Professional Documents
Culture Documents
DOI 10.1007/s11517-006-0107-4
TECHNICAL NOTE
Abstract One challenge in the current research of normal output channels of peripheral nerves and
brain–computer interfaces (BCIs) is how to classify muscles, arouses more and more interests of late
time-varying electroencephalographic (EEG) signals years [9, 13–15]. Up to now, study of BCI systems has
as accurately as possible. In this paper, we address this mainly involved recording of electroencephalographic
problem from the aspect of updating feature extractors (EEG) signals using surface electrodes, as this kind
and propose an adaptive feature extractor, namely of recording is relatively convenient, harmless and
adaptive common spatial patterns (ACSP). Through inexpensive compared with other methods [2]. In this
the weighed update of signal covariances, the most paper, we focus on the classification problem of
discriminative features related to the current brain EEG signals, a crucial component embodied in gen-
states are extracted by the method of multi-class eral EEG-based BCIs. For an EEG-based BCI,
common spatial patterns (CSP). Pseudo-online simu- adaptive learning algorithms are necessary in princi-
lations of EEG signal classification with a support ple, because the recorded EEG signals usually change
vector machine (SVM) classifier for multi-class mental over time due to both biological and technical causes,
imagery tasks show the effectiveness of the proposed such as subject attention, subject fatigue, disease
adaptive feature extractor. progression, electrode impedances, amplifier noise,
and environmental noise [13]. The high variability of
Keywords Brain–computer interface (BCI) Æ EEG recordings makes it a difficult task to classify
Common spatial patterns (CSP) Æ EEG signal different EEG signals accurately and necessitates
classification Æ Feature extraction adaptive learning to boost up the performance of
existing BCIs.
With respect to adaptive learning for EEG signal
1 Introduction classification, one can choose to update classifiers or
alternatively the feature extractors. However, up to
The research of brain–computer interfaces (BCIs), now, there is not much work addressing this problem.
which aim to provide their users communication and The adaptive update of Bayesian statistical classifier
control capabilities that do not depend on the brain’s with Gaussian mixture model (GMM) is recently
studied in several papers [6, 7, 10, 11], whereas the
performance is still very moderate. Wolpaw and
McFarland [16] used the least-mean-square (LMS)
S. Sun (&) Æ C. Zhang algorithm to adaptively adjust weights for a two-
State Key Laboratory of Intelligent Technology
and Systems, Department of Automation,
dimensional movement control and found out that
Tsinghua University, Beijing 100084, China people with severe motor disabilities could use scalp
e-mails: shiliangsun@gmail.com; sunsl02@mails.tsinghua.edu.cn EEG signals to operate a robotic arm or a neuro-
C. Zhang prosthesis. In this paper, we propose to address the
e-mail: zcs@mail.tsinghua.edu.cn adaptive learning problem in EEG signal classification
123
Med Bio Eng Comput
123
Med Bio Eng Comput
123
Med Bio Eng Comput
Table 1 The classification accuracies (%) using different feature and the present study does not take this into account.
extractors A complete adaptive algorithm should also address the
Subject Training session Test session Accuracy adaptive behavior of the brain itself.
SCSP WCSP ACSP The computational complexity of ACSP is much less.
Because the number of electrodes (data dimensions) in
S1 1 2 69.03 68.60 70.32 BCI utilities is usually small, such as 64, 128, and 256 (15
1 3 68.74 68.31 76.66
electrodes in our experiments), the simultaneous diag-
2 1 61.59 65.24 63.73
2 3 69.38 69.16 64.24 onalization of covariance matrices could almost be
3 1 51.93 59.23 63.30 implemented in real time. This could completely meet
3 2 58.71 57.42 67.96 the needs of online learning. Besides, as the subjects
S2 1 2 51.29 57.33 65.09 used in this article represent three different levels of
1 3 56.71 60.82 74.46
2 1 54.31 53.88 63.36 mental consistency, which are respectively consistent,
2 3 58.01 57.36 69.70 scarcely consistent, and inconsistent [5], we are confi-
3 1 53.02 56.03 70.47 dent that ACSP would function well in a wide range of
3 2 59.91 56.03 65.52 users. We believe that ACSP would show more merits
S3 1 2 56.49 58.87 65.80
1 3 52.60 48.48 57.58 in future developments of BCI technology.
2 1 54.63 54.85 53.96
2 3 55.19 54.33 56.06 Acknowledgments The authors would like to thank IDIAP
3 1 51.98 54.85 57.27 Research Institute of Switzerland for providing the analyzed
3 2 64.94 63.64 66.67 data. The authors are also grateful to the anonymous editor and
Average 58.25 59.14 65.12 reviewers for giving valuable comments. This work was sup-
ported by the Chinese Natural Science Foundation (60475001)
and Postdoctoral Science Foundation (2005038075).
best among SCSP, WCSP, and ACSP, at least on the
used data set. At the same time, this also manifests the
necessity and applicability of our adaptive feature References
extractor. 1. Chiappa S, Millán JR (2005) Data set V <metal imagery,
multi-class> [http://www.ida.first.fraunhofer.de/projects/bci/
competition_iii/ desc_V.html]. IDIAP Research Institute,
4 Discussions and conclusions Switzerland
2. Curran EA, Stokes MJ (2003) Learning to control brain
activity: a review of the production and control of EEG
In this paper, we propose the ACSP method for the
components for driving brain–computer interface (BCI)
feature extraction of EEG signals. Its efficacy and systems. Brain Cogn 51:326–336
superiority over the SCSP and WCSP methods are 3. Dornhege G, Blankertz B, Curio G, Müller KR (2004)
validated through classification experiments on multi- Boosting bit rates in noninvasive EEG single-trial classifi-
cations by feature combination and multiclass paradigms.
ple recording sessions of three subjects. Theoretically,
IEEE Trans Biomed Eng 51:993–1002
because EEG signals are time-varying, if we use SCSP 4. Duda RO, Hart PE, Stork DG (2000) Pattern classification.
to extract features on new EEG segments, the distri- Wiley, New York
bution of signal features would be transferred. In this 5. Galán F, Oliva F, Guàrdia J (2005) BCI competition III, data
set V: algorithm description [http://www.ida.first.fraunhofer.
sense, adaptive feature extraction has a sound basis.
de/projects/bci/competition_iii/results/ martigny/FerranGalan_
However, because WCSP treats all the EEG entries in desc.pdf]. Faculty of Psychology, University of Barcelona
computing covariance matrix equally, it cannot catch 6. Millán JR (2004) On the need for on-line learning in brain–
hold of the variability of EEG signals effectively. This computer interfaces. In: Proceedings of the international
joint conference on neural networks, Budapest, Hungary
is the reason why WCSP is inferior to ACSP which
7. Millán JR, Renkens F, Mouriño J, Gerstner W (2004) Brain-
considers the weighted problem of EEG entries actuated interaction. Artif Intell 159:241–259
advisably. 8. Müller-Gerking J, Pfurtscheller G, Flyvbjerg H (1999)
It should be noted that although ACSP has obtained Designing optimal spatial filters for single-trial EEG classi-
fication in a movement task. Clin Neurophysiol 110:787–798
the best results generally, pitfalls also exist. From
9. Nicolelis MAL (2001) Actions from thoughts. Nature
Table 1, we can find that there are several training and 409:403–407
test trails where ACSP does not show improvements in 10. Sun S, Zhang C (2005) Learning on-line classification via
the classification. We provide an explanation for this decorrelated LMS algorithm: application to brain–computer
interfaces. Lect Notes Comput Sci 3735:215–226
phenomenon. Though the subjects are doing mental
11. Sun S, Zhang C, Lu N (2005) On the on-line learning algo-
imagery tasks, there exist some irrelevant activities rithms for EEG signal classification in brain computer
from the brain. These activities also change over time, interfaces. Lect Notes Comput Sci 3614:638–647
123
Med Bio Eng Comput
12. Vapnik V (2000) The nature of statistical learning theory. 15. Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G,
Springer, New York Vaughan TM (2002) Brain–computer interfaces for commu-
13. Vaughan TM (2003) Guest editorial brain–computer inter- nication and control. Clin Neurophysiol 113:767–791
face technology: a review of the second international meet- 16. Wolpaw JR, McFarland DJ (2004) Control of a two-dimen-
ing. IEEE Trans Neural Syst Rehabil 11:94–109 sional movement signal by a non-invasive brain–computer
14. Wolpaw JR, McFarland DJ, Neat GW, Forneris C (1991) An interface in humans. Proc Natl Acad Sci 101:17849–17854
EEG-based brain–computer interface for cursor control.
Electroencephalogr Clin Neurophysiol 78:252–259
123