طبقه‌بندی خودکار پاسخ‌های SSVEP با نمونه‌های آموزشی محدود و ماتریس کوواریانس تنظیم شده مبتنی بر انقباض

نوع مقاله : علمی-پژوهشی

نویسندگان

1 استادیار، گروه مهندسی ورزش، دانشکده علوم مهندسی، دانشکدگان فنی، دانشگاه تهران، تهران، ایران

2 استادیار، دانشکده مهندسی پزشکی، دانشگاه صنعتی سهند، تبریز، ایران.

چکیده

یکی از چالش‌های اساسی در توسعه سیستم‌های رابط مغز و رایانه (BCI)، پایین بودن نرخ انتقال اطلاعات (ITR) است. استفاده از زمان تحریک کوتاه راه‌حلی است که دارای مزیت‌های افزایش مقدار ITR و کاهش خستگی ذهنی کاربران است. به هنگام استفاده از زمان تحریک کوتاه، الگوریتم‌های مبتنی بر شکل‌دهیِ پرتوِ واریانس کمینه با محدودیت خطی (LCMV) عملکرد مناسبی نسبت به سایر طبقه‌بندها فراهم می‌کنند. اما عملکرد آن‌ها در شرایط مذکور بدلیل تخمین بد ماتریس کوواریانس همچنان پایین است. برای بهبود عملکرد شکل‌دهنده پرتو LCMV، این مطالعه چهار ماتریس کوواریانس تنظیم شده مبتنی بر انقباض؛ شامل ترکیب محدب (CC)، ترکیب خطی کلی (GLC)، CC اصلاح‌شده (MCC) و GLC اصلاح‌شده (MGLC) را پیشنهاد می‌کند. تخمین‌گر‌های پیشنهادی با بهبود تخمین بردار وزن به کار رفته در شکل‌دهنده پرتو مکانی-زمانی LCMVst عملکرد طبقه‌بندی را بهبود می‌دهند. نتایج نشان داد که به هنگام استفاده از کوتاه‌ترین زمان تحریک (25/0 ثانیه)، شکل‌دهنده‌های پرتو پیشنهادی LCMVst-MCC و LCMVst-MGLC بهبود قابل توجهی در حدود 27 درصد در میانگین دقت طبقه‌بندی نسبت به LCMVst ارائه کردند. همچنین، روش‌های LCMVst-MCC، LCMVst-MGLC نسبت به روش‌های LCMVst-CC، LCMVst-GLC بهبود تقریبی 9 درصد را در دقت طبقه‌بندی ارائه کردند. نتایج نشان می‌دهد که شکل‌دهنده‌های پرتو پیشنهادی دارای پتانسیل بالایی در توسعه سیستم‌های BCI مبتنی بر SSVEP هستند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Automatic Classification of SSVEP Responses with Limited Training Samples and Shrinkage-Based Regularized Covariance Matrix

نویسندگان [English]

  • Alireza Talesh Jafadideh 1
  • Asghar Zarei 2
1 School of Engineering Science, College of Engineering, University of Tehran, Tehran, Iran
2 Biomedical Engineering Faculty, Sahand University of Technology, Tabriz, Iran
چکیده [English]

A major hurdle in brain computer interface (BCI) development is the low information transfer rate (ITR). Using a short stimulation time is a solution that offers the advantages of increasing the ITR value and reducing the mental fatigue of users. When using short stimulation time, algorithms based on linearly constrained minimum variance beamforming (LCMV) provide better performance over other classifiers. However, their performance in aforementioned condition is still low due to the ill-conditioned estimation of the data covariance matrix. To address this problem, this study proposes the use of four Shrinkage-based regularized covariance matrices, including convex combination (CC), generalized linear combination (GLC), modified CC (MCC), and modified GLC (MGLC). The proposed covariance matrices are applied in the spatial-temporal beamformer LCMVst to construct a better weight vector, thereby improving the classification performance. The results showed that when using the shortest stimulation time (0.25s), the proposed beamformers LCMVst-CC, LCMVst-GLC, LCMVst-MCC, and LCMVst-MGLC provided a significant improvement of about 27% in average classification accuracy over conventional LCMVst. Also, the LCMVst-MCC and LCMVst-MGLC methods compared to LCMVst-CC and LCMVst-GLC methods provided approximately 9% improvement in classification accuracy. The results of this study show that the proposed beamformers have high potential in the development of SSVEP-based BCI systems.

کلیدواژه‌ها [English]

  • Brain-computer interface
  • Steady-state visual evoked potential
  • Adaptive beamforming
  • Shrinkage-based regularized covariance matrix
  • EEG signal

مراجع

[1] Lotte, F., Bougrain, L., Cichocki, A., Clerc, M., Congedo, M., Rakotomamonjy, A., & Yger, F., “A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update”, Journal of neural engineering, vol. 15, no. 3, pp. 031005, 2018.
[2] Akbarzadeh Totonchi, M. R., Hosseini, S. A., & Naghibi Sistani, M. B., “Evaluation of visual selective attention by event-related potential analysis in brain activity”, TABRIZ JOURNAL OF ELECTRICAL ENGINEERING (TJEE), vol. 46, no. 1, pp. 13–24, 2016.
[3] Jahantigh, M., & Charmi, M., “Increasing classification accuracy of motor imagery EEG signals with logical combination of classifiers and by applying genetic algorithm and small decision trees”, TABRIZ JOURNAL OF ELECTRICAL ENGINEERING (TJEE), vol. 47 no. 3, pp. 931–938, 2017.
[4] Xiao, X., Xu, M., Han, J., Yin, E., Liu, S., Zhang, X., ... & Ming, D., “Enhancement for P300-speller classification using multi-window discriminative canonical pattern matching. Journal of neural engineering”, vol. 18, no. 4, pp. 046079, 2021.
[5] Yin, E., Zhou, Z., Jiang, J., Yu, Y., & Hu, D., “A dynamically optimized SSVEP brain–computer interface (BCI) speller”, IEEE transactions on biomedical engineering, vol. 62, no. 6, pp. 1447-1456, 2014.
[6] Jin, J., Xiao, R., Daly, I., Miao, Y., Wang, X., & Cichocki, A “Internal feature selection method of CSP based on L1-norm and Dempster–Shafer theory”, IEEE transactions on neural networks and learning systems, vol. 32, no. 11, pp. 4814-4825, 2020.
[7] Norcia, A. M., Appelbaum, L. G., Ales, J. M., Cottereau, B. R., & Rossion, B., “The steady-state visual evoked potential in vision research: A review. Journal of vision”, vol. 15, no. 6, pp. 4-4, 2015.
[8] Gu, M., Pei, W., Gao, X., & Wang, Y., “Optimizing Visual Stimulation Paradigms for User-Friendly SSVEP-Based BCIs”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 32, 2024.
[9] Wong, C. M., Wang, Z., Wang, B., Rosa, A., Jung, T. P., & Wan, F., “Enhancing detection of multi-frequency-modulated SSVEP using phase difference constrained canonical correlation analysis”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 31, pp. 1343-1352, 2023.
[10] De Paula, P. O., da Silva Costa, T. B., de Faissol Attux, R. R., & Fantinato, D. G., “Classification of image encoded SSVEP-based EEG signals using Convolutional Neural Networks”, Expert Systems with Applications, vol. 214, p. 119096, 2023.
[11] Luo, A., & Sullivan, T. J., “A user-friendly SSVEP-based brain–computer interface using a time-domain classifier”, Journal of neural engineering, vol. 7, no. 2, 026010, 2010.
[12] Liu, Q., Jiao, Y., Miao, Y., Zuo, C., Wang, X., Cichocki, A., & Jin, J., “Efficient representations of EEG signals for SSVEP frequency recognition based on deep multiset CCA”, Neurocomputing, vol. 378, pp. 36-44, 2020.
[13] Nakanishi, M., Wang, Y., Wang, Y. T., & Jung, T. P., “A comparison study of canonical correlation analysis based methods for detecting steady-state visual evoked potentials”, PloS one, vol. 10, no. 10, p. e0140703, 2015.
[14] Yin, X., & Lin, M., “Multi-information improves the performance of CCA-based SSVEP classification”, Cognitive Neurodynamics, vol. 18, no. 1, pp. 165-172, 2024.
[15] Jaramillo Gonzalez, A., Unlocking communication: advancing brain-computer interfaces for ALS Patients in locked-in and completely locked-in states (Doctoral dissertation, Universität Tübingen), 2024.
[16] Zhang, Y., Guo, D., Li, F., Yin, E., Zhang, Y., Li, P., ... & Xu, P., “Correlated component analysis for enhancing the performance of SSVEP-based brain-computer interface”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 5, pp. 948-956, 2018.
[17] Zhang, Y., Yin, E., Li, F., Zhang, Y., Tanaka, T., Zhao, Q., ... & Guo, D., “Two-stage frequency recognition method based on correlated component analysis for SSVEP-based BCI”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 7, pp. 1314-1323, 2018.
[18] Yuan, X., Zhang, L., Sun, Q., Lin, X., & Li, C., “A novel command generation method for SSVEP-based BCI by introducing SSVEP blocking response”, Computers in Biology and Medicine, vol. 146, p. 105521, 2022.
[19] Zhao, X., Du, Y., & Zhang, R., “A CNN-based multi-target fast classification method for AR-SSVEP”, Computers in biology and medicine, vol. 141, p. 105042, 2022.
[20] Wittevrongel, B., & Van Hulle, M. M., “Frequency-and phase encoded SSVEP using spatiotemporal beamforming”, PloS one, vol. 11, no. 8, p. e0159988, 2016.
[21] Van Veen, B. D., Van Drongelen, W., Yuchtman, M., & Suzuki, A., “Localization of brain electrical activity via linearly constrained minimum variance spatial filtering”, IEEE Transactions on biomedical engineering, vol. 44, no. 9, pp. 867-880, 1997.
[22] Reed, I. S., Mallett, J. D., & Brennan, L. E., “Rapid convergence rate in adaptive arrays”, IEEE Transactions on Aerospace and Electronic Systems, no. 6, pp. 853-863, 1974.
[23] Ravan, M., Reilly, J. P., & Hasey, G., “Minimum variance brain source localization for short data sequences”, IEEE Transactions on Biomedical Engineering, vol. 61, no. 2, pp. 535-546, 2013.
[24] Vorobyov, S. A., Gershman, A. B., & Luo, Z. Q., “Robust adaptive beamforming using worst-case performance optimization: A solution to the signal mismatch problem”, IEEE transactions on signal processing, vol. 51, no. 2, pp. 313-324, 2003.
[25] Stoica, P., Li, J., Zhu, X., & Guerci, J. R., “On using a priori knowledge in space-time adaptive processing”, IEEE transactions on signal processing, vol. 56, no. 6, pp. 2598-2602, 2008.
[26] Jafadideh, A. T., & Asl, B. M., “A new data covariance matrix estimation for improving minimum variance brain source localization”, Computers in Biology and Medicine, vol. 143, p. 105324, 2022.
[27] Van Vliet, M., Chumerin, N., De Deyne, S., Wiersema, J. R., Fias, W., Storms, G., & Van Hulle, M. M., “Single-trial erp component analysis using a spatiotemporal lcmv beamformer”, IEEE Transactions on Biomedical Engineering, vol. 63, no. 1, pp. 55-66, 2015.
[28] Ribeiro, L. N., de Almeida, A. L., & Mota, J. C. M., “Separable linearly constrained minimum variance beamformers”, Signal Processing, vol. 158, pp. 15-25, 2019.
[29] Amar, A., & Doron, M. A., “A linearly constrained minimum variance beamformer with a pre-specified suppression level over a pre-defined broad null sector”, Signal Processing, vol. 109, pp. 165-171, 2015.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار