Limits...
Online artifact removal for brain-computer interfaces using support vector machines and blind source separation.

Halder S, Bensch M, Mellinger J, Bogdan M, Kübler A, Birbaumer N, Rosenstiel W - Comput Intell Neurosci (2007)

Bottom Line: In order to select a suitable BSS/ICA method, three ICA algorithms (JADE, Infomax, and FastICA) and one BSS algorithm (AMUSE) are evaluated to determine their ability to isolate electromyographic (EMG) and electrooculographic (EOG) artifacts into individual components.An implementation of the selected BSS/ICA method with SVMs trained to classify EMG and EOG artifacts, which enables the usage of the method as a filter in measurements with online feedback, is described.This filter is evaluated on three BCI datasets as a proof-of-concept of the method.

View Article: PubMed Central - PubMed

Affiliation: Institute of Medical Psychology and Behavioral Neurobiology, University of Tübingen, Gartenstr. 29, 72074 Tübingen, Germany. halder@informatik.uni-tuebingen.de

ABSTRACT
We propose a combination of blind source separation (BSS) and independent component analysis (ICA) (signal decomposition into artifacts and nonartifacts) with support vector machines (SVMs) (automatic classification) that are designed for online usage. In order to select a suitable BSS/ICA method, three ICA algorithms (JADE, Infomax, and FastICA) and one BSS algorithm (AMUSE) are evaluated to determine their ability to isolate electromyographic (EMG) and electrooculographic (EOG) artifacts into individual components. An implementation of the selected BSS/ICA method with SVMs trained to classify EMG and EOG artifacts, which enables the usage of the method as a filter in measurements with online feedback, is described. This filter is evaluated on three BCI datasets as a proof-of-concept of the method.

No MeSH data available.


Related in: MedlinePlus

Power spectra showing the differences in the features used for classification,in this case of an IC containing jaw muscle contraction (a) and eye movement(b).
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2234090&req=5

fig3: Power spectra showing the differences in the features used for classification,in this case of an IC containing jaw muscle contraction (a) and eye movement(b).

Mentions: Figure 2 shows the difference between the topography of eye blinking and horizontal eye movement ICs. The eye blinking artifacts project most strongly on the frontal electrodes Fp1 and Fp2, whereas horizontal eye movement artifacts have a very distinct projection, in which electrodes on different hemispheres have a different polarity. The topography of EMG artifacts depends strongly on the muscles used, but they all show a characteristic power spectrum. An EMG power spectrum of a jaw muscle artifact is shown next to an eye movement power spectrum in Figure 3.


Online artifact removal for brain-computer interfaces using support vector machines and blind source separation.

Halder S, Bensch M, Mellinger J, Bogdan M, Kübler A, Birbaumer N, Rosenstiel W - Comput Intell Neurosci (2007)

Power spectra showing the differences in the features used for classification,in this case of an IC containing jaw muscle contraction (a) and eye movement(b).
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2234090&req=5

fig3: Power spectra showing the differences in the features used for classification,in this case of an IC containing jaw muscle contraction (a) and eye movement(b).
Mentions: Figure 2 shows the difference between the topography of eye blinking and horizontal eye movement ICs. The eye blinking artifacts project most strongly on the frontal electrodes Fp1 and Fp2, whereas horizontal eye movement artifacts have a very distinct projection, in which electrodes on different hemispheres have a different polarity. The topography of EMG artifacts depends strongly on the muscles used, but they all show a characteristic power spectrum. An EMG power spectrum of a jaw muscle artifact is shown next to an eye movement power spectrum in Figure 3.

Bottom Line: In order to select a suitable BSS/ICA method, three ICA algorithms (JADE, Infomax, and FastICA) and one BSS algorithm (AMUSE) are evaluated to determine their ability to isolate electromyographic (EMG) and electrooculographic (EOG) artifacts into individual components.An implementation of the selected BSS/ICA method with SVMs trained to classify EMG and EOG artifacts, which enables the usage of the method as a filter in measurements with online feedback, is described.This filter is evaluated on three BCI datasets as a proof-of-concept of the method.

View Article: PubMed Central - PubMed

Affiliation: Institute of Medical Psychology and Behavioral Neurobiology, University of Tübingen, Gartenstr. 29, 72074 Tübingen, Germany. halder@informatik.uni-tuebingen.de

ABSTRACT
We propose a combination of blind source separation (BSS) and independent component analysis (ICA) (signal decomposition into artifacts and nonartifacts) with support vector machines (SVMs) (automatic classification) that are designed for online usage. In order to select a suitable BSS/ICA method, three ICA algorithms (JADE, Infomax, and FastICA) and one BSS algorithm (AMUSE) are evaluated to determine their ability to isolate electromyographic (EMG) and electrooculographic (EOG) artifacts into individual components. An implementation of the selected BSS/ICA method with SVMs trained to classify EMG and EOG artifacts, which enables the usage of the method as a filter in measurements with online feedback, is described. This filter is evaluated on three BCI datasets as a proof-of-concept of the method.

No MeSH data available.


Related in: MedlinePlus