Advertisement

Brain Computer Interface Development Based on Recurrent Neural Networks and ANFIS Systems

  • Emanuel Morales-Flores
  • Juan Manuel Ramírez-Cortés
  • Pilar Gómez-Gil
  • Vicente Alarcón-Aquino
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 294)

Abstract

Brain Computer Interfaces (BCI) is the generic denomination of systems aiming to establish communication between a human being and an automated system, based on the electric brain signals detected through a variety of modalities. Among these, electroencephalographic signals (EEG) have received considerable attention due to several factors arising on practical scenarios, such as noninvasiveness, portability, and relative cost, without lost on accuracy and generalization. In this chapter we discuss the characteristics of a typical phenomenon associated to motor imagery and mental tasks experiments, known as event related synchronization and desynchronization (ERD/ERS), as well as its energy distribution in the time-frequency space. The typical behavior of ERD/ERS phenomenon has led proposal of different approaches oriented to the solution of the identification problem. In this work, an architecture based on adaptive neuro-fuzzy inference systems (ANFIS) assembled to a recurrent neural network, applied to the problem of mental tasks temporal classification, is presented. The electroencephalographic signals (EEG) are pre-processed through band-pass filtering in order to separate the set of energy signals in alpha and beta bands. The energy in each band is represented by fuzzy sets obtained through an ANFIS system, and the temporal sequence corresponding to the combination to be detected, associated to the specific mental task, is entered into a recurrent neural network. Experimentation using EEG signals corresponding to mental tasks exercises, obtained from a database available to the international community for research purposes, is reported. Two recurrent neural networks are used for comparison purposes: Elman network, and a fully connected recurrent neural network (FCRNN) trained by RTRL-EKF (real time recurrent learning – extended Kalman filter). A classification rate of 88.12 % in average was obtained through the FCRNN during the generalization stage.

Keywords

Independent Component Analysis Motor Imagery Recurrent Neural Network Adaptive Neuro Fuzzy Inference System Mental Task 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Brunner, P., Bianchi, L., Guger, C., Cincotti, F., Schalk, G.: Current trends in hardware and software for brain–computer interfaces (BCIs). Journal of Neural Engineering 8, 025001 (2011)CrossRefGoogle Scholar
  2. 2.
    Bashashati, M., Fatourechi, R., Ward, K., Birch, G.E.: A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals. Journal of Neural Engineering 4(2), R32–R57 (2007)Google Scholar
  3. 3.
    Berger, T.W., Chapin, J.K., Gerhardt, G.A., McFarland, D.J., Principe, J.C., Soussou, W.V., Taylor, D.M., Tresco, P.A.: WTEC Panel Report on International Assessment of Research and Development in Brain-Computer Interfaces. World Technology Evaluation Center, Inc. (2007), http://www.wtec.org/bci/BCI-finalreport-26Aug2008-lowres.pdf
  4. 4.
    Hosni, S.M., Gadallah, M.E., Bahgat, S.F., AbdelWahab, M.S.: Classification of EEG signals using different feature extraction techniques for mental-task BCI. In: 2007 International Conference on Computer Engineering Systems, pp. 220–226 (2007)Google Scholar
  5. 5.
    Neuper, C., Scherer, R., Wriessnegger, S., Pfurtscheller, G.: Motor imagery and action observation: Modulation of sensorimotor brain rhythms during mental control of a brain–computer interface. Clinical Neurophysiology 120(2), 239–247 (2009)CrossRefGoogle Scholar
  6. 6.
    Solis-Escalante, T., Muller-Putz, G., Brunner, C., Kaiser, V., Pfurtscheller, G.: Analysis of sensorimotor rhythms for the implementation of a brain switch for healthy subjects. Biomedical Signal Processing and Control 5(1), 15–20 (2010)CrossRefGoogle Scholar
  7. 7.
    McFarland, D.J., Sarnacki, W.A., Townsend, G., Vaughan, T., Wolpaw, J.R.: The P-300-based brain–computer interface (BCI): Effects of stimulus rate. Clinical Neurophysiology 122(4), 731–737 (2011)CrossRefGoogle Scholar
  8. 8.
    Ramirez-Cortes, J.M., Alarcon-Aquino, V., Rosas-Cholula, G., Gomez-Gil, P., Escamilla-Ambrosio, J.: Anfis-Based P300 Rhythm Detection Using Wavelet Feature Extraction on Blind Source Separated EEG Signals. In: Ao, S., Amouzegar, M., Rieger, B.B. (eds.) Intelligent Automation and Systems Engineering, ch. 27. LNEE, vol. 103, pp. 353–365. Springer, New York (2011)CrossRefGoogle Scholar
  9. 9.
    Shyu, K.K., Lee, P.L., Liu, Y.J., Sie, J.J.: Dual-frequency steady-state visual evoked potential for brain computer interface. Neuroscience Letters 483(1), 28–31 (2010)CrossRefGoogle Scholar
  10. 10.
    Horki, P., Solis-Escalante, T., Neuper, C., Muller-Putz, G.R.: Hybrid Motor Imagery and Steady-state Visual Evoked Potential Based BCI for Artificial Arm Control. In: Proceedings of the First Tools for Brain Computer Interaction Workshop, Graz, Austria, p. 46 (2010)Google Scholar
  11. 11.
    Wang, H., Li, C.S., Li, Y.G.: Brain-computer interface design based on slow cortical potentials using Matlab/Simulink. In: Proceedings of the International Conference on Mechatronics and Automation, Changchun, China, pp. 1044–1048 (2009)Google Scholar
  12. 12.
    Khare, V., Santhosh, J., Anand, S., Bhatia, M.: Performance comparison of three artificial neural network methods for classification of electroencephalograph signals of five mental tasks. J. Biomedical Science and Engineering 3, 200–205 (2010)Google Scholar
  13. 13.
    Pfurtscheller, G.: Spatiotemporal ERD/ERS patterns during voluntary movement and motor imagery. Supplements to Clinical Neurophysiology 53, 196–198 (2000)CrossRefGoogle Scholar
  14. 14.
    Chiappa, S., Bengio, S.: HMM and IOHMM modeling of EEG rhythms for asynchronous BCI systems. In: European Symposium on Artificial Neural Networks, ESANN (2004)Google Scholar
  15. 15.
    Millan, J.R., Mouriño, J.: Asynchronous BCI and local neural classifiers: an overview of the adaptive brain interface project. IEEE Transactions on Neural Systems and Rehabilitation Engineering 11, 159–161 (2003)CrossRefGoogle Scholar
  16. 16.
    Pfurtscheller, G., Neuper, C., Schlogl, A., Lugger, K.: Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans. Rehabil. Eng. 6, 316–325 (1998)CrossRefGoogle Scholar
  17. 17.
    Pfurtscheller, G., Neuper, C., Flotzinger, D., Pregenzer, M.: EEG-based discrimination between imagination of right and left hand movement. Electroenceph. Clin. Neurophysiology 103, 642–651 (1997)CrossRefGoogle Scholar
  18. 18.
    Wang, T., He, B.: An efficient rhythmic component expression and weighting synthesis strategy for classifying motor imagery EEG in a brain–computer interface. J. Neural Eng. 1, 1–7 (2004)CrossRefGoogle Scholar
  19. 19.
    Wang, T., Denga, J., He, B.: Classifying EEG-based motor imagery tasks by means of time-frequency synthesized spatial patterns. Clinical Neurophysiology 115, 2744–2753 (2004)CrossRefGoogle Scholar
  20. 20.
    Durka, P.: Matching Pursuit and Unification in EEG Analysis. Artech House, Inc., Norwood (2007)Google Scholar
  21. 21.
    Wang, J., Xu, G., Wang, L., Zhang, H.: Feature extraction of brain-computer interface based on improved multivariate adaptive autoregressive models. In: Proceedings of the 3rd International Conference on Biomedical Engineering and Informatics (BMEI), Yantai, China, pp. 895–898 (2010)Google Scholar
  22. 22.
    Kołodziej, M., Majkowski, A., Rak, R.J.: A New Method of EEG Classification for BCI with Feature Extraction Based on Higher Order Statistics of Wavelet Components and Selection with Genetic Algorithms. In: Dobnikar, A., Lotrič, U., Šter, B. (eds.) ICANNGA 2011, Part I. LNCS, vol. 6593, pp. 280–289. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  23. 23.
    Vijean, V., Hariharan, M., Saidatul, A., Yaacob, S.: Mental tasks classifications using S-transform for BCI applications. In: Proceedings of the IEEE Conference on Sustainable Utilization and Development in Engineering and Technology, Semenyih, Malaysia, pp. 69–73 (2011)Google Scholar
  24. 24.
    Lotte, F.: The use of fuzzy inference systems for classification in EEG-based brain-computer interfaces. In: Proceedings of the 3rd International Brain-Computer Interfaces Workshop and Training Course, Graz, Austria (2006)Google Scholar
  25. 25.
    Zhang, L., He, W., He, C., Wang, P.: Improving mental task classification by adding high frequency band information. Journal of Medical Systems 34(1), 51–60 (2010)CrossRefGoogle Scholar
  26. 26.
    Palaniappan, R.: Utilizing Gamma band to improve mental task based brain-computer interface design. IEEE Transactions on Neural Systems and Rehabilitation Engineering 14(3), 299–303 (2006)CrossRefGoogle Scholar
  27. 27.
    Park, C., Looney, D., Kidmose, P., Ungstrup, M., Mandic, D.P.: Time-frequency analysis of EEG asymmetry using bivariate Empirical Mode Decomposition. IEEE Transactions on Neural Systems and Rehabilitation Engineering 19(4), 366–373 (2011)CrossRefGoogle Scholar
  28. 28.
    Kousarrizi, M.R.N., Ghanbari, A.A., Teshnehlab, M., Shorehdeli, M.A., Gharaviri, A.: Feature extraction and classification of EEG signals using Wavelet Transform, SVM and artificial neural networks for brain computer interfaces. In: Proceedings of the International Joint Conference on Bioinformatics, Systems Biology and Intelligent Computing, Shanghai, China, pp. 352–355 (2009)Google Scholar
  29. 29.
    Forney, E.M., 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, San Jose, California, USA, pp. 2749–2755 (2011)Google Scholar
  30. 30.
    Coyle, D., McGinnity, T.M., Prasad, G.: Improving the separability of multiple EEG features for a BCI by neural-time-series-prediction-preprocessing. Biomedical Signal Processing and Control 5(3), 196–204 (2010)CrossRefGoogle Scholar
  31. 31.
    Chang, F., Chang, Y.: Adaptive neuro-fuzzy inference system for prediction of water level in reservoir. Advances in Water Resources 29(1), 1–10 (2006)CrossRefGoogle Scholar
  32. 32.
    Subasi, A.: Application of adaptive neuro-fuzzy inference system for epileptic seizure detection using wavelet feature extraction. Computers in Biology and Medicine 37(2), 227–244 (2007)CrossRefGoogle Scholar
  33. 33.
    Jang, J.S.R.: ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems Man and Cybernetics 23(3), 665–685 (1993)CrossRefGoogle Scholar
  34. 34.
    Mandic, D., Chambers, J.: Recurrent neural networks for prediction. John Wiley & Sons, Chinchester (2001)CrossRefGoogle Scholar
  35. 35.
    Fuchs, E., Gruber, C., Reitmaier, T., Sick, B.: Processing short-term and long-term information with a combination of polynomial approximation techniques and time-delay neural networks. IEEE Transactions on Neural Networks 20(9), 1450–1462 (2009)CrossRefGoogle Scholar
  36. 36.
    Gomez-Gil, P.: Long term prediction, chaos and artificial neural networks. Where is the meeting point? Engineering Letters 15(1), 1–5 (2007)Google Scholar
  37. 37.
    Skarda, C., Freeman, W.: How brains make chaos in order to make sense of the world. Behavioral and Brain Sciences 10, 161–195 (1987)CrossRefGoogle Scholar
  38. 38.
    Jordan, M.: Serial order: a parallel distributed processing approach. Technical Report TR-8604. UC San Diego Institute for Cognitive Science, San Diego (1986)Google Scholar
  39. 39.
    Elman, J.: Finding structure in time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
  40. 40.
    Werbos, P.: Backpropagation through time: what it does and how to do it. Proceedings IEEE 74(10), 1550–1560 (1990)CrossRefGoogle Scholar
  41. 41.
    Williams, R., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1, 270–280 (1989)CrossRefGoogle Scholar
  42. 42.
    Graves, A., Fernandez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369–376. ACM, Pittsburgh (2006), doi:10.1145/1143844.1143891Google Scholar
  43. 43.
    Williams, R.: Some observations on the use of the extended Kalman Filter as a recurrent network learning algorithm. Technical Report NU-CCS-92-1, Northeastern University, Boston, MA (1992)Google Scholar
  44. 44.
    Haykin, S.: Neural Networks, 2nd edn. Prentice Hall, Upper Saddle River (1999)zbMATHGoogle Scholar
  45. 45.
    Cernansky, M.: Matlab functions for training recurrent neural networks RTRL-EKF (2008), http://www2.fiit.stuba.sk/~cernans/main/download.html (accessed January 2009)
  46. 46.
    Werbos, P.: Beyond regression: new tools for prediction and analysis of the behavioral sciences. PhD Thesis, Cambridge, MA (1974)Google Scholar
  47. 47.
    Rumelhart, D., Hinton, E., Williams, R.: Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. I. Bradford Books, Cambridge (1986)Google Scholar
  48. 48.
    Čerňanský, M.: Training Recurrent Neural Network Using Multistream Extended Kalman Filter on Multicore Processor and Cuda Enabled Graphic Processor Unit. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds.) ICANN 2009, Part I. LNCS, vol. 5768, pp. 381–390. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  49. 49.
    Ralaivola, L., d’Alché-Buc, F.: Nonlinear Time Series Filtering, Smoothing and Learning using the Kernel Kalman Filter. Technical Report, Universite Pierre et Marie Curie, Paris France (2004)Google Scholar
  50. 50.
    Alanis, A., Sanchez, E., Loukianov, A.: Discrete-time adaptive backstepping nonlinear control via high-order neural networks. IEEE Transactions on Neural Networks 18(4), 1185–1195 (2007)CrossRefGoogle Scholar
  51. 51.
    Prokhorov, D.: Toyota prius hev neurocontrol and diagnostics. Neural Networks 21, 458–465 (2008)CrossRefGoogle Scholar
  52. 52.
    García-Pedrero, A.: Arquitectura neuronal apoyada en señales reconstruidas con wavelets para predicción de series de tiempo caóticas, M. Sc. Thesis, INAOE, Tonantzintla, Puebla (2009) (in spanish)Google Scholar
  53. 53.
    Doka, K.: Handbook of brain theory and neural networks, 2nd edn. MIT Press, Cambridge (2002)Google Scholar
  54. 54.
    Kachenoura, A., Albera, L., Senhadji, L., Comon, P.: ICA: A Potential Tool for BCI Systems. IEEE Signal Processing Magazine, 57–68 (January 2008)Google Scholar
  55. 55.
    Keralapura, M., Pourfathi, M., Sirkeci-Mergen, B.: Impact of Contrast Functions in Fast-ICA on Twin ECG Separation. IAENG International Journal of Computer Science 38(1), 38–47 (2011)Google Scholar
  56. 56.
    Keirn, Z.A., Aunon, J.I.: A new mode of communication between man and his surroundings. IEEE Trans. Biomed. Eng. 37(12), 1209–1214 (1990)CrossRefGoogle Scholar
  57. 57.
    Cawley, G.C.: Leave-One-Out Cross-Validation Based Model Selection Criteria for Weighted LS-SVMs. In: Proceedings of the International Joint Conference on Neural Networks, Vancouver, Canada, pp. 1661–1668 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Emanuel Morales-Flores
    • 1
  • Juan Manuel Ramírez-Cortés
    • 1
  • Pilar Gómez-Gil
    • 2
  • Vicente Alarcón-Aquino
    • 3
  1. 1.Department of ElectronicsNational Institute of Astrophysics, Optics and ElectronicsTonantzintlaMexico
  2. 2.Department of Computer ScienceNational Institute of Astrophysics, Optics and ElectronicsTonantzintlaMexico
  3. 3.Department of ElectronicsUniversity of the AmericasCholulaMexico

Personalised recommendations