Online Classification of Multiple Motor Imagery Tasks Using Filter Bank Based Maximum-a-Posteriori Common Spatial Pattern Filters - 26/05/20
pages | 10 |
Iconographies | 7 |
Vidéos | 0 |
Autres | 0 |
Graphical abstract |
Highlights |
• | Run-time (real-time) classification of multiple motor imagery (MI) tasks. |
• | Filter bank based maximum-a-posteriori common spatial pattern (CSP) filtering. |
• | Classification of tasks by detecting event-related de-synchronization in rhythm. |
• | Superior classification and computational efficiency compared to conventional CSP. |
Abstract |
Objective |
The main objective of this paper is to propose a novel technique, called filter bank maximum a-posteriori common spatial pattern (FB-MAP-CSP) algorithm, for online classification of multiple motor imagery activities using electroencephalography (EEG) signals. The proposed technique addresses the overfitting issue of CSP in addition to utilizing the spectral information of EEG signals inside the framework of filter banks while extending it to more than two conditions.
Materials and methods |
The classification of motor imagery signals is based upon the detection of event-related de-synchronization (ERD) phenomena in the μ and β rhythms of EEG signals. Accordingly, two modifications in the existing MAP-CSP technique are presented: (i) The (pre-processed) EEG signals are spectrally filtered by a bank of filters lying in the μ and β brainwave frequency range, (ii) the framework of MAP-CSP is extended to deal with multiple (more than two) motor imagery tasks classification and the spatial filters thus obtained are calculated for each sub-band, separately. Subsequently, the most imperative features over all sub-bands are selected and un-regularized linear discriminant analysis is employed for classification of multiple motor imagery tasks.
Results |
Publicly available dataset (BCI Competition IV Dataset I) is used to validate the proposed method i.e. FB-MAP-CSP. The results show that the proposed method yields superior classification results, in addition to be computationally more efficient in the case of online implementation, as compared to the conventional CSP based techniques and its variants for multiclass motor imagery classification.
Conclusion |
The proposed FB-MAP-CSP algorithm is found to be a potential / superior method for classifying multi-condition motor imagery EEG signals in comparison to FBCSP based techniques.
Le texte complet de cet article est disponible en PDF.Keywords : Electroencephalogram (EEG), Brain Computer Interface (BCI), Event-related de-synchronization, Filter bank, common spatial patterns, Motor imagery
Plan
Vol 41 - N° 3
P. 141-150 - juin 2020 Retour au numéroBienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’achat d’article à l’unité est indisponible à l’heure actuelle.
Déjà abonné à cette revue ?