On the use of interaction error potentials for adaptive brain computer interfaces

Fulltext present in this item

Fulltext: 98171.pdf

Format: PDF

Description: publisher's version

Embargo: until further notice

Title:	On the use of interaction error potentials for adaptive brain computer interfaces
Author(s):	Llera, A. ; Gerven, M.A.J. van ; Gomez Cerda, V. ; Jensen, O. ; Kappen, H.J.
Publication year:	2011
Source:	Neural Networks, vol. 24, iss. 10, (2011), pp. 1120-1127
Number of Pages:	8 p.
ISSN:	0893-6080
DOI:	https://doi.org/10.1016/j.neunet.2011.05.006
Publication type:	Article / Letter to editor
Please use this identifier to cite or link to this item : https://hdl.handle.net/2066/98171
Display more details
Subject:	160 000 Neuronal Oscillations Biophysics Cognitive artificial intelligence DCN 3: Neuroinformatics DI-BCB_DCC_Theme 4: Brain Networks and Neuronal Communication Data Science
Organization:	Donders Centre for Cognitive Neuroimaging Biophysics Cognitive Neuroscience SW OZ DCC KI Data Science PI Group Neuronal Oscillations
Former Organization:	F.C. Donders Centre for Cognitive Neuroimaging
Journal title:	Neural Networks
Volume:	vol. 24
Issue:	iss. 10
Page start:	p. 1120
Page end:	p. 1127
Abstract:	We propose an adaptive classification method for the Brain Computer Interfaces (BCI) which uses Interaction Error Potentials (IErrPs) as a reinforcement signal and adapts the classifier parameters when an error is detected. We analyze the quality of the proposed approach in relation to the misclassification of the IErrPs. In addition we compare static versus adaptive classification performance using artificial and MEG data. We show that the proposed adaptive framework significantly improves the static classification methods.
Languages used:	English (eng)