Abstract | ||
---|---|---|
Traditional analysis methods for single-trial classificat ion of electro- encephalography (EEG) focus on two types of paradigms: phase locked methods, in which the amplitude of the signal is used as the feature for classifica- tion, e.g. event related potentials; and second order metho ds, in which the feature of interest is the power of the signal, e.g. event related (de )synchronization. The procedure for deciding which paradigm to use is ad hoc and is typically driven by knowledge of the underlying neurophysiology. Here we propose a principled method, based on a bilinear model, in which the algorithm simultaneously learns the best first and second order spatial and temporal features for classification of EEG. The method is demonstrated on simulated data as well as on EEG taken from a benchmark data used to test classification algorithms for brain computer interfaces. |
Year | Venue | Keywords |
---|---|---|
2007 | NIPS | event related potential,second order,discriminant analysis,brain computer interface |
Field | DocType | Citations |
Synchronization,Neurophysiology,Pattern recognition,Computer science,Event-related potential,Brain–computer interface,Artificial intelligence,Linear discriminant analysis,Statistical classification,Electroencephalography,Machine learning,Bilinear interpolation | Conference | 5 |
PageRank | References | Authors |
0.63 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Christoforos Christoforou | 1 | 100 | 8.34 |
Paul Sajda | 2 | 651 | 89.86 |
Lucas C. Parra | 3 | 928 | 88.98 |