TY - JOUR
T1 - Toward unsupervised adaptation of LDA for brain-computer interfaces
AU - Vidaurre, C.
AU - Kawanabe, M.
AU - Von Bünau, P.
AU - Blankertz, B.
AU - Müller, K. R.
N1 - Funding Information:
Manuscript received August 27, 2010; revised October 10, 2010; accepted October 10, 2010. Date of publication November 18, 2010; date of current version February 18, 2011. This work was supported by the European Union (EU) MC-IEF-040666, IST-PASCAL2 Network of Excellence, ICT-216886 and by the Bundesministerium für Bildung und Forschung (BMBF) FKZ-01IBE01A/B. Asterisk indicates corresponding author. *C. Vidaurre is with the Department of Machine Learning, Berlin Institute of Technology, 10623 Berlin, Germany.
PY - 2011/3
Y1 - 2011/3
N2 - There is a step of significant difficulty experienced by brain-computer interface (BCI) users when going from the calibration recording to the feedback application. This effect has been previously studied and a supervised adaptation solution has been proposed. In this paper, we suggest a simple unsupervised adaptation method of the linear discriminant analysis (LDA) classifier that effectively solves this problem by counteracting the harmful effect of nonclass-related nonstationarities in electroencephalography (EEG) during BCI sessions performed with motor imagery tasks. For this, we first introduce three types of adaptation procedures and investigate them in an offline study with 19 datasets. Then, we select one of the proposed methods and analyze it further. The chosen classifier is offline tested in data from 80 healthy users and four high spinal cord injury patients. Finally, for the first time in BCI literature, we apply this unsupervised classifier in online experiments. Additionally, we show that its performance is significantly better than the state-of-the-art supervised approach.
AB - There is a step of significant difficulty experienced by brain-computer interface (BCI) users when going from the calibration recording to the feedback application. This effect has been previously studied and a supervised adaptation solution has been proposed. In this paper, we suggest a simple unsupervised adaptation method of the linear discriminant analysis (LDA) classifier that effectively solves this problem by counteracting the harmful effect of nonclass-related nonstationarities in electroencephalography (EEG) during BCI sessions performed with motor imagery tasks. For this, we first introduce three types of adaptation procedures and investigate them in an offline study with 19 datasets. Then, we select one of the proposed methods and analyze it further. The chosen classifier is offline tested in data from 80 healthy users and four high spinal cord injury patients. Finally, for the first time in BCI literature, we apply this unsupervised classifier in online experiments. Additionally, we show that its performance is significantly better than the state-of-the-art supervised approach.
KW - Adaptive signal processing
KW - brain computer interfaces
KW - linear discriminant analysis
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=79952167211&partnerID=8YFLogxK
U2 - 10.1109/TBME.2010.2093133
DO - 10.1109/TBME.2010.2093133
M3 - Article
C2 - 21095857
AN - SCOPUS:79952167211
VL - 58
SP - 587
EP - 597
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
SN - 0018-9294
IS - 3 PART 1
ER -