Name
Abstract | ||
|---|---|---|
The processes giving rise to an event related potential engage several evoked and induced oscillatory components, which reflect phase or non-phase locked activity throughout the multiple trials. The separation and identification of such components could not only serve diagnostic purposes, but also facilitate the design of brain-computer interface systems. However, the effective analysis of components is hindered by many factors including the complexity of the EEG signal and its variation over the trials. In this paper we study several measures for the identification of the nature of independent components and address the means for efficient decomposition of the rich information content embedded in the multi-channel EEG recordings associated with the multiple trials of an event-related experiment. The efficiency of the proposed methodology is demonstrated through simulated and real experiments. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1007/978-3-642-04277-5_37 | ICANN (2) |
Keywords | Field | DocType |
effective analysis,induced oscillatory component,erp recordings,brain-computer interface system,independent component,detailed analysis,diagnostic purpose,event-related experiment,multi-channel eeg recording,efficient decomposition,decomposition methods,multiple trial,eeg signal,eeg,time frequency,information content,brain computer interface,decomposition method,event related potential,pca | Pattern recognition,Computer science,Event-related potential,Speech recognition,Artificial intelligence,Electroencephalography | Conference |
Volume | ISSN | Citations |
5769 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 4 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Vasiliki Iordanidou | 1 | 1 | 0.35 |
| K. Michalopoulos | 2 | 14 | 3.68 |
| Vangelis Sakkalis | 3 | 110 | 23.68 |
| Michalis Zervakis | 4 | 199 | 21.30 |