Limits...
Fully online multicommand brain-computer interface with visual neurofeedback using SSVEP paradigm.

Martinez P, Bakardjian H, Cichocki A - Comput Intell Neurosci (2007)

Bottom Line: We propose a new multistage procedure for a real-time brain-machine/computer interface (BCI).Extensive experiments with five young healthy subjects confirmed the high performance of the proposed online BCI system.The modular structure, high speed, and the optimal frequency band characteristics of the BCI platform are features which allow an extension to a substantially higher number of commands in the near future.

View Article: PubMed Central - PubMed

Affiliation: Laboratory for Advanced Brain Signal Processing, Brain Science Institute RIKEN, Wako-Shi, Saitama 351-0198, Japan. pablo.martinez@brain.riken.jp

ABSTRACT
We propose a new multistage procedure for a real-time brain-machine/computer interface (BCI). The developed system allows a BCI user to navigate a small car (or any other object) on the computer screen in real time, in any of the four directions, and to stop it if necessary. Extensive experiments with five young healthy subjects confirmed the high performance of the proposed online BCI system. The modular structure, high speed, and the optimal frequency band characteristics of the BCI platform are features which allow an extension to a substantially higher number of commands in the near future.

No MeSH data available.


Enhancementof EEG via BSS. First, the raw EEG data (sensor signals) is decomposed andranked as independent or spatially decorrelated components; in the next step,only the useful components are projected back to the scalp level, whileundesirable components containing artifacts and noise are removed from thesignal. The main advantage of our approach is that we do not need any expertdecision to select significant components, since the AMUSE algorithmautomatically ranks the components as illustrated in Figure 6.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2266836&req=5

fig5: Enhancementof EEG via BSS. First, the raw EEG data (sensor signals) is decomposed andranked as independent or spatially decorrelated components; in the next step,only the useful components are projected back to the scalp level, whileundesirable components containing artifacts and noise are removed from thesignal. The main advantage of our approach is that we do not need any expertdecision to select significant components, since the AMUSE algorithmautomatically ranks the components as illustrated in Figure 6.

Mentions: The AMUSE BSS algorithm allowed us to automaticallyrank the EEG components. The undesired components corresponding to artifactswere removed and the rest of the useful (significant) components were projectedback to scalp level using the pseudo inverse of W, see Figure 5(6)X^=W+X.The six EEG channels werehigh-pass-filtered with a cutoff frequency of 2 Hz before the AMUSE algorithmwas applied.


Fully online multicommand brain-computer interface with visual neurofeedback using SSVEP paradigm.

Martinez P, Bakardjian H, Cichocki A - Comput Intell Neurosci (2007)

Enhancementof EEG via BSS. First, the raw EEG data (sensor signals) is decomposed andranked as independent or spatially decorrelated components; in the next step,only the useful components are projected back to the scalp level, whileundesirable components containing artifacts and noise are removed from thesignal. The main advantage of our approach is that we do not need any expertdecision to select significant components, since the AMUSE algorithmautomatically ranks the components as illustrated in Figure 6.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2266836&req=5

fig5: Enhancementof EEG via BSS. First, the raw EEG data (sensor signals) is decomposed andranked as independent or spatially decorrelated components; in the next step,only the useful components are projected back to the scalp level, whileundesirable components containing artifacts and noise are removed from thesignal. The main advantage of our approach is that we do not need any expertdecision to select significant components, since the AMUSE algorithmautomatically ranks the components as illustrated in Figure 6.
Mentions: The AMUSE BSS algorithm allowed us to automaticallyrank the EEG components. The undesired components corresponding to artifactswere removed and the rest of the useful (significant) components were projectedback to scalp level using the pseudo inverse of W, see Figure 5(6)X^=W+X.The six EEG channels werehigh-pass-filtered with a cutoff frequency of 2 Hz before the AMUSE algorithmwas applied.

Bottom Line: We propose a new multistage procedure for a real-time brain-machine/computer interface (BCI).Extensive experiments with five young healthy subjects confirmed the high performance of the proposed online BCI system.The modular structure, high speed, and the optimal frequency band characteristics of the BCI platform are features which allow an extension to a substantially higher number of commands in the near future.

View Article: PubMed Central - PubMed

Affiliation: Laboratory for Advanced Brain Signal Processing, Brain Science Institute RIKEN, Wako-Shi, Saitama 351-0198, Japan. pablo.martinez@brain.riken.jp

ABSTRACT
We propose a new multistage procedure for a real-time brain-machine/computer interface (BCI). The developed system allows a BCI user to navigate a small car (or any other object) on the computer screen in real time, in any of the four directions, and to stop it if necessary. Extensive experiments with five young healthy subjects confirmed the high performance of the proposed online BCI system. The modular structure, high speed, and the optimal frequency band characteristics of the BCI platform are features which allow an extension to a substantially higher number of commands in the near future.

No MeSH data available.