Name
Title | ||
|---|---|---|
Adaptive Spatial Filters with predefined Region of Interest for EEG based Brain-Computer-Interfaces |
Abstract | ||
|---|---|---|
The performance of EEG-based Brain-Computer-Interfaces (BCIs) critically de- pends on the extraction of features from the EEG carrying information relevant for the classification of different mental states. For BCIs e mploying imaginary movements of different limbs, the method of Common Spatial Patterns (CSP) has been shown to achieve excellent classification results. The CSP-algorithm how- ever suffers from a lack of robustness, requiring training d ata without artifacts for good performance. To overcome this lack of robustness, we propose an adaptive spatial filter that replaces the training data in the CSP appr oach by a-priori infor- mation. More specifically, we design an adaptive spatial filt er that maximizes the ratio of the variance of the electric field originating in a pr edefined region of inter- est (ROI) and the overall variance of the measured EEG. Since it is known that the component of the EEG used for discriminating imaginary movements originates in the motor cortex, we design two adaptive spatial filters wi th the ROIs centered in the hand areas of the left and right motor cortex. We then use these to classify EEG data recorded during imaginary movements of the right and left hand of three subjects, and show that the adaptive spatial filters outperf orm the CSP-algorithm, enabling classification rates of up to 94.7 % without artifac t rejection. |
Year | Venue | Keywords |
|---|---|---|
2006 | NIPS | common spatial pattern,spatial filtering,electric field,brain computer interface,region of interest |
Field | DocType | Citations |
Training set,Computer vision,Computer science,Brain–computer interface,Robustness (computer science),Artificial intelligence,Motor cortex,Region of interest,Spatial ecology,Electroencephalography,Machine learning,Spatial filter | Conference | 14 |
PageRank | References | Authors |
1.34 | 4 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Moritz Grosse-Wentrup | 1 | 273 | 24.44 |
| Klaus Gramann | 2 | 168 | 19.01 |
| Martin Buss | 3 | 1799 | 159.02 |
| scholkopf | 4 | 216 | 13.73 |
| joseph b platt | 5 | 14 | 1.34 |
| t hofmann | 6 | 14 | 1.34 |