Deep Belief Networks Based Brain Activity Classification Using EEG from Slow Cortical Potentials in Stroke

Abstract

An electroencephalogram (EEG) is an electrical activity which is recorded from the scalp over the sensorimotor cortex during vigilance or sleeping conditions of subjects.  It can be used to detect potential problems associated with brain disorders.  The aim of this study is assessing the clinical usefulness of EEG which is recorded from slow cortical potentials (SCP) training in stroke patients using Deep belief network (DBN) which has a greedy layer wise training using Restricted Boltzmann Machines based unsupervised weight and bias evaluation and neural network based supervised training. EEGs are recorded during eight SCP neurofeedback sessions from two stroke patients with a sampling rate of 256 Hz. All EEGs are filtered with a low pass filter. Hilbert-Huang Transform is applied to the trails and various numbers of Instinct Mode Functions (IMFs) are obtained. High order statistics and standard statistics are extracted from IMFs to create the dataset. The proposed DBN-based brain activity classification has discriminated positivity and negativity tasks in stroke patients and has achieved high rates of 90.30%, 96.58%, and 91.15%, for sensitivity, selectivity, and accuracy, respectively.

Keywords

• Deep Belief Networks,SCP,Slow Cortical potentials,Hilbert-Huang Transform,EEG

References

1. R. M. Stern, W. J. Ray, and K. S. Quigley, “Psychophysiological recording (2nd ed.),” Journal of Psychophysiology, vol. 15, no. 1. pp. 47–47, 2001.
2. S. Sanei and J. a. Chambers, EEG Signal Processing, vol. 1, no. 11. 2007.
3. T. Hinterberger, S. Schmidt, N. Neumann, J. Mellinger, B. Blankertz, G. Curio, and N. Birbaumer, “Brain-computer communication and slow cortical potentials,” IEEE Trans. Biomed. Eng., vol. 51, no. 6, pp. 1011–1018, 2004.
4. V. Bosch, A. Mecklinger, and A. D. Friederici, “Slow cortical potentials during retention of object, spatial, and verbal information,” Cogn. Brain Res., vol. 10, no. 3, pp. 219–237, 2001.
5. M. Pham, T. Hinterberger, N. Neumann, A. Kübler, N. Hofmayer, A. Grether, B. Wilhelm, J.-J. Vatine, and N. Birbaumer, “An auditory brain-computer interface based on the self-regulation of slow cortical potentials.,” Neurorehabil. Neural Repair, vol. 19, no. 3, pp. 206–218, 2005.
6. M. Devrim, T. Demiralp, A. Kurt, and I. Yücesir, “Slow cortical potential shifts modulate the sensory threshold in human visual system,” Neurosci. Lett., vol. 270, no. 1, pp. 17–20, 1999.
7. B. Kotchoubey, D. Schneider, H. Schleichert, U. Strehl, C. Uhlmann, V. Blankenhorn, W. Fr??scher, and N. Birbaumer, “Self-regulation of slow cortical potentials in epilepsy: A retrial with analysis of influencing factors,” Epilepsy Res., vol. 25, no. 3, pp. 269–276, 1996.
8. B. Kotchoubey, U. Strehl, C. Uhlmann, S. Holzapfel, M. König, W. Fröscher, V. Blankenhorn, and N. Birbaumer, “Modification of slow cortical potentials in patients with refractory epilepsy: a controlled outcome study.,” Epilepsia, vol. 42, no. 3, pp. 406–16, 2001.

9. M. Siniatchkin, E. Kirsch, P. Kropp, U. Stephani, and W. D. Gerber, “Slow cortical potentials in migraine families,” Cephalalgia, vol. 20, no. 10, pp. 881–892, 2000.
10. F. Schneider, T. Elbert, H. Heimann, a Welker, F. Stetter, R. Mattes, N. Birbaumer, and K. Mann, “Self-regulation of slow cortical potentials in psychiatric patients: alcohol dependency.,” Biofeedback Self. Regul., vol. 18, no. 1, pp. 23–32, 1993.
11. N. Ozdemir and E. Yildirim, “Patient specific seizure prediction system using hilbert spectrum and Bayesian networks classifiers,” Comput. Math. Methods Med., vol. 2014, 2014.
12. T. Ergenoglu, T. Demiralp, H. Beydagi, S. Karamürsel, M. Devrim, and N. Ermutlu, “Slow cortical potential shifts modulate P300 amplitude and topography in humans,” Neurosci. Lett., vol. 251, no. 1, pp. 61–64, 1998.
13. N. Birbaumer, T. Elbert, A. G. Canavan, and B. Rockstroh, “Slow potentials of the cerebral cortex and behavior.,” Physiol. Rev., vol. 70, no. 1, pp. 1–41, 1990.
14. B. Rockstroh, “Area-specific regulation of slow cortical potentials,” in Brain Dynamics, Springer, 1989, pp. 467–477.
15. W. Lutzenberger, L. E. Roberts, and N. Birbaumer, “Memory performance and area-specific self-regulation of slow cortical potentials: Dual-task interference,” Int. J. Psychophysiol., vol. 15, no. 3, pp. 217–226, 1993.
16. P. Khader, T. Schicke, B. Röder, and F. Rösler, “On the relationship between slow cortical potentials and BOLD signal changes in humans,” Int. J. Psychophysiol., vol. 67, no. 3, pp. 252–261, 2008.
17. U. Strehl, T. Trevorrow, R. Veit, T. Hinterberger, B. Kotchoubey, M. Erb, and N. Birbaumer, “Deactivation of brain areas during self-regulation of slow cortical potentials in seizure patients,” Appl. Psychophysiol. Biofeedback, vol. 31, no. 1, pp. 85–94, 2006.
18. Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, “Greedy Layer-Wise Training of Deep Networks,” Adv. Neural Inf. Process. Syst., vol. 19, no. 1, p. 153, 2007.
19. G. E. Hinton, S. Osindero, and Y.-W. Teh, “A fast learning algorithm for deep belief nets.,” Neural Comput., vol. 18, no. 7, pp. 1527–54, 2006.
20. H. a Song and S. Y. Lee, “Hierarchical Data Representation Model-Multi-layer NMF,” arXiv Prepr. arXiv1301.6316, pp. 1–4, 2013.
21. R. Ruben, E. Helena, H. Andreas, and et al., “Slow cortical potential training in stroke,” Germany, 2014.
22. R. J. Oweis and E. W. Abdulhay, “Seizure classification in EEG signals utilizing Hilbert-Huang transform.,” Biomed. Eng. Online, vol. 10, p. 38, 2011.
23. N. E. Huang and Z. Wu, “a Review on Hilbert-Huang Transform : Method and Its Applications,” October, vol. 46, no. 2007, pp. 1–23, 2008.
24. Y. Hou and H. Tian, “An automatic modulation recognition algorithm based on HHT and SVD,” in Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010, 2010, vol. 8, pp. 3577–3581.
25. M. Huang, P. Wu, Y. Liu, L. Bi, and H. Chen, “Application and contrast in brain-computer interface Between hilbert-huang transform and wavelet transform,” in Proceedings of the 9th International Conference for Young Computer Scientists, ICYCS 2008, 2008, pp. 1706–1710.
26. N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, N.-C. Yen, C. C. Tung, and H. H. Liu, “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” Proc. R. Soc. A Math. Phys. Eng. Sci., vol. 454, no. 1971, pp. 903–995, 1998.
27. G. Hinton, G. Hinton, T. Sejnowski, and T. Sejnowski, Learning and relearning in Boltzmann machines, vol. 1. 1986.
28. Y. Bengio and O. Delalleau, “Justifying and generalizing contrastive divergence,” Neural Comput., vol. 21, no. 6, pp. 1601–1621, 2009.
29. N. Allahverdi, G. Altan, and Y. Kutlu, “Diagnosis of Coronary Artery Disease Using Deep Belief Networks,” 2. Int. Conf. Eng. Nat. Sci., Nat. Sci., Sarajevo, Bosnia-Herzegovina, The Book of Abstracts, p.9, 2016
30. Y. Li, F. Yingle, L. Gu, and T. Qinye, “Sleep stage classification based on EEG hilbert-huang transform,” in 2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009, 2009, pp. 3676–3681