Limits...
Context-based filtering for assisted brain-actuated wheelchair driving.

Vanacker G, del R Millán J, Lew E, Ferrez PW, Moles FG, Philips J, Van Brussel H, Nuttin M - Comput Intell Neurosci (2007)

Bottom Line: With the use of intelligent processing algorithms adapted to the task at hand, however, the performance can be increased.Experimental results show a possibility for significant improvement in the overall driving performance when using the shared control system compared to driving without it.These results have been obtained with 2 healthy subjects during their first day of training with the brain-actuated wheelchair.

View Article: PubMed Central - PubMed

Affiliation: The Department of Mechanical Engineering, Katholieke Universiteit, 3001 Leuven, Belgium. gerolf.vanacker@mech.kuleuven.be

ABSTRACT
Controlling a robotic device by using human brain signals is an interesting and challenging task. The device may be complicated to control and the nonstationary nature of the brain signals provides for a rather unstable input. With the use of intelligent processing algorithms adapted to the task at hand, however, the performance can be increased. This paper introduces a shared control system that helps the subject in driving an intelligent wheelchair with a noninvasive brain interface. The subject's steering intentions are estimated from electroencephalogram (EEG) signals and passed through to the shared control system before being sent to the wheelchair motors. Experimental results show a possibility for significant improvement in the overall driving performance when using the shared control system compared to driving without it. These results have been obtained with 2 healthy subjects during their first day of training with the brain-actuated wheelchair.

No MeSH data available.


The EEGclassifier performance for all days for subject 2. The left bar in each daydepicts the performance when driving without filter, the right one shows theperformance for sessions when filtering was active.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2267887&req=5

fig8: The EEGclassifier performance for all days for subject 2. The left bar in each daydepicts the performance when driving without filter, the right one shows theperformance for sessions when filtering was active.

Mentions: For both subjects the classifier performance isdifferent when controlling with or without the environmental filter as isvisible in Figures 7 and 8. When the overall BCI performance is rather bad, itis much better to drive with the filter (e.g., subject 1, day 1). On the otherhand, when the BCI performance is exceptionally good, driving with the sharedcontrol system may make it worse (e.g., subject 1, day 5). It is also worthmentioning that although subject 2 did not show the same increase in averageclassifier performance over all days (see Figure 8), he showed a steadyimprovement regarding the standard deviation on the performance (depicted inFigure 9). This reflects the gradually more constant driving behavior of thesubject, as his mental driving models become more mature.


Context-based filtering for assisted brain-actuated wheelchair driving.

Vanacker G, del R Millán J, Lew E, Ferrez PW, Moles FG, Philips J, Van Brussel H, Nuttin M - Comput Intell Neurosci (2007)

The EEGclassifier performance for all days for subject 2. The left bar in each daydepicts the performance when driving without filter, the right one shows theperformance for sessions when filtering was active.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2267887&req=5

fig8: The EEGclassifier performance for all days for subject 2. The left bar in each daydepicts the performance when driving without filter, the right one shows theperformance for sessions when filtering was active.
Mentions: For both subjects the classifier performance isdifferent when controlling with or without the environmental filter as isvisible in Figures 7 and 8. When the overall BCI performance is rather bad, itis much better to drive with the filter (e.g., subject 1, day 1). On the otherhand, when the BCI performance is exceptionally good, driving with the sharedcontrol system may make it worse (e.g., subject 1, day 5). It is also worthmentioning that although subject 2 did not show the same increase in averageclassifier performance over all days (see Figure 8), he showed a steadyimprovement regarding the standard deviation on the performance (depicted inFigure 9). This reflects the gradually more constant driving behavior of thesubject, as his mental driving models become more mature.

Bottom Line: With the use of intelligent processing algorithms adapted to the task at hand, however, the performance can be increased.Experimental results show a possibility for significant improvement in the overall driving performance when using the shared control system compared to driving without it.These results have been obtained with 2 healthy subjects during their first day of training with the brain-actuated wheelchair.

View Article: PubMed Central - PubMed

Affiliation: The Department of Mechanical Engineering, Katholieke Universiteit, 3001 Leuven, Belgium. gerolf.vanacker@mech.kuleuven.be

ABSTRACT
Controlling a robotic device by using human brain signals is an interesting and challenging task. The device may be complicated to control and the nonstationary nature of the brain signals provides for a rather unstable input. With the use of intelligent processing algorithms adapted to the task at hand, however, the performance can be increased. This paper introduces a shared control system that helps the subject in driving an intelligent wheelchair with a noninvasive brain interface. The subject's steering intentions are estimated from electroencephalogram (EEG) signals and passed through to the shared control system before being sent to the wheelchair motors. Experimental results show a possibility for significant improvement in the overall driving performance when using the shared control system compared to driving without it. These results have been obtained with 2 healthy subjects during their first day of training with the brain-actuated wheelchair.

No MeSH data available.