raxDAWN: Circumventing Overfitting of the Adaptive xDAWN

Mario Michael Krell, Hendrik Wöhrle, Anett Seeland

Abstract

The xDAWN algorithm is a well-established spatial filter which was developed to enhance the signal quality of brain-computer interfaces for the detection of event-related potentials. Recently, an adaptive version has been introduced. Here, we present an improved version that incorporates regularization to reduce the influence of noise and avoid overfitting. We show that regularization improves the performance significantly for up to 4%, when little data is available as it is the case when the brain-computer interface should be used without or with a very short prior calibration session.

References

  1. Blankertz, B., Lemm, S., Treder, M., Haufe, S., and Müller, K.-R. (2011). Single-Trial Analysis and Classification of ERP Components-a Tutorial. NeuroImage, 56(2):814-825.
  2. Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., and M üller, K.-R. (2008). Optimizing Spatial filters for Robust EEG Single-Trial Analysis. IEEE Signal Processing Magazine, 25(1):41-56.
  3. Buttfield, A., Ferrez, P. W., and Mil lán, J. d. R. (2006). Towards a robust BCI: error potentials and online learning. IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society, 14(2):164- 8.
  4. Chang, C.-C. and Lin, C.-J. (2011). LIBSVM. ACM Transactions on Intelligent Systems and Technology, 2(3):1-27.
  5. Ghaderi, F. and Kirchner, E. A. (2013). Periodic Spatial Filter for Single Trial Classification of Event Related Brain Activity. In Biomedical Engineering, Calgary,AB,Canada. ACTAPRESS.
  6. Golub, G. H. and Van Loan, C. F. (1996). Matrix computations. Johns Hopkins University Press.
  7. Kirchner, E. A., Kim, S. K., Straube, S., Seeland, A., W öhrle, H., Krell, M. M., Tabie, M., and Fahle, M. (2013). On the applicability of brain reading for predictive human-machine interfaces in robotics. PloS ONE, 8(12):e81732.
  8. Krell, M. M., Straube, S., Seeland, A., W öhrle, H., Teiwes, J., Metzen, J. H., Kirchner, E. A., and Kirchner, F. (2013). pySPACE a signal processing and classification environment in Python. Frontiers in Neuroinformatics, 7(40):1-11.
  9. Krusienski, D. J., Sellers, E. W., Cabestaing, F., Bayoudh, S., McFarland, D. J., Vaughan, T. M., and Wolpaw, J. R. (2006). A comparison of classification techniques for the P300 Speller. Journal of neural engineering, 3(4):299-305.
  10. Liao, X., Yao, D., Wu, D., and Li, C. (2007). Combining spatial filters for the classification of single-trial EEG in a finger movement task. IEEE transactions on biomedical engineering, 54(5):821-31.
  11. Lotte, F. and Guan, C. (2010). Spatially Regularized Common Spatial Patterns for EEG Classification. In2010 20th International Conference on Pattern Recognition (ICPR), pages 3712-3715.
  12. Mika, S. (2003). Kernel Fisher Discriminants. PhD thesis, Technische Universität Berlin.
  13. Mika, S., Rätsch, G., and Müller, K.-R. (2001). A mathematical programming approach to the kernel fisher algorithm. Advances in Neural Information Processing Systems 13 (NIPS 2000), pages 591-597.
  14. Rao, Y. and Principe, J. (2001). An RLS type algorithm for generalized eigendecomposition. In Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584), pages 263-272. IEEE.
  15. Rivet, B., Souloumiac, A., Attina, V., and Gibert, G. (2009). xDAWN algorithm to enhance evoked potentials: application to brain-computer interface. IEEE Transactions on Biomedical Engineering, 56(8):2035-2043.
  16. Samek, W., Vidaurre, C., M üller, K.-R., and Kawanabe, M. (2012). Stationary common spatial patterns for braincomputer interfacing. Journal of neural engineering, 9(2):026013.
  17. van Erp, J., Lotte, F., and Tangermann, M. (2012). BrainComputer Interfaces: Beyond Medical Applications. Computer, 45(4):26-34.
  18. Wöhrle, H., Krell, M. M., Straube, S., Kim, S. K., Kirchner, E. A., and Kirchner, F. (2015). An Adaptive Spatial Filter for User-Independent Single Trial Detection of Event-Related Potentials. IEEE transactions on biomedical engineering, PP(99):1.
  19. Wöhrle, H., Teiwes, J., Krell, M. M., Kirchner, E. A., and Kirchner, F. (2013). A Dataflow-based Mobile Brain Reading System on Chip with Supervised Online Calibration - For Usage without Acquisition of Training Data. In Proceedings of the International Congress on Neurotechnology, Electronics and Informatics, pages 46-53, Vilamoura, Portugal. SciTePress.
  20. Zander, T. O. and Kothe, C. (2011). Towards passive braincomputer interfaces: applying brain-computer interface technology to human-machine systems in general. Journal of Neural Engineering, 8(2):025005.
Download


Paper Citation


in Harvard Style

Michael Krell M., Wöhrle H. and Seeland A. (2015). raxDAWN: Circumventing Overfitting of the Adaptive xDAWN . In Proceedings of the 3rd International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX, ISBN 978-989-758-161-8, pages 68-75. DOI: 10.5220/0005657500680075


in Bibtex Style

@conference{neurotechnix15,
author={Mario Michael Krell and Hendrik Wöhrle and Anett Seeland},
title={raxDAWN: Circumventing Overfitting of the Adaptive xDAWN},
booktitle={Proceedings of the 3rd International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX,},
year={2015},
pages={68-75},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005657500680075},
isbn={978-989-758-161-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX,
TI - raxDAWN: Circumventing Overfitting of the Adaptive xDAWN
SN - 978-989-758-161-8
AU - Michael Krell M.
AU - Wöhrle H.
AU - Seeland A.
PY - 2015
SP - 68
EP - 75
DO - 10.5220/0005657500680075