Visuo-Spatial Attention Frame Recognition for Brain-Computer Interfaces
Objective: To assess the feasibility of recognizing visual spatial attention frames for brain-computer interfaces (BCI) applications. Methods: EEG data was recorded with 64 electrodes from two subjects executing a visuo-spatial attention task indicating two target locations. Continuous Morlet wavelet coefficients were estimated on 18 frequency components and 16 preselected electrodes in trials of 600ms. The spatial patterns of the 16 frequency components frames were simultaneously detected and classified (between the two targets). The classification accuracy was assessed using 20-fold cross-validation. Results: The maximum frames average classification accuracies are 80.64% and 87.31% for subject 1 and 2 respectively, both utilizing frequency components located in gamma band.
Unable to display preview. Download preview PDF.
- 6.Galán, F., Ferrez, P. W., Oliva, F., Guárdia, J., Millán, J. del R.: Feature extraction for multi-class BCI using canonical variates analysis. In: Proceedings of the 2007 IEEE Int. Symp. Intell. Signal Process (WISP 2007). Alcaláde Henares, Spain, (2007).Google Scholar
- 7.Palix, J., Hauert, C. A., Leonards, U.: Brain oscillations: Indicators for serial processing in inefficient visual search? Perception 35 (2006) 234.Google Scholar