Limits...
The self-paced graz brain-computer interface: methods and applications.

Scherer R, Schloegl A, Lee F, Bischof H, Jansa J, Pfurtscheller G - Comput Intell Neurosci (2007)

Bottom Line: The presented system is able to automatically reduce electrooculogram (EOG) artifacts, to detect electromyographic (EMG) activity, and uses only three bipolar EEG channels.Two applications are presented: the freeSpace virtual environment (VE) and the Brainloop interface.The Brainloop interface provides an interface between the Graz-BCI and Google Earth.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Brain-Computer Interfaces, Institute for Knowledge Discovery, Graz University of Technology, Krenngasse 37, 8010 Graz, Austria. reinhold.scherer@tugraz.at

ABSTRACT
We present the self-paced 3-class Graz brain-computer interface (BCI) which is based on the detection of sensorimotor electroencephalogram (EEG) rhythms induced by motor imagery. Self-paced operation means that the BCI is able to determine whether the ongoing brain activity is intended as control signal (intentional control) or not (non-control state). The presented system is able to automatically reduce electrooculogram (EOG) artifacts, to detect electromyographic (EMG) activity, and uses only three bipolar EEG channels. Two applications are presented: the freeSpace virtual environment (VE) and the Brainloop interface. The freeSpace is a computer-game-like application where subjects have to navigate through the environment and collect coins by autonomously selecting navigation commands. Three subjects participated in these feedback experiments and each learned to navigate through the VE and collect coins. Two out of the three succeeded in collecting all three coins. The Brainloop interface provides an interface between the Graz-BCI and Google Earth.

No MeSH data available.


(a) Electrodepositions used for self-paced feedback experiments. Fz served as ground. Thecurves show the average classification accuracy (40 trials/class) of thespecified motor imagery tasks. (b) Timing of the cue-based training paradigm.The task was to move a smiley-shaped cursor into the direction indicated by thecue.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2266812&req=5

fig2: (a) Electrodepositions used for self-paced feedback experiments. Fz served as ground. Thecurves show the average classification accuracy (40 trials/class) of thespecified motor imagery tasks. (b) Timing of the cue-based training paradigm.The task was to move a smiley-shaped cursor into the direction indicated by thecue.

Mentions: Three healthy subjects (2 males, 1 female, righthanded) participated in self-paced experiments. Subject specific electrodepositions (according to the international 10–20 system), motor imagery tasksand the on-line classification accuracies of CFRMI after about 4 hours ofcue-based 3-class feedback training are summarized in Figure 2(a). Threebipolar EEG channels (named C3, Cz, and C4) and three monopolar EOG channels (Figure1(a)) were recorded from Ag/AgCl electrodes, analog filtered between 0.5 and100 Hz and sampled at a rate of 250 Hz. Figure 2(b) shows the timing of thecue-based paradigm. Classifier CFRMI was realized by combining 3pairwise trained Fisher's linear discriminant analysis (LDA) functions with amajority vote. A maximum of six band power (BP) features were extracted fromthe EEG by band pass filtering the signal (5th-order Butterworth), squaring andapplying a 1-second moving average filter. From the averaged value thelogarithm was computed (BPlog).


The self-paced graz brain-computer interface: methods and applications.

Scherer R, Schloegl A, Lee F, Bischof H, Jansa J, Pfurtscheller G - Comput Intell Neurosci (2007)

(a) Electrodepositions used for self-paced feedback experiments. Fz served as ground. Thecurves show the average classification accuracy (40 trials/class) of thespecified motor imagery tasks. (b) Timing of the cue-based training paradigm.The task was to move a smiley-shaped cursor into the direction indicated by thecue.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2266812&req=5

fig2: (a) Electrodepositions used for self-paced feedback experiments. Fz served as ground. Thecurves show the average classification accuracy (40 trials/class) of thespecified motor imagery tasks. (b) Timing of the cue-based training paradigm.The task was to move a smiley-shaped cursor into the direction indicated by thecue.
Mentions: Three healthy subjects (2 males, 1 female, righthanded) participated in self-paced experiments. Subject specific electrodepositions (according to the international 10–20 system), motor imagery tasksand the on-line classification accuracies of CFRMI after about 4 hours ofcue-based 3-class feedback training are summarized in Figure 2(a). Threebipolar EEG channels (named C3, Cz, and C4) and three monopolar EOG channels (Figure1(a)) were recorded from Ag/AgCl electrodes, analog filtered between 0.5 and100 Hz and sampled at a rate of 250 Hz. Figure 2(b) shows the timing of thecue-based paradigm. Classifier CFRMI was realized by combining 3pairwise trained Fisher's linear discriminant analysis (LDA) functions with amajority vote. A maximum of six band power (BP) features were extracted fromthe EEG by band pass filtering the signal (5th-order Butterworth), squaring andapplying a 1-second moving average filter. From the averaged value thelogarithm was computed (BPlog).

Bottom Line: The presented system is able to automatically reduce electrooculogram (EOG) artifacts, to detect electromyographic (EMG) activity, and uses only three bipolar EEG channels.Two applications are presented: the freeSpace virtual environment (VE) and the Brainloop interface.The Brainloop interface provides an interface between the Graz-BCI and Google Earth.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Brain-Computer Interfaces, Institute for Knowledge Discovery, Graz University of Technology, Krenngasse 37, 8010 Graz, Austria. reinhold.scherer@tugraz.at

ABSTRACT
We present the self-paced 3-class Graz brain-computer interface (BCI) which is based on the detection of sensorimotor electroencephalogram (EEG) rhythms induced by motor imagery. Self-paced operation means that the BCI is able to determine whether the ongoing brain activity is intended as control signal (intentional control) or not (non-control state). The presented system is able to automatically reduce electrooculogram (EOG) artifacts, to detect electromyographic (EMG) activity, and uses only three bipolar EEG channels. Two applications are presented: the freeSpace virtual environment (VE) and the Brainloop interface. The freeSpace is a computer-game-like application where subjects have to navigate through the environment and collect coins by autonomously selecting navigation commands. Three subjects participated in these feedback experiments and each learned to navigate through the VE and collect coins. Two out of the three succeeded in collecting all three coins. The Brainloop interface provides an interface between the Graz-BCI and Google Earth.

No MeSH data available.