Striving for Better and Earlier Movement Prediction by Postprocessing of Classification Scores

Sirko Straube, Anett Seeland, David Feess

Abstract

Brain-computer interfaces that enable movement prediction are useful for many application fields from telemanipulation to rehabilitation. Current systems still struggle with a level of unreliability that requires improvement. Here, we investigate several postprocessing methods that operate on the classification outcomes. In particular, the data was classified after preprocessing using a support vector machine (SVM). The output of the SVM, i.e. the raw score values, were postprocessed using previously obtained scores to account for trends in the classification result. The respective methods differ in the way the transformation is performed. The idea is to use trends, like the rise of the score values approaching an upcoming movement, to yield a better prediction in terms of detection accuracy and/or an earlier time point. We present results from different subjects where upcoming voluntary movements of the right arm were predicted using the lateralized readiness potential from the EEG. The results illustrate that better and earlier predictions are indeed possible with the suggested methods. However, the best postprocessing method was rather subject-specific. Depending on the requirements of the application at hand, postprocessing the classification scores as suggested here can be used to find the best compromise between prediction accuracy and time point.

References

  1. Ahmadian, P., Cagnoni, S., and Ascari, L. (2013). How capable is non-invasive EEG data of predicting the next movement? A mini review. Frontiers in Human Neuroscience, 7:124.
  2. Bai, O., Rathi, V., Lin, P., Huang, D., Battapady, H., Fei, D.-Y., Schneider, L., Houdayer, E., Chen, X., and Hallett, M. (2011). Prediction of human voluntary movement before it occurs. Clinical Neurophysiology, 122(2):364-372.
  3. Blankertz, B., Dornhege, G., Lemm, S., Krauledat, M., Curio, G., and Müller, K. (2006). The Berlin BrainComputer Interface: Machine learning based detection of user specific brain states. Journal of Universal Computer Science, 12(6):581-607.
  4. Chang, C.-C. and Lin, C.-J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1-27:27. Software available at http://www.csie.ntu.edu.tw/ cjlin/libsvm.
  5. Fabiani, M., Gratton, G., and Federmeier, K. D. (2007). Event-related brain potentials: Methods, theory, and applications. In Cacioppo, J., Tassinary, L. G., and Berntson, G. G., editors, Handbook of Psychophysiology, pages 85-119. Cambridege University Press, Cambridge [u.a], 3rd edition.
  6. Folgheraiter, M., Jordan, M., Straube, S., Seeland, A., Kim, S. K., and Kirchner, E. A. (2012). Measuring the improvement of the interaction comfort of a wearable exoskeleton. International Journal of Social Robotics, 4(3):285-302.
  7. Kirchner, E. A., Albiez, J., Seeland, A., Jordan, M., and Kirchner, F. (2013). Towards assistive robotics for home rehabilitation. In Chimeno, M. F., Solé-Casals, J., Fred, A., and Gamboa, H., editors, In Proceedings of the 6th International Conference on Biomedical Electronics and Devices (BIODEVICES-13), pages 168-177, Barcelona. SciTePress.
  8. Kirchner, E. A. and Tabie, M. (2013). Closing the gap: combined EEG and EMG analysis for early movement prediction in exoskeleton based rehabilitation. In Proceedings of the 4th European Conference on Technically Assisted Rehabilitation - TAR 2013.
  9. Kornhuber, H. H. and Deecke, L. (1965). Hirnpotentialänderungen bei Willkürbewegungen und passiven Bewegungen des Menschen: Bereitschaftspotential und reafferente Potentiale. Pflüger's Archiv für die gesamte Physiologie des Menschen und der Tiere, 284(1):1-17.
  10. Kubat, M., Holte, R. C., and Matwin, S. (1998). Machine learning for the detection of oil spills in satellite radar images. Machine Learning, 30(2-3):195-215.
  11. Lemm, S., Schäfer, C., and Curio, G. (2004). BCI competition 2003-data set III: probabilistic modeling of sensorimotor mu rhythms for classification of imaginary hand movements. IEEE Transactions on Biomedical Engineering, 51(6):1077-80.
  12. Libet, B., Gleason, C. A., Wright, E. W., and Pearl, D. K. (1983). Time of conscious intention to act in relation to onset of cerebral activity (readiness-potential) the unconscious initiation of a freely voluntary act. Brain, 106(3):623-642.
  13. Mohammadi, R., Mahloojifar, A., and Coyle, D. (2012). A combination of pre- and postprocessing techniques to enhance self-paced BCIs. Advances in HumanComputer Interaction, 2012:3:1-3:10.
  14. 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.
  15. Solis-Escalante, T., Müller-Putz, G., and Pfurtscheller, G. (2008). Overt foot movement detection in one single laplacian EEG derivation. Journal of Neuroscience Methods, 175(1):148-153.
  16. Tabie, M. and Kirchner, E. A. (2013). EMG onset detection - comparison of different methods for a movement prediction task based on EMG. In Alvarez, S., Solé-Casals, J., Fred, A., and Gamboa, H., editors, In Proceedings of the 6th International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS-13), pages 242-247, Barcelona. SciTePress.
  17. Vapnik, V. N. (1995). The nature of statistical learning theory. Springer New York, Inc., New York, NY, USA.
  18. Zhu, X., Wu, J., Cheng, Y., and Wang, Y. (2006). GMMbased classification method for continuous prediction in brain-computer interface. In Proceedings of the 18th International Conference on Pattern Recognition - Volume 01, ICPR 7806, pages 1171-1174, Washington, DC, USA. IEEE Computer Society.
Download


Paper Citation


in Harvard Style

Straube S., Seeland A. and Feess D. (2013). Striving for Better and Earlier Movement Prediction by Postprocessing of Classification Scores . In Proceedings of the International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX, ISBN 978-989-8565-80-8, pages 13-20. DOI: 10.5220/0004632600130020


in Bibtex Style

@conference{neurotechnix13,
author={Sirko Straube and Anett Seeland and David Feess},
title={Striving for Better and Earlier Movement Prediction by Postprocessing of Classification Scores},
booktitle={Proceedings of the International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX,},
year={2013},
pages={13-20},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004632600130020},
isbn={978-989-8565-80-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Congress on Neurotechnology, Electronics and Informatics - Volume 1: NEUROTECHNIX,
TI - Striving for Better and Earlier Movement Prediction by Postprocessing of Classification Scores
SN - 978-989-8565-80-8
AU - Straube S.
AU - Seeland A.
AU - Feess D.
PY - 2013
SP - 13
EP - 20
DO - 10.5220/0004632600130020