Name
Abstract | ||
|---|---|---|
In this study, we explored the classification of singlehanded motor imagery (MI) EEG signals with different complexity. Eight healthy participants were asked to complete a finger-tapping task of different complexity. In signal processing, CSP features were extracted from the band-passed EEG signals. Then, these features were used to define a score using the step-wise linear discriminant analysis (SWLDA) method. The classification accuracy was evaluated by a five-fold cross-validation strategy. The experimental results showed that the average accuracy between different complexity is 79.20%, and the highest is up to 80.84%, indicating the separability of EEG-based MI tasks with different complexity. The EEG-based complexity distinction achieved in this paper would encourage further study of the realization of multiclass MI-based BCI paradigm. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1007/978-3-319-67777-4_55 | INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING, ISCIDE 2017 |
Keywords | Field | DocType |
Brain-computer interface (BCI), Electroencephalogram (EEG), Motor imagery, Task complexity, Common spatial pattern (CSP) | Signal processing,Pattern recognition,Computer science,Brain–computer interface,Artificial intelligence,Linear discriminant analysis,Electroencephalography,Motor imagery | Conference |
Volume | ISSN | Citations |
10559 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 11 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kunjia Liu | 1 | 3 | 0.75 |
| Yang Yu | 2 | 38 | 5.71 |
| Yadong Liu | 3 | 105 | 14.04 |
| Zongtan Zhou | 4 | 412 | 33.89 |