نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 کارشناسی ارشد مهندسی پزشکی، گروه مهندسی پزشکی، دانشکده‌ی مهندسی برق و کامپیوتر، دانشگاه سمنان، سمنان، ایران

2 دانشیار، گروه مهندسی پزشکی، دانشکده‌ی مهندسی برق و کامپیوتر، دانشگاه سمنان، سمنان، ایران

10.22041/ijbme.2022.540893.1728

چکیده

امروزه استفاده از سیستم‌ رابط مغز-رایانه مبتنی بر پتانسیل‌های برانگیخته‌ی بینایی حالت ماندگار به دلیل مزایایی مانند صحت قابل قبول و نیاز حداقلی به آموزش کاربر، رو به افزایش است. با وجود این مزایا، نویزهای ناخواسته‌ای که SSVEP را تحت تاثیر قرار می‌دهد از مسائلی است که می‌تواند سبب کاهش کارایی چنین سیستم‌هایی شود. در این مقاله از الگوریتم EMD در مرحله‌ی ابتدایی و از روش‌های CCA یا LASSO برای بازشناسی فرکانس تحریک استفاده شده است. در گام اول، الگوریتم EMD اعمال شده است تا سیگنال غیرایستان SSVEP به توابعی نوسانی تجزیه شده و امکان استخراج ویژگی‌های بامعنی از سیگنال SSVEP فراهم شود. در بین IMF-های به دست آمده از روش EMD، تنها IMF-هایی انتخاب شده که دامنه‌ی طیف فرکانسی آن‌ها در محدوده‌ی فرکانسی مربوط به تحریک بیش‌تر بوده است. با این گزینش می‌توان سیگنال‌های حاوی نویز و فاقد اطلاعات ارزشمند را کنار گذاشت. در ادامه دو روش تشخیصی CCA و LASSO روی مجموع سیگنال‌های انتخابی اجرا شده است تا به کمک آن‌ها فرکانس تحریک شناسایی شود. نتایج شبیه‌سازی، صحت بازشناسی 76/81 و 26/82 درصد را به ترتیب برای روش‌های EMD-CCA و EMD-LASSO نشان داده در حالی که دو روش پایه‌ی CCA و LASSO به ترتیب دارای صحت‌های 10/78 و 72/78 درصد می‌باشند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Combined Method of EMD with CCA or LASSO to Detect SSVEP Frequency

نویسندگان [English]

  • Marzie Alirezaei Alavijeh 1
  • Ali Maleki 2

1 M.Sc. Graduated, Biomedical Engineering Department, Semnan University, Semnan, Iran

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

چکیده [English]

Nowadays, brain-computer interface system based on steady-state visual evoked potentials is increased due to advantages such as accepted accuracy and minimal need for user training. Despite these benefits, the unwanted noise that affects SSVEP is one of the issues that can reduce the efficiency of such systems. This paper uses the EMD algorithm in the initial phase and CCA or LASSO for the recognition of the stimulation frequency. In the first step, the EMD algorithm is applied so that non-stationary SSVEP signal breaks into oscillating functions and meaningful information are extracted. Among the IMFs obtained from the EMD method, only IMFs whose amplitude of the frequency spectrum in the frequency ranges corresponding to the excitation is higher were selected. With this selection, noisy signals and unprofitable information can be omitted. In the proposed method, two CCA and LASSO diagnostic methods were performed on the sum of selected signals to identify the frequency of stimulation. The simulation results show the recognition accuracy of 81.76% and 82.26% for the proposed method EMD-CCA and EMD-LASSO, respectively. While detection accuracy is 78.10% and 78.72% for conventional methods of CCA and LASSO. 

کلیدواژه‌ها [English]

  • Brain-Computer Interface
  • Steady-State Visual Evoked Potentials
  • Empirical Mode Decomposition
  • Canonical Correlation Analysis
  1. F. Diez et al., “Asynchronous BCI control using high-frequency SSVEP,” Journal of Neuro Engineering and Rehabilitation, vol. 8, no. 1, p. 39, 2011.
  2. Mouli, R. Palaniappan, E. Molefi, and I. McLoughlin, “In-Ear Electrode EEG for Practical SSVEP BCI,” Technologies, vol. 8, no. 4, p. 63, 2020.
  3. H. Wu, H. C. Chang, and P. L. Lee, “Instantaneous gaze-target detection by empirical mode decomposition: Application to brain computer interface,” IFMBE Proceedings, vol. 25, no. 9, pp. 215–218, 2009.
  4. Putze, D. Weib, L. M. Vortmann, and T. Schultz, “Augmented reality interface for smart home control using SSVEP-BCI and eye gaze,” Conf. Proc. - IEEE Int. Conf. Syst. Man Cybern., vol. 2019-October, pp. 2812–2817, 2019.
  5. H. Wu 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. 170–181, 2011.
  6. Chevallier, E. K. Kalunga, Q. Barthélemy, and E. Monacelli, “Review of Riemannian Distances and Divergences, Applied to SSVEP-based BCI,” Neuroinformatics, vol. 19, no. 1, pp. 93–106, 2020.
  7. Liu, K. Chen, Q. Ai, and S. Q. Xie, “Review: Recent development of signal processing algorithms for SSVEP-based brain computer interfaces,” Journal of Medical and Biological Engineering, vol. 34, no. 4, pp. 299–309, 2014.
  8. K. Gao et al., “Multivariate empirical mode decomposition and multiscale entropy analysis of EEG signals from SSVEP-based BCI system,” Epl, vol. 122, no. 4, 2018.
  9. M. G. Tello, S. M. T. Muller, T. Bastos-Filho, and A. Ferreira, “Comparison of new techniques based on EMD for control of a SSVEP-BCI,” IEEE Int. Symp. Ind. Electron., pp. 992–997, 2014.
  10. Lin, C. Zhang, W. Wu, and X. Gao, “Frequency recognition based on canonical correlation analysis for SSVEP-Based BCIs,” IEEE Transactions on Biomedical Engineering, vol. 54, no. 6, pp. 1172–1176, 2006.
  11. Oehler, P. Neumann, M. Becker, G. Curio, and M. Schilling, “Extraction of SSVEP signals of a capacitive EEG helmet for human machine interface” Conference: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, vol. 2008, no. factor 2, pp. 4495–4498, 2008.
  12. Li, G. Bin, X. Gao, B. Hong, and S. Gao, “Analysis of phase coding SSVEP based on canonical correlation analysis (CCA),” 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011, pp. 368–371, 2011.
  13. Ravi, N. H. Beni, J. Manuel, and N. Jiang, “Comparing user-dependent and user-independent training of CNN for SSVEP BCI,” J. Neural Eng., vol. 17, no. 2, 2020.
  14. Zhang, J. Jin, X. Qing, B. Wang, and X. Wang, “LASSO based stimulus frequency recognition model for SSVEP BCIs,” Biomedical Signal Processing and Control, vol. 7, no. 2, pp. 104–111, 2012.
  15. Huang, X.Huang, Y.Wang. “Empirical mode decomposition improves detection of SSVEP” 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2013.
  16. [Online]. Available: http://www.setzner.com/avi-ssvep-dataset/. [Accessed: 09-Mar-2017].
  17. E. Huang et al., “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” Proc. Royal Soc. Lond., vol. A 495, pp. 903–995, 1998.
  18. Huang, X. Huang, Y. Wang, Y. Wang, T. Jung, and C. Cheng, “Empirical Mode Decomposition Improves Detection of SSVEP,” pp. 3901–3904, 2013.
  19. Cao, Z. Ju, J. Li, R. Jian, and C. Jiang, “Sequence detection analysis based on canonical correlation for steady-state visual evoked potential brain computer interfaces,” Journal of Neuroscience Methods, vol. 253, pp. 10–17, 2015.
  20. Zhang, G. Zhou, J. Jin, X. Wang, and A. Cichocki, “Frequency recognition in SSVEP-based BCI using multiset canonical correlation analysis.,” Int. J. Neural Syst., vol. 24, no. 4, p. 1450013, 2014.
  21. Tibshirani, “Regression Selection and Shrinkage via the Lasso,” Journal of the Royal Statistical Society B, vol. 58, no. 1. pp. 267–288, 1996.
  22. Wang, K. Iramina, and S. Ge, “An improved multiple LASSO model for steady-state visual evoked potential detection,” IFMBE Proc., vol. 63, pp. 427–430, 2018.
  23. L. S. Ferreira, L. C. de Miranda, E. E. C. de Miranda, and S. G. Sakamoto, “A Survey of Interactive Systems based on Brain-Computer Interfaces,” SBC Journal on Interactive Systems, vol. 4, no. 1, pp. 3–13, 2013.
  24. Sansana, “BCI-based spatial navigation control: a comparison study.” Ph.D thesis, University of Lisbon, 2016.
  25. Ojha, M, Mukul, "Detection of target frequency from SSVEP signal using empirical mode decomposition for SSVEP based BCI inference system." Wireless Personal Communications 116, no. 1, pp. 777-789, 2021.
  26. [26]D.Aminaka, S.Makino, and T. Rutkowski. “Chromatic ssvep bci paradigm targeting the higher frequency EEG responses,” Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014.
  27. Che, K.Atal, S.Xie. “A new multivariate empirical mode decomposition method for improving the performance of SSVEP-based brain–computer interface” Journal of neural engineering 14. 4, 2017.