Abstract
High-performance feature engineering and classification algorithms are significantly important for motor imagery (MI) related brain-computer interface (BCI) applications. In this research, we offer a new composite kernel support vector machine (CKSVM) based method to extract significant common spatial pattern (CSP) feature components from multiple temporal-frequency segments in a data-driven manner. Furthermore, we firstly introduce a multiple kernel discriminant analysis (MKDA) method for MI EEG classification. The experimental results on BCI competition IV data set 2b clearly showed the effectiveness of our method outperforming other similar approaches in the literature.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Arvaneh, M., Guan, C.T., Ang, K.K., Quek, C.: Optimizing spatial filters by minimizing within-class dissimilarities in electroencephalogram-based brain-computer interface. IEEE Trans. Neural Netw. Learn. Syst. 24, 610–619 (2013)
Zhang, Y., Zhou, G.X., Jin, J., Wang, X.Y., Cichocki, A.: Optimizing spatial patterns with sparse filter bands for motor-imagery based brain-computer interface. J. Neurosci. Methods 255, 85–91 (2015)
Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., Muller, K.R.: Optimizing spatial filters for robust EEG single-trial analysis. IEEE Sig. Process. Mag. 25, 41–56 (2008)
Ang, K.K., Chin, Z.Y., Zhang, H.H., Guan, C.T.: Mutual information-based selection of optimal spatial-temporal patterns for single-trial EEG-based BCIs. Pattern Recogn. 45, 2137–2144 (2012)
Lemm, S., Blankertz, B., Curio, G., Muller, K.R.: Spatio-spectral filters for improving the classification of single trial EEG. IEEE Trans. Biomed. Eng. 52, 1541–1548 (2005)
Xu, P., Liu, T.J., Zhang, R., Zhang, Y.S., Yao, D.Z.: Using particle swarm to select frequency band and time interval for feature extraction of EEG based BCI. Biomed. Sig. Process. Control 10, 289–295 (2014)
Thomas, K.P., Guan, C.T., Lau, C.T., Vinod, A.P., Ang, K.K.: A new discriminative common spatial pattern method for motor imagery brain-computer interfaces. IEEE Trans. Biomed. Eng. 56, 2730–2733 (2009)
Nicolas-Alonso, L.F., Corralejo, R., Gomez-Pilar, J., Alvarez, D., Hornero, R.: Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain-computer interfaces. Neurocomputing 159, 186–196 (2015)
Cai, D., He, X.F., Han, J.W.: Speed up kernel discriminant analysis. Vldb J. 20, 21–33 (2011)
Yan, F., Kittler, J., Mikolajczyk, K., Tahir, A.: Non-sparse multiple kernel fisher discriminant analysis. J. Mach. Lear. Res. 13, 607–642 (2012)
Castro, E., Martinez-Ramon, M., Pearlson, G., Sui, J., Calhoun, V.D.: Characterization of groups using composite kernels and multi-source fMRI analysis data: application to schizophrenia. Neuroimage 58, 526–536 (2011)
Acknowledgments
This work was supported by the National Major Scientific Instruments and Equipment Development Program of China under Grant 2013YQ17052502, Nation Nature Science Foundation of China under Grant 61673105, Jiangsu Province Science and Technology Support Program of China under Grant BE2012740.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Miao, M., Zeng, H., Wang, A. (2017). Composite and Multiple Kernel Learning for Brain Computer Interface. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10635. Springer, Cham. https://doi.org/10.1007/978-3-319-70096-0_82
Download citation
DOI: https://doi.org/10.1007/978-3-319-70096-0_82
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70095-3
Online ISBN: 978-3-319-70096-0
eBook Packages: Computer ScienceComputer Science (R0)