Publication:
Exactly periodic spatial filter for SSVEP based BCIs

Placeholder Image
Date
26-12-2018
Journal Title
Journal ISSN
Volume Title
Publisher
Research Projects
Organizational Units
Journal Issue
Abstract
This study introduces a novel, high accuracy, calibration less spatial filter for reliable steady-state visual evoked potential (SSVEP) extraction from noisy electroencephalogram (EEG) data. The proposed method, exactly periodic subspace decomposition (EPSD), utilises the periodic properties of the SSVEP components to achieve a robust spatial filter for SSVEP extraction. It tries to extract the SSVEP components by projecting the EEG data onto a subspace where only the target signal components are retained. The performance of the method was tested on an SSVEP dataset obtained from ten subjects and compared with common SSVEP spatial filtering and detection techniques. The results obtained from the study shows that EPSD consistently provides a significant improvement in detection performance than other SSVEP spatial filters used in brain-computer interface (BCI) applications.
Description
Keywords
Brain-computer interface (BCI), Electroencephalogram (EEG), Exactly periodic subspace decomposition (EPSD), Spatial filter, Steady-state visual evoked potential (SSVEP)
Citation
Collections