| |
| 8.
Direct Brain–Computer Communication |
| |
8.3.
Components of graz BCI
| |
8.3.1.
Parameter Estimation and Classification |
| |
|
8.3.1.1.
Band Power Estimates |
|
The EEG is composed of different types
of oscillatory activities whereby oscillations in the alpha
and beta band are particularly important to discriminate between
different brain states during visual and motor imagery.
Possibilities to select parameters from the ongoing
EEG:
| |
1)
First calculate short-term power spectra in intervals of,
e.g., 250 ms and thereafter estimate the band power. |
| |
| |
2)
First bandpass-filter the EEG and then to estimate the band
power in intervals of, e.g., 250 ms thereafter. |
Both methods assume stationarity of the EEG over short time
intervals. The selection of most reactive frequency can be done
by the DSLVQ algorithm.
Source:
Motor Imagery and Direct Brain–Computer Communication, Gert Pfurtscheller and Christa Neuper 
