The EMD-CCA with Neural Network Classifier to Recognize the SSVEP Frequency

Sadeghi, Sahar; Maleki, Ali

doi:10.22041/ijbme.2018.63800.1219

Document Type : Full Research Paper

Authors

Sahar Sadeghi ¹
Ali Maleki ²

¹ PhD Student, Biomedical Engineering Department, Semnan University, Semnan, Iran

² Assistant Professor, Biomedical Engineering Department, Semnan University, Semnan, Iran

https://doi.org/10.22041/ijbme.2018.63800.1219

Abstract

To increase the number of stimulation frequencies in the Steady-state visual evoked potential (SSVEP)-based brain-computer interface, we are forced to broaden the frequency range due to the frequency resolution restriction. This will enter frequencies with harmonic relation into the stimulation frequency range and lead to increase in frequency recognition error. In this paper, a three-stage method including the empirical mode decomposition (EMD), the canonical correlation analysis (CCA) and neural network classifier has been proposed that can solve the recognition error problem for wide frequency range including frequencies with harmonic relation. Visual stimulus ranged from 6-16 Hz with an interval of 0.5 have been generated using Matlab and the psychophysics toolbox. The SSVEP signal was recorded from ten subjects via one electrode placed at Oz. After extracting the intrinsic mode functions (IMFs) of the signal by EMD and reconstructing the combined signals, the CCA has been applied. Two features including the detected frequency and the correlation value in this frequency have been extracted and they were given to the neural network classifier. For eight-second time window, the average accuracy of the CCA for N=1 was 78% and for N=2 was 74%, while the corresponding values of the proposed method were 82% and 77% respectively. For four-second time window, the accuracy was increased from 78% to 83% for N=1 and it was increased from 78% to 80% for N=2. N is the number of harmonics in the generation of the reference signal in the CCA. For wide frequency range, the proposed method has been able to improve the frequency recognition accuracy compared to the standard CCA method. according to this, by broadening the stimulation frequency range, the possibility of increasing the number of frequency options and thus increasing the information transfer rate are provided.

Keywords

Main Subjects

Human Computer Interaction / HCI

References

[1] HJ. Hwang, DH. Kim, CH. Han, CH. Im, “A new dual-frequency stimulation method to increase the number of visual stimuli for multi-class SSVEP-based brain–computer interface (BCI),” brain research, vol 1515, pp. 66-77, Jun. 2013.

[2] M. J. Cui, W. Wong, S. Mann, “Time-frequency analysis of visual evoked potentials by means of matching pursuit with chirplet atoms,” Proc. IEEE Conference on Engineering in Medicine and Biology Society (IEMBS'04), San Francisco, CA, USA, Vol. 1, pp. 267-270, Sep. 2004.

[3] CM. Wong, B. Wang, F. Wan, PU. Mak, PI. Mak, MI. Vai, “A solution to harmonic frequency problem: frequency and phase coding-based brain-computer interface,” Proc. IEEE Conference on Neural Networks (IJCNN), pp. 2119-2126, Jul. 2011.

[4] L. Huang, X. Huang, YT. Wang, Y. Wang, TP. Jung, CK. Cheng, “Empirical mode decomposition improves detection of SSVEP,” Proc. IEEE Conference on Engineering in Medicine and Biology Society (EMBC), pp. 3901-3904, Jul. 2013.

[5] CM. Ng, MI. Vai, “Detection of attention-to-rest transition from EEG signals with the help of empirical mode decomposition,” Intelligent Computing and Information Science, pp. 66-71, 2011

[6] X. Ruan, K. Xue, M. Li, “Feature extraction of SSVEP-based brain-computer interface with ICA and HHT method,” Proc. 11th World Congress on Intelligent Control and Automation (WCICA), pp. 2418-2423, Jun. 2014.

[7] CH. Wu, HC. Chang, PL. Lee, KS. Li, JJ. Sie, CW. Sun, et al, “Frequency recognition in an SSVEP-based brain computer interface using empirical mode decomposition and refined generalized zero-crossing,” Journal of neuroscience methods, vol. 196, no. 1, pp. 170-81, Mar. 2011.

[8] M. Huang, P. Wu, Y. Liu, L. Bi, H. Chen, “Application and contrast in brain-computer interface Between hilbert-huang transform and wavelet transform,” Proc. IEEE Conference on Young Computer Scientists (ICYCS), pp. 1706-1710, Nov. 2008.

[9] M. Nakanishi, Y. Wang, X. Chen, Y.T. Wang, X. Gao, and T.P. Jung. "Enhancing Detection of SSVEPs for a high-speed brain speller using task-related component analysis." IEEE Transactions on Biomedical Engineering, Vol. 65, No. 1, pp. 104-112, 2018.

[10] G. Xiaorong, D. Xu, M. Cheng, and Sh. Gao. "A BCI-based environmental controller for the motion-disabled." IEEE Transactions on neural systems and rehabilitation engineering 11, No. 2, pp. 137-140, 2003.

[11] ف. آهنین‌جان، ع. مالکی، « توسعه یک سیستم واسط مغز-کامپیوتر مبتنی بر پتانسیل برانگیخته بینایی حالت ماندگار برای تایپ متون فارسی»، مجله دانشکده پزشکی اصفهان، سال 34ام، شماره 393، صفحه 914-918، پاییز 1395.

[12] L. Meng, J. Jin and X. Wang, "A comparison of three electrode channels selection methods applied to SSVEP BCI. " 4th IEEE International Conference in Biomedical Engineering and Informatics (BMEI), Vol. 1, pp. 584-587, 2011.

[13] م. علیرضایی علویجه، ع. مالکی، « روش همبستگی با پیش‌تنظیم بر اساس CCA برای سیستم مغز-کامپیوتر مبتنی بر SSVEP»، مجله مهندسی پزشکی زیستی، دوره‌ی 10، شماره 2، صفحه 187-196، تابستان 1395.

[14] JV. Odom, M. Bach, M. Brigell, GE. Holder, DL. McCulloch, A. Mizota, AP. Tormene. "ISCEV standard for clinical visual evoked potentials:(2016 update).", International Society for Clinical Electrophysiology of Vision, Documenta Ophthalmologica, Vol. 133, No. 1, pp. 1-9, 2016.

[15] Odom, J. Vernon, et al. "Visual evoked potentials standard (2004)." Documenta ophthalmologica, Vol. 108, No. 2, pp. 115-123, 2004.

[16] RM. Tello, SM. Muller, T. Bastos-Filho, A. Ferreira, “A comparison of techniques and technologies for SSVEP classification,” Proc. IEEE Conference on Biosignals and Robotics for Better and Safer Living (BRC), vol. 196, no. 1, pp. 1-6, May. 2014.

[17] G. Bin, X. Gao, Z. Yan, B. Hong, S. Gao, “An online multi-channel SSVEP-based brain–computer interface using a canonical correlation analysis method, “Journal of neural engineering, vol. 6, no. 4, pp. 046002, Jun. 2009.

[18] J. Castillo, S. Muller, E. Caicedo, T. Bastos, “Feature extraction techniques based on power spectrum for a SSVEP-BCI, “Proc. IEEE 23rd International Symposium on Industrial Electronics (ISIE)., pp. 1051-1055, Jun. 2014.

[19] N. Williams, SJ. Nasuto, JD. Saddy, “Evaluaton of empirical mode decomposition for event-related potential analysis, “EURASIP Journal on Advances in Signal Processing, vol. 1, pp. 965237, Dec. 2011.

[20] YH. Wang, CH. Yeh, HW. Young, K. Hu, MT. Lo, “On the computational complexity of the empirical mode decomposition algorithm, “Physica A: Statistical Mechanics and its Applications, vol. 400, pp. 159-67, Apr. 2014.

[21] N.E. Huang, Z. shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, H. H. Liu, “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, “Proc. in Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences. vol. 454, no. 1971, pp. 903-995, Mar. 1998.

Iranian Journal of Biomedical Engineering

The EMD-CCA with Neural Network Classifier to Recognize the SSVEP Frequency

References

References

Volume 11, Issue 2
June 2017
Pages 101-109

The EMD-CCA with Neural Network Classifier to Recognize the SSVEP Frequency

References

References

Volume 11, Issue 2June 2017Pages 101-109

Volume 11, Issue 2
June 2017
Pages 101-109