• Keine Ergebnisse gefunden

Improving Motor Imagery BCI with User Response to Feedback

N/A
N/A
Protected

Academic year: 2022

Aktie "Improving Motor Imagery BCI with User Response to Feedback "

Copied!
1
0
0

Wird geladen.... (Jetzt Volltext ansehen)

Volltext

(1)

Improving Motor Imagery BCI with User Response to Feedback

Mahta Mousavi*, Adam S. Koerner, Qiong Zhang, Eunho Noh, and Virginia R. de Sa

University of California San Diego, La Jolla, CA, USA

*Address: 9500 Gilman Dr., La Jolla, CA, 92093-0515 . E-mail: mahta@ucsd.edu

&%)' $%&!!&&&%%'&"$!$ !&!$$+56 7;80 !)($.&$%%&&&( !'&!)&$%"! %&! %&% . )&$ & % '% &! %%+ !$ '$&+0 &% )!$. ) %!) &&

$%"! % % % $ !& $$ %$ $#' + % (%&& )+% &!

"$!(%%&! 0

&)$!&$!A%'&%%&!! &$!'$%!$)&$& & !&!$

$+ )! )$ %!) % '$%!$ !( & % (%' 0 '$%!$ !( ($+ @:: %

%! "$1&$ !( &"&&$ &!%'&"$!$ 0%5!

)&%'&%)$' )$6%$&&!* &$!!(%'! '%$2%0 &

%% " &!&. +$&! %"&) &% &(%'%

'&!'%&!&'%$2%$%"! %&!(%'! &$0&!&!@%"&&$%5=

"$ %%6 )$ !% &$!' !! %"& "&&$ % 56 7<8 & ! "!)$ ! & &$

% %)$%%)& $%$ & +%%56&$ )&;:1!$!%%1(&! 0

'$5;6%!)%%%&! $%'&% %& $$$!$!%%&! $&!$

!'$ ! !'$ %'&% 5 ' = ! !'$ %&6 & + %!)% & % &+ !( (

56%! & '$!&$%7=8 &$ &%:0?(0( &%%%+

&) $& ($%'% & 0 ( &% %%$ "$!$ !$ %%$ &$ &! %& '%

)&$&%&'$%!$!( &)% &%$5!!6!$ ! 1%$56$&! 0!&&&

( %%&! )% %'%%' %$ $#' + % % ( %%&! 7>8 && &

!$&! !'& )&$ & %'& 34 & !( & !$ !& + ! !' )& &

!"'&$2% $ !'& % 0 +"!&%, && %&&1!1& $& &'$ *&$&!

%%&! 100.%! ! '$5;61% &&+ &$%"!& &&!

"$!(&%& $"$!'$0""!%&$$%%! &!&!'&"'&!( (%%$%

)$)&$ &)!%& &%%$%!$) &'$%!$!(%&!&&!$&!&$&/&&%.&!

$&+& &!!' &&!%$('$%!$!( &0%'&%$%!) )& & ! '$

5;60! %%$%&!"$!(&( &$#' + %&&(%%$%!(

(5--!$"B:0;.9!$"B:0:? 99!$"B:0:;60'&%$( !&$ )&$

5! +&' $&%6.)+*" &!($!)'$%0

Figure 1. Figures show correct classification rate versus frequency band for four subjects. Note that the RvL and GvB classifiers have above chance performance in similar frequency bands.

)!$%!)%&&$%"! % % %$"$% & &%$#' + % && $ '% !$ %%&! 0 "$!"!% &! ""+ !%& $$%%! &! ! ( (%%$%%"!& &)+&!(&&&!(%'0%(%%&! %!$

$!'%& &! ! 1%&&! $+ %&$'&! % 7?8. '&'$ )!$ ) (%&& !$ %!"%&& &!% !$

! &%% %(Supported by NSF grants IIS 1219200, SMA 1041755, IIS 1528214).

[1] Barbero A, Grosse-Wentrup M. Biased feedback in brain-computer interfaces. J. of neuroengineering and rehabilitation, 7:34, 2010.

[2] Muller-Gerking J, Pfurtscheller G, and Flyvbjerg H. Designing optimal spatial filters for single-trial EEG classification in a movement task. J Clin Neurophysiol, 110(5):787–798, 1999.

[3] Muller-putz GR, Scherer R, Brunner C, Leeb R, Pfurtscheller G. Better than random? A closer look on BCI results. International J. of Bioelectromegnetism, 10(1):52-55, 2008.

[4] Pfurtscheller G, Brunner C, Scholgl A, and Lopes da Silva FH. Mu rhythm (de)synchronization and single-trial classification of different motor imagery tasks. Neuroimage, 31:153-159, 2006.

[5] de Sa, V.R. (2012). An interactive control strategy is more robust to non-optimal classification boundaries. ICMI'12 pp 579-586.

frequency interval (Hz)

**

** ~~

**** **

**

******** ~~

*

*******************

**

DOI: 10.3217/978-3-85125-467-9-28 Proceedings of the 6th International Brain-Computer Interface Meeting, organized by the BCI Society

Published by Verlag der TU Graz, Graz University of Technology, sponsored by g.tec medical engineering GmbH 28

Referenzen

ÄHNLICHE DOKUMENTE

To compare classification accuracy of the SRC method, we use two most widely used classification methods in the BCI field, namely, linear discriminant analysis

In Motor Imagery (MI)-based BCIs, the considered features typically rely on the power spectral density (PSD) of brain signals, but alternative features can be explored looking

Despite the main role that experimenters have in the experimental process and the literature regarding the impact of social and emotional feedback, no studies had yet been led in

In this work, we have extended the multivariate empirical mode decomposition (MEMD) [1] by filtering the intrinsic mode functions (IMFs) based on mean frequency measure to obtain

Clinical tests of motor performance, and paired-pulse TMS inter-hemispheric inhibition (IHI) tests were evaluated at three time points: baseline, post-rTMS/BCI, and

Here, we investigate a combination of a motor imagery BCI with a relaxation/concentration paradigm to operate remote-controlled cars in a gaming application using IMEC’s wearable

There- fore, signals recorded by these distant electrodes can be used as a noise reference for any multichannel algorithm of adaptive filtering.. In theory, signal achieved as a

This work presents a novel processing stage for BCI systems using the Filter Bank Common Spatial Patterns algorithm for feature extraction and Particle Swarm