Abstract
Brain–computer interfaces performing movement prediction are useful in a variety of application fields from telemanipulation to rehabilitation. However, current systems still struggle with a level of unreliability requiring improvement, so that the full potential of these systems can be used in the future. Here, we suggest to improve the performance and robustness of classification outcomes by postprocessing the raw score values with the history of previous classifications. For this several postprocessing methods that operate on the classification outcomes are investigated. 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 movement related cortical potentials 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. Finally, we use straightforward ensemble approaches to exemplify how the methods can be directly used in an application and how this can influence the overall movement prediction performance. 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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kornhuber HH, Deecke L. Hirnpotentialänderungen bei Willkürbewegungen und passiven Bewegungen des Menschen: Bereitschaftspotential und reafferente Potentiale. Pflüger’s Archiv für die gesamte Physiologie des Menschen und der Tiere 1965;284(1):1–17.
Libet B, Gleason CA, Wright EW, Pearl DK. Time of conscious intention to act in relation to onset of cerebral activity (readiness-potential) the unconscious initiation of a freely voluntary act. Brain 1983;106(3):623–42.
Fabiani M, Gratton G, Federmeier KD. Event-related brain potentials: methods, theory, and applications. In: Cacioppo J, Tassinary LG, Berntson GG, editors. Handbook of psychophysiology. 3rd ed. Cambridge [u.a]: Cambridge University Press; 2007. p. 85–119.
Blankertz B, Dornhege G, Lemm S, Krauledat M, Curio G, Müller K. The Berlin brain-computer interface: machine learning based detection of user specific brain states. J Univ Comput Sci 2006;12(6):581–607.
Bai O, Rathi V, Lin P, Huang D, Battapady H, Fei DY, Schneider L, Houdayer E, Chen X, Hallett M. Prediction of human voluntary movement before it occurs. Clin Neurophysiol 2011;122(2):364–72. http://www.sciencedirect.com/science/article/pii/S1388245710005699.
Ahmadian P, Cagnoni S, Ascari L. How capable is non-invasive EEG data of predicting the next movement? A mini review. Front Hum Neurosci 2013;7:124.
Kirchner EA, Albiez J, Seeland A, Jordan M, Kirchner F. Towards assistive robotics for home rehabilitation. In: Chimeno MF, Solé-Casals J, Fred A, Gamboa H, editors. Proceedings of the 6th International Conference on Biomedical Electronics and Devices (BIODEVICES-13). Barcelona: SciTePress; 2013. p. 168–77.
Kirchner EA, Tabie M. 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; 2013 March.
Folgheraiter M, Jordan M, Straube S, Seeland A, Kim SK, Kirchner EA. Measuring the improvement of the interaction comfort of a wearable exoskeleton. Int J Soc Robot 2012;4(3):285–302.
Folgheraiter M, Kirchner EA, Seeland A, Kim SK, Jordan M, Wöhrle H, Bongardt B, Schmidt S, Albiez J, Kirchner F. A multimodal brain-arm interface for operation of complex robotic systems and upper limb motor recovery. In: Vieira P, Fred A, Filipe J, Gamboa H, editors. Proceedings of the 4th International Conference on Biomedical Electronics and Devices (BIODEVICES-11). Rome: SciTePress; 2011. p. 150–62.
Seeland A, Woehrle H, Straube S, Kirchner EA. Online movement prediction in a robotic application scenario. In: 6th International IEEE EMBS Conference on Neural Engineering (NER). San Diego, CA: IEEE; 2013. p. 41–4
Lemm S, Schäfer C, Curio G. BCI competition 2003–data set III: probabilistic modeling of sensorimotor mu rhythms for classification of imaginary hand movements. IEEE Trans Biomed Eng 2004;51(6):1077–80. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=1300806.
Mohammadi R, Mahloojifar A, Coyle D. A combination of pre- and postprocessing techniques to enhance self-paced BCIs. Adv Hum Comput Interact 2012;2012:3:1–10. http://www.hindawi.com/journals/ahci/2012/185320/abs/.
Solis-Escalante T, Müller-Putz G, Pfurtscheller G. Overt foot movement detection in one single laplacian EEG derivation. J Neurosci Meth 2008;175(1):148–53.
Zhu X, Wu J, Cheng Y, Wang Y. GMM-based classification method for continuous prediction in brain-computer interface. In: Proceedings of the 18th International Conference on Pattern Recognition - ICPR ’06, Washington, DC: IEEE Computer Society; 2006. vol. 01. p. 1171–4. http://dx.doi.org/10.1109/ICPR.2006.610.
Vapnik VN. The nature of statistical learning theory. New York: Springer; 1995.
Tabie M, Kirchner EA. EMG onset detection – comparison of different methods for a movement prediction task based on EMG. In: Alvarez S, Solé-Casals J, Fred A, Gamboa H, editors. Proceedings of the 6th International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS-13). Barcelona: SciTePress; 2013. p. 242–7.
Krell MM, Straube S, Seeland A, Wöhrle H, Teiwes J, Metzen JH, Kirchner EA, Kirchner F. pySPACE - a signal processing and classification environment in Python. Front Neuroinf 2013;7(40). http://www.frontiersin.org/neuroinformatics/10.3389/fninf.2013.00040/abstract, https://github.com/pyspace.
Rivet B, Souloumiac A, Attina V, Gibert G. xDAWN algorithm to enhance evoked potentials: application to brain-computer interface. IEEE Trans Biomed Eng 2009;56(8):2035–43. http://dx.doi.org/10.1109/TBME.2009.2012869.
Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2011;2:27:1–27. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
Kubat M, Holte RC, Matwin S. Machine learning for the detection of oil spills in satellite radar images. Mach Learn 1998;30(2–3):195–215. http://dx.doi.org/10.1023/A:1007452223027.
Straube S, Krell MM. How to evaluate an agent’s behaviour to infrequent events? – reliable performance estimation insensitive to class distribution. Front Comput Neurosci 2014;8(43). http://www.frontiersin.org/computational_neuroscience/10.3389/fncom.2014.00043/abstract.
Acknowledgements
This work was supported by the German Bundesministerium für Wirtschaft und Technologie (BMWi, grant FKZ 50 RA 1012 and grant FKZ 50 RA 1011). The authors like to thank Marc Tabie for providing us with the evaluation data.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Straube, S., Feess, D., Seeland, A. (2015). Learning from the Past: Postprocessing of Classification Scores to Find a More Accurate and Earlier Movement Prediction. In: Londral, A., Encarnação, P., Rovira, J. (eds) Neurotechnology, Electronics, and Informatics. Springer Series in Computational Neuroscience, vol 13. Springer, Cham. https://doi.org/10.1007/978-3-319-15997-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-15997-3_7
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-15996-6
Online ISBN: 978-3-319-15997-3
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)