Multi-class motor imagery EEG decoding for brain-computer interfaces

Deng Wang, Duoqian Miao, Gunnar Blohm, Deng Wang, Duoqian Miao, Gunnar Blohm

Abstract

Recent studies show that scalp electroencephalography (EEG) as a non-invasive interface has great potential for brain-computer interfaces (BCIs). However, one factor that has limited practical applications for EEG-based BCI so far is the difficulty to decode brain signals in a reliable and efficient way. This paper proposes a new robust processing framework for decoding of multi-class motor imagery (MI) that is based on five main processing steps. (i) Raw EEG segmentation without the need of visual artifact inspection. (ii) Considering that EEG recordings are often contaminated not just by electrooculography (EOG) but also other types of artifacts, we propose to first implement an automatic artifact correction method that combines regression analysis with independent component analysis for recovering the original source signals. (iii) The significant difference between frequency components based on event-related (de-) synchronization and sample entropy is then used to find non-contiguous discriminating rhythms. After spectral filtering using the discriminating rhythms, a channel selection algorithm is used to select only relevant channels. (iv) Feature vectors are extracted based on the inter-class diversity and time-varying dynamic characteristics of the signals. (v) Finally, a support vector machine is employed for four-class classification. We tested our proposed algorithm on experimental data that was obtained from dataset 2a of BCI competition IV (2008). The overall four-class kappa values (between 0.41 and 0.80) were comparable to other models but without requiring any artifact-contaminated trial removal. The performance showed that multi-class MI tasks can be reliably discriminated using artifact-contaminated EEG recordings from a few channels. This may be a promising avenue for online robust EEG-based BCI applications.

Keywords: EEG channel selection; artifact processing; brain-computer interface; electroencephalogram; multi-class motor imagery.

Figures

Figure 1
Figure 1
Left: trial timing of the motor imagery paradigm. (Cued MI: left hand, right hand, both feet, tongue); Right: electrode montage corresponding to the international 10–20 system (adapted from Brunner et al., 2008).
Figure 2
Figure 2
Schematic diagram for the EEG signal processing procedure (Five-stage decoding EEG – FSDE).
Figure 3
Figure 3
Influence of artifacts: the number of artifact-contaminated trials influences the decoding of the test set (A) but not the training set (B).
Figure 4
Figure 4
Time-frequency maps (ERD/ERS) relative to the baseline recorded seconds before the event for all 22 EEG channels during four-class motor imagery task. Event-related desynchronization (ERD) is plotted in red, while event-related synchronization (ERS) is in blue.
Figure 5
Figure 5
Comparison of kappa scores using three different filtering approaches.
Figure 6
Figure 6
Correlation between the selected channel set size and kappa score.
Figure 7
Figure 7
Information transfer rate (ITR) obtained for all nine subjects.
Figure 8
Figure 8
Comparison of the performance measures (kappa scores) for different processing stage removal across all subjects on the test set (session 2).
Figure 9
Figure 9
Comparison of the performance measures (kappa scores) for the whole processing framework with and without artifact removal for subject 1 to 9 on the test set (session 2).

References

    1. Alkadhi H., Brugger P., Boendermaker S. H., Crelier G., Curt A., Hepp-Reymond M. C., et al. (2005). What disconnection tells about motor imagery: evidence from paraplegic patients. Cereb. Cortex 15, 131–14010.1093/cercor/bhh116
    1. Ang K. K., Chin Z. Y., Zhang H., Guan C. (2008). “Filter bank common spatial pattern (FBCSP) in brain-computer interface,” in Proceeding of IJCNN’08, Hong Kong, China, 2390–2397
    1. Arvaneh M., Guan C. T., Ang K. K., Quek C. (2011). Optimizing the channel selection and classification accuracy in EEG-Based BCI source. IEEE Trans. Biomed. Eng. 58, 1865–187310.1109/TBME.2011.2131142
    1. Bashashati A., Fatourechi M., Ward R. K., Birch G. E. (2007). A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals. J. Neural. Eng. 4, R32–R5710.1088/1741-2560/4/2/R03
    1. Brunner C., Leeb R., Müller-Putz G. R., Schlögl A., Pfurtscheller G. (2008). BCI Competition 2008 – Graz data set A. Available at:
    1. Chang C. C., Lin C. J. (2001). Libsvm: A Library for Support Vector Machines. Available at:
    1. Cohen J. (1960). A coefficient of agreement for nominal scales. Educ. Psychol. Meas. 20, 37–4610.1177/001316446002000104
    1. Doud A. J., Lucas J. P., Pisansky M. T., He B. (2011). Continuous three-dimensional control of a virtual helicopter using a motor imagery based brain-computer interface. PLoS ONE 6, e26322.10.1371/journal.pone.0026322
    1. Fatourechi M., Bashashati A., Ward R. K., Birch G. E. (2007). EMG and EOG artifacts in brain computer interface systems: a survey. Clin. Neurophysiol. 118, 480–49410.1016/j.clinph.2006.10.019
    1. Gouy-Pailler C., Congedo M., Brunner C., Jutten C., Pfurtscheller G. (2008). “Multi-class independent common spatial patterns: exploiting energy variations of brain sources,” in Proceeding of the 4rd International Brain–Computer Interface Workshop and Training Course, Graz, Austria
    1. Gouy-Pailler C., Congedo M., Brunner C., Jutten C., Pfurtscheller G. (2010). Nonstationary brain source separation for multiclass motor imagery. IEEE Trans. Biomed. Eng. 57, 469–47810.1109/TBME.2009.2032162
    1. Hallez H., De Vos M., Vanrumste B., Van Hese P., Assecondi S., Van Laere K., et al. (2009). Removing muscle and eye artifacts using blind source separation techniques in ictal EEG source imaging. Clin. Neurophysiol. 120, 1262–127210.1016/j.clinph.2009.05.010
    1. Hoffmann U., Vesin J. M., Ebrahimi T., Diserens K. (2008). An efficient P300-based brain-computer interface for disabled subjects. J. Neurosci. Methods 167, 115–12510.1016/j.jneumeth.2007.03.005
    1. Hyvärinen A. (1999). Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. Neural. Netw. 10, 626–63410.1109/72.761722
    1. Hyvarinen A., Karhunen J., Oja E. (2001). Independent Component Analysis. New York: John Wiley and Sons
    1. Hyvarinen A., Oja E. (1997). A fast fixed-point algorithm for independent component analysis. Neural. Comput. 9, 1483–146210.1162/neco.1997.9.7.1483
    1. Joyce C. A., Gorodnitsky I. F., Kutas M. (2004). Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. Psychophysiology 41, 313–32510.1111/j.1469-8986.2003.00141.x
    1. Kolodziej M., Majkowski A., Rak R. J. (2010). Matlab FE-Toolbox – an universal utility for feature extraction of EEG signals for BCI realization. Prz. Elektrotechniczny 86, 44–46
    1. Lake D. E., Richman J. S., Griffin M. P., Moorman J. R. (2002). Sample entropy analysis of neonatal heart rate variability. Am. J. Physiol. Regul. Integr. Comp. Physiol. 283, R789–R797
    1. Lew E., Nuttin M., Ferrez P. W., Degeest A., Buttfield A., Vanacker G., et al. (2006). “Noninvasive brain–computer interface for mental control of a simulated wheelchair,” in Proceeding of the 3rd International Brain–Computer Interface Workshop and Training Course, Graz, Austria
    1. Millán JdR., Renkens F., Mouriño J., Gerstner W. (2004). Noninvasive brain actuated control of a mobile robot by human EEG. IEEE Trans. Biomed. Eng. 51, 1026–103310.1109/TBME.2004.827086
    1. Nakayama K., Inagaki K. (2006). “A brain computer interface based on neural network with efficient pre-processing,” in Proceeding of ISPACS ‘06, Yonago, Japan, 673–676
    1. Noirhomme Q., Kitney R. I., Macq B. (2008). Single-trial EEG source reconstruction for brain-computer interface. IEEE Trans. Biomed. Eng. 55, 1592–160110.1109/TBME.2007.913986
    1. Pfurtscheller G. (1977). Graphical display and statistical evaluation of event-related desynchronization (ERD). Electroencephalogr. Clin. Neurophysiol. 43, 757–76010.1016/0013-4694(77)90092-X
    1. Pfurtscheller G. (1992). Event-related synchronization (ERS): an electrophysiological correlate of cortical areas at rest. Electroencephalogr. Clin. Neurophysiol. 83, 62–6910.1016/0013-4694(92)90133-3
    1. Pfurtscheller G., Aranibar A. (1977). Event-related cortical desynchronization detected by power measurements of scalp EEG. Electroencephalogr. Clin. Neurophysiol. 42, 817–82610.1016/0013-4694(77)90235-8
    1. Pfurtscheller G., Aranibar A. (1979). Evaluation of event-related desynchronization (ERD) preceding and following voluntary self-paced movement. Electroencephalogr. Clin. Neurophysiol. 46, 138–14610.1016/0013-4694(79)90063-4
    1. Pfurtscheller G., Lopes da Silva F. H. L. (1999). Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin. Neurophysiol. 110, 1842–185710.1016/S1388-2457(99)00141-8
    1. Pfurtscheller G., Neuper C., Flotzinger D., Pregenzer M. (1997). EEG-based discrimination between imagination of right and left hand movement. Electroencephalogr. Clin. Neurophysiol. 103, 642–65110.1016/S0013-4694(97)00080-1
    1. Pfurtscheller G., Neuper C., Guger C., Harkam W., Ramoser H., Schlögl A., et al. (2000). Current trends in Graz brain-computer interface (BCI) research. IEEE Trans. Rehabil. Eng. 8, 216–21910.1109/86.847821
    1. Pincus S. M. (1991). Approximate entropy as a measure of system complexity. Proc. Natl. Acad. Sci. U.S.A. 88, 2297–230110.1073/pnas.88.6.2297
    1. Richman J. S., Moorman J. R. (2000). Physiological time-series analysis using approximate entropy and sample entropy. Am. J. Physiol. Heart Circ. Physiol. 278, H2039–H2049
    1. Schlögl A., Keinrath C., Zimmermann D., Scherer R., Leeb R., Pfurtscheller G. (2007). A fully automated correction method of EOG artifacts in EEG recordings. Clin. Neurophysiol. 118, 98–10410.1016/j.clinph.2006.11.231
    1. Vapnik V. N. (1995). The Nature of Statistical Learning Theory. New York: Springer-Verlag
    1. Wolpaw J. R., Birbaumer N., McFarland D. J., Pfurtscheller G., Vaughan T. M. (2002). Brain-computer interfaces for communication and control. Clin. Neurophysiol. 113, 767–79110.1016/S1388-2457(02)00057-3
    1. Zhou W. D., Gotman J. (2009). Automatic removal of eye movement artifacts from the EEG using ICA and the dipole model. Prog. Nat. Sci. 19, 1165–117010.1016/j.pnsc.2008.11.013

Source: PubMed

Upcoming Clinical Trials

Subscribe