEGs during sessions. Based Bayesian inference criterion (BIC), proposed training algorithm able select optimal number states each EEG records. For...
In this work we investigate a nonlinear approach for feature extraction of Electroencephalogram (EEG) signals in order to classify motor imagery Brain Computer Interface (BCI). This is based on the Empirical Mode Decomposition (EMD) and band power (BP). The EMD method data-driven technique analyze non-stationary signals. It generates set stationary time series called Intrinsic Functions (IMF) represent original data. These IMFs are analyzed with spectral density (PSD) study active frequency...
We describe a clustering algorithm based on continuous hidden Markov models (HMM) to automatically classify both electrocardiogram (ECG) and intracranial pressure (ICP) beats their morphology. The detects, classifies labels each beat In order avoid the numerical problems with classical expectation-maximization (EM) we apply novel method of simulated annealing (SIM) for HMM optimization. show that better results are achieved using approach.
An algorithm for the training of Hidden Markov Models (HMMs) by simulated annealing is presented. This based on a finite coding solution space optimal trajectory state. It applied to both discrete and continuous Gaussian observations. The needs no specific initialisation initial HMM user, cooling schedule being general applicable any model. parameters (initial final temperatures) are derived automatically from theoretical considerations. objective function evaluations made independent...