Abstract
Mutual information has been found to be a suitable measure of dependence among variables for input variable selection. For time-series prediction mutual information can quantify the average amount of information contained in the lagged measurements of a time series. Information quantities can be used for selecting the optimal time lag, τ, and embedding dimension, Δ, to optimize prediction accuracy. Times series modeling and prediction through traditional and computational intelligence techniques such as fuzzy and recurrent neural networks (FNNs and RNNs) have been promoted for EEG preprocessing and feature extraction to maximize signal separability to improve the performance of brain-computer interface (BCI) systems. This work shows that spatially disparate EEG channels have different optimal time embedding parameters which change and evolve depending on the class of motor imagery (movement imagination) being processed. To determine the optimal time embedding for each EEG channel (time-series) for each class an approach based on the estimation of partial mutual information (PMI) is employed. The PMI selected embedding parameters are used to embed the time series for each channel and class before self-organizing fuzzy neural network (SOFNN) based predictors are specialization to predict channel and class specific data in a prediction based signal processing framework, referred to as neural-time-seriesprediction- preprocessing (NTSPP). The results of eighteen subjects show that subject-, channel- and class-specific optimal time embedding parameter selection using PMI improves the NTSPP framework, increasing time-series separability. The chapter also shows how a range of traditional signal processing tools can be combined with multiple computational intelligence based approaches including the SOFNN and practical swarm optimization (PSO) to develop a more autonomous parameter optimization setup and ultimately a novel and more accurate BCI.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Wolpaw, J.R., Birbaumer, N., McFarland, D.J., Pfurtscheller, G., Vaughan, T.M.: Brain-computer interfaces for communication and control. J. Clinical Neurophysiology 113, 767–791 (2002)
Kubler, A., Kotchoubey, B., Kaiser, J., Wolpaw, J.R., Birbaumer, N.: Brain-Computer communication: unlocking the locked-in. Psychological Bulletin 127(3), 358–375 (2001)
Pfurtscheller, G., Guger, C., Muller, G., Krausz, G., Neuper, C.: Brain oscillations control hand orthosis in a tetraplegic. Neurosci. Lett. 292, 211–214 (2000)
Coyle, D., Satti, A., Stow, J., McCreadie, K., Carroll, A., McElligott, J.: Operating a Brain Computer Interface: Able Bodied vs. Physically Impaired Performance. In: Proc. of the Recent Advances in Assistive Technology & Engineering Conference (2011)
Stow, J., Coyle, D., Carroll, A., Satti, A., McElligott, J.: Achievable Brain Computer Communication through Short Intensive Motor Imagery Training despite Long Term Spinal Cord Injury. In: Proc. of the Annual IICN Registrar’s Prize in Neuroscience (2011)
Coyle, D., Carroll, A., Stow, J., McCann, A., Ally, A., McElligott, J.: Enabling Control in the Minimally Conscious State in a Single Session with a Three Channel BCI. In: Proc. of the 1st International DECODER Workshop (2012)
Prasad, G., Herman, P., Coyle, D., McDonough, S., Crosbie, J.: Applying a brain-computer interface to support motor imagery practice in people with stroke for upper limb recovery: a feasibility study. J. Neuroeng. Rehab. 7(60), 1–17 (2011)
Coyle, D., Garcia, J., Satti, A., McGinnity, T.M.: EEG-based Continuous Control of a Game using a 3 Channel Motor Imagery BCI. In: IEEE Symposium Series on Computa-tional Intelligence, pp. 88–93 (2011)
Enzinger, C., Ropele, S., Fazekas, F., Loitfelder, M., Gorani, F., Seifert, T., Reiter, G., Neuper, C., Pfurtscheller, G., Muller-Putz, G.: Brain motor system function in a patient with complete spinal cord injury following extensive brain–computer interface training. Exp. Brain Res. 190, 215–223 (2008)
Chatrian, G.E., Peterson, M., Lazarte, J.A.: The blocking of the rolandic wicket rhythm and some central changes related to movement. Electroencephalogr. Clin. Neurophysiol. 11, 497–510 (1959)
Pfurtscheller, G., Neuper, C., Flotzinger, D., Pregenzer, M.: EEG-based discrimination between imagination of right and left hand movement. Electroencephalography and Clinical Neurophysiology 113(6), 642–651 (1997)
Felzer, T., Freisleben, B.: Analyzing EEG signals using the probability estimated guarded neural classifier. IEEE Trans. on Neural Sys. and Rehab. Eng. 11(2), 361–371 (2003)
Anderson, C., Sijercic, Z.: Classification of EEG signals from four subjects during five mental tasks. In: Proc of the Conference on Eng. Applications in Neural Networks (EANN 1996), pp. 407–414 (1996)
Muller, K.-R., Anderson, C.W., Birch, G.E.: Linear and nonlinear methods for brain-computer interfaces. IEEE Trans. on Neural Systems and Rehab. Eng. 11(2), 165–169 (2003)
Schlogl, A., Flotzinger, D., Pfurtscheller, G.: Adaptive autoregressive modelling used for single-trial EEG classification. Biomedizinische Technik, Band 42, 162–167 (1997)
Forney, E., Anderson, C.W.: Classification of EEG during Imagined Mental Tasks by Forecasting with Elman Recurrent Neural Networks. In: Proceedings of the International Joint Conference on Neural Networks, pp. 2749–2755 (2011)
Pfurtscheller, G., Neuper, C., Schlogl, A., Lugger, K.: Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Transactions on Rehabilitation Engineering 6(3), 316–324 (1998)
Schloegl, A.: The electroencephalogram and the adaptive autoregressive model: theory and applications. Shaker Verlag, Aachen (2000)
Kohlmorgen, J., Müller, K.-R., Rittweger, J., Pawelzik, K.: Identification of non-stationary dynamics in physiological recordings. Biological Cybernetics 83(1), 73–84 (2000)
Haselsteiner, E., Pfurtscheller, G.: Using Time-Dependent NNs for EEG classification. IEEE Trans. on Rehab. Eng. 8(4), 457–462 (2000)
Coyle, D., Prasad, G., McGinnity, T.M.: A time-series prediction approach for feature extraction in a brain-computer interface. IEEE Transactions on Neural Systems and Rehabilitation Engineering 13(4), 461–467 (2005)
Coyle, D.: Neural network based auto association and time-series prediction for biosignal processing in brain-computer interfaces. IEEE Computational Intelligence Magazine 4(4), 47–59 (2009)
Coyle, D., Prasad, G., McGinnity, T.M.: Faster self-organizing fuzzy neural network training and a hyperparameter analysis for a brain-computer interface. IEEE Transactions on Systems, Man and Cybernetics (Part B) 39(6), 1458–1471 (2009)
Coyle, D., Prasad, G., McGinnity, T.M.: Improving the separability of multiple feature types for a brain-computer interface by neural time-series prediction preprocessing. Biomedical Signal Processing and Control, 196–204 (2010)
Sharma, A.: Seasonal to inter annual rainfall probabilistic forecasts for improved water supply management: part 1 – a strategy for system predictor identification. Journal of Hydrology 239, 232–239 (2000)
May, R.J., Maier, H.R., Dandy, G.C., Gayani Fernando, T.M.K.: Non-linear variable selection for artificial neural networks using partial mutual information. Environmental Modelling and Software 23, 1312–1326 (2008)
Blankertz, et al.: BCI Competition III and IV (2005), http://www.bbci.de/competition/
Blankertz, et al.: The BCI competition. III: Validating alternative approaches to actual BCI problems. IEEE Trans. Neural. Syst. Rehabil. Eng. 14, 153–159 (2006)
Schlogl, A., Lee, F., Birschof, H., Pfurtscheller, G.: Characterization of four-class motor imagery EEG data for the BCI-competition 2005. J. of Neural Engineering 2, L.14–L.22 (2005)
Schlogl, et al.: BCI-Competition IV (Dataset 2A and 2B) (2008), http://www.bbci.de/competition/iv/desc_2b.pdf , http://www.bbci.de/competition/iv/desc_2a.pdf
Leeb, R., Lee, F., Keinrath, C., Scherer, R., Bischof, H., Pfurtscheller, G.: Brain-computer communication: motivation, aim, and impact of exploring a virtual apartment. IEEE Transactions on Neural Systems and Rehabilitation Engineering 15, 473–482 (2007)
Schlogl, A., Keinrath, C., Zimmermann, D., Scherer, R., Leeb, R., Pfurtscheller, G.: A fully automated correction method for EOG artifacts in EEG recordings. Clin. Neuro-Phys. 118(1), 98–104 (2007)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)
Jang, J.S.R.: Neuro-Fuzzy & Soft Computing. Prentice-Hall (1997)
Leng, G.: Algorithmic Developments for Self-Organising Fuzzy Neural Networks. PhD Dissertation, University of Ulster (2003)
Prasad, G., McGinnity, T.M., Leng, G., Coyle, D.: On-line identification of self-organizing fuzzy neural networks for modelling time-varying complex systems. In: Plamen, et al. (eds.) Evolving Intelligent Systems, pp. 302–324. John Wiley, NY (2010)
Coyle, D., Prasad, G., McGinnity, T.M.: Faster Self-organising Fuzzy Neural Network Training and Improved Autonomy with Time-Delayed Synapses for Locally Recurrent Learning. In: Temel (ed.) System and Circuit Design for Biologically-Inspired Learning, pp. 156–183. IGI-Global (2010)
Ramouser, H., Muller-Gerking, J., Pfurtscheller, G.: Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans. on Rehab. Eng. 8(4), 441–446 (2000)
Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., Müller, K.R.: Optimizing spatial filters for robust EEG Analysis. IEEE Signal Processing Magazine, 41–56 (2008)
Satti, A., Coyle, D., Prasad, G.: Spatio-spectral & temporal parameter searching using class correlation analysis and particle swarm optimization for a brain computer interface. In: Proc. of the 2009 IEEE Systems, Man and Cybernetics Conference, pp. 1731–1735 (2009)
Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings IEEE International Conference on Neural Networks, vol. 1, pp. 1942–1948 (1995)
Herman, P., Prasad, G., McGinnity, T.M., Coyle, D.: Comparative analysis of spectral approaches to feature extraction for EEG-based motor imagery classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering 16(4), 317–326 (2008)
Coyle, D., Prasad, G., McGinnity, T.M.: A time-frequency approach to feature extraction for a brain-computer interface with a comparative analysis of performance measures. EURASIP JASP, Trends in Brain-Computer Interfaces (special issue) 19, 3141–3151 (2005)
Coyle, D., Prasad, G., McGinnity, T.M., Herman, P.: Estimating the predictability of EEG recorded over the motor cortex using information theoretic functionals. In: Proceedings of the 2nd International Brain-Computer Interface Workshop and Training Course, Biomedizinische Technik, pp. 43–44 (2004)
Fraser, A.M.: Information and Entropy in Strange Attractors. IEEE Trans. on Info. Theory. 35(2), 245–262 (1989)
Palus, M., Pecen, L., Pivka, D.: Estimating predictability: The redundancy and surrogate data method. Neural Network World 5(4), 537–552 (1995)
Palus, M.: Testing for nonlinearity using redundancies: Quantitative and qualitative aspects. Physica D, 186–205 (1995)
Williams, G.P.: Chaos Theory Tamed. Taylor and Francis, London (1997)
Shannon, C.E., Weaver, W.: The mathematical theory of communication. University of Illinois Press (1963)
Scott, D.W.: Multivariate Density Estimation: Theory, Practice and Visualisation. John Wiley and Sons, New York (1992)
Chow, T.W.S., Huang, D.: Estimating optimal feature subsets using efficient estimation of high-dimensional mutual information. IEEE Transactions on Neural Networks 16(1), 213–224 (2005)
Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Chapman and Hall, London (1986)
Davies, L., Gather, U.: The identification of multiple outliers. Journal of the American Statistical Association 88(423), 782–792 (1993)
Zar, J.H.: Biostatistical Analysis, 4th edn., pp. 255–259. Upper Saddle River, New-Jersey (1999)
Greene, J., D’Oliveira, M.: Learning to use statistical tests in psychology. Open University Press (1982)
Satti, A., Guan, C., Coyle, D., Prasad, G.: A covariate shift minimisation method to alleviate non-stationarity effects for an adaptive brain-computer interface. In: 20th International Conference Pattern Recognition, August 23-26, pp. 105–108 (2010)
Krusienski, D.J., Grosse-Wentrup, M., Galan, F., Coyle, D., Miller, K.J., Forney, E., Anderson, C.W.: Critical Issues in Brain Computer Interface Research. Journal of Neural Engineering 8, 025002 (8pp) (2011)
Coyle, D., McGinnity, T.M., Prasad, G.: A multi-class brain-computer interface with SOFNN-based prediction preprocessing. In: IEEE World Congress on Computational Intelligence, pp. 3695–3702 (2008)
Coyle, D., Prasad, G., McGinnity, T.M.: Improving information transfer rates of a brain-computer interface by self-organising fuzzy neural network-based multi-step-ahead time-series prediction. In: Proceedings of the 3rd IEEE Systems, Man and Cybernetics (UK&RI Chapter) Conference, pp. 230–235 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Coyle, D. (2013). Channel and Class Dependent Time-Series Embedding Using Partial Mutual Information Improves Sensorimotor Rhythm Based Brain-Computer Interfaces. In: Pedrycz, W., Chen, SM. (eds) Time Series Analysis, Modeling and Applications. Intelligent Systems Reference Library, vol 47. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33439-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-33439-9_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33438-2
Online ISBN: 978-3-642-33439-9
eBook Packages: EngineeringEngineering (R0)