L
Lotfi Senhadji
Researcher at University of Rennes
Publications - 194
Citations - 3443
Lotfi Senhadji is an academic researcher from University of Rennes. The author has contributed to research in topics: Wavelet & Independent component analysis. The author has an hindex of 28, co-authored 193 publications receiving 3119 citations. Previous affiliations of Lotfi Senhadji include Southeast University & University of Rennes 1.
Papers
More filters
Journal ArticleDOI
Comparing wavelet transforms for recognizing cardiac patterns
TL;DR: In this paper, the authors used wavelet transforms to describe and recognize isolated cardiac beats and evaluated their capability of discriminating between normal, premature ventricular contraction, and ischemic beats by means of linear discriminant analysis.
Journal ArticleDOI
Ica: a potential tool for bci systems
TL;DR: A comparative study of widely used ICA algorithms in the BCI community, conducted on simulated electroencephalography (EEG) data, shows that an appropriate selection of an ICA algorithm may significantly improve the capabilities of BCI systems.
Journal ArticleDOI
From EEG signals to brain connectivity: A model-based evaluation of interdependence measures
Fabrice Wendling,Karim Ansari-Asl,Fabrice Bartolomei,Fabrice Bartolomei,Lotfi Senhadji,Lotfi Senhadji +5 more
TL;DR: Three families of methods (linear and nonlinear regression, phase synchronization, and generalized synchronization) are reviewed and it is recommended to first apply these "robust" methods in order to characterize brain connectivity before using more sophisticated methods that require specific assumptions about the underlying model of relationship.
Journal ArticleDOI
Removal of muscle artifact from EEG data: comparison between stochastic (ICA and CCA) and deterministic (EMD and wavelet-based) approaches
Doha Safieddine,Doha Safieddine,Amar Kachenoura,Amar Kachenoura,Laurent Albera,Laurent Albera,Gwénaël Birot,Gwénaël Birot,Ahmad Karfoul,Anca Pasnicu,Arnaud Biraben,Arnaud Biraben,Fabrice Wendling,Fabrice Wendling,Lotfi Senhadji,Lotfi Senhadji,Isabelle Merlet,Isabelle Merlet +17 more
TL;DR: EMD outperformed the three other algorithms for the denoising of data highly contaminated by muscular activity and suggests that the performance of muscle artifact correction methods strongly depend on the level of data contamination, and of the source configuration underlying EEG signals.
Journal ArticleDOI
Quantitative evaluation of linear and nonlinear methods characterizing interdependencies between brain signals.
TL;DR: A comprehensive comparison of different classes of methods (linear and nonlinear regressions, phase synchronization, and generalized synchronization) based on various simulation models is proposed and shows that the performances of the compared methods are highly dependent on the hypothesis regarding the underlying model for the generation of the signals.