Ashvaani Engambaram soutiendra sa thèse intitulée ONLINE DETECTION AND REMOVAL OF EYE BLINK ARTIFACTS FROM ELECTROENCEPHALOGRA le 10 juin à 9h en visioconférence depuis la Malaisie.
Jury de thèse :
CHRISTOPHE DUCOTTET, Professeur, Université de Saint-Etienne, Examinateur
VRABIE VALERIU, Professeur, Université de Reims, Rapporteur
DESIRE SIDIBE, Professeur, Université d’Evry Val d’Essonne, Rapporteur
OLIVIER LALIGANT, Professeur, Université de Bourgogne, Examinateur
CHRISTOPHE STOLZ, Maitre de Conférences HDR, Université Bourgogne, Directeur de thèse
ERIC FAUVET, Maitre de conférences, Université de Bourgogne, Co-encadrant
NASREEN BADRUDDIN Associate Professor, Universiti Teknologi PETRONAS, Co-Directeur de thèse
IBRAHIMA FAYE, Associate Professor, Universiti Teknologi PETRONAS, Invité
Résumé :
The most prominent type of artifact contaminating electroencephalogram (EEG) signals is the eyeblink (EB) artifacts, which could potentially lead to misinterpretation of EEG signal. Online detection and removal of eyeblink artifacts from EEG signals are essential in applications such a Brain-Computer Interfaces (BCI), neurofeedback and epilepsy monitoring. In this thesis, algorithms that combine unsupervised eyeblink artifact detection (eADA) with enhanced Empirical Mode Decomposition (FastEMD) and Canonical Correlation Analysis (CCA) are proposed, i.e. FastEMD-CCA2 and FastCCA, to automatically identify eyeblink artifacts and remove them in an online setting. FastEMD-CCA2 and FastCCA have outperformed one of the existing state-of-the-art methods, FORCe. The average artifact removal accuracy, sensitivity, specificity and error rate of FastEMD-CCA2 is 97.9%, 97.65%, 99.22%, and 2.1% respectively, validated on a Hitachi dataset. FastCCA achieved an average of 99.47%, 99.44%, 99.74% and 0.53% artifact removal accuracy, sensitivity, specificity and error rate respectively, validated on Hitachi dataset too. FastEMD-CCA2 and FastCCA algorithms are developed and implemented in the C++ programming language to investigate the processing speed these algorithms could achieve in a different medium. Analysis has shown that FastEMD-CCA2 and FastCCA took about 10.7 and 12.7 milliseconds respectively, on average to clean a 1-second length of EEG segment. This makes them a feasible solution for applications requiring online removal of eyeblink artifacts from EEG signals.