Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Computers in Biology and Medicine
EEG-based classification for elbow versus shoulder torque intentions involving stroke subjects
Computers in Biology and Medicine
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Hi-index | 0.01 |
Neuronal power attenuation or enhancement in specific frequency bands over the sensorimotor cortex, called Event-Related Desynchronization (ERD) or Event-Related Synchronization (ERS), respectively, is a major phenomenon in brain activities involved in imaginary movement of body parts. However, it is known that the nature of motor imagery-related electroencephalogram (EEG) signals is non-stationary and highly variable over time and frequency. In this paper, we propose a novel method of finding a discriminative time- and frequency-dependent spatial filter, which we call 'non-homogeneous filter.' We adaptively select bases of spatial filters over time and frequency. By taking both temporal and spectral features of EEGs in finding a spatial filter into account it is beneficial to be able to consider non-stationarity of EEG signals. In order to consider changes of ERD/ERS patterns over the time-frequency domain, we devise a spectrally and temporally weighted classification method via statistical analysis. Our experimental results on the BCI Competition IV dataset II-a and BCI Competition II dataset IV clearly presented the effectiveness of the proposed method outperforming other competing methods in the literature.