نویسندگان

1 دانشجوی کارشناسی ارشد مهندسی پزشکی، گروه مهندسی پزشکی، دانشکده‌ی فنی مهندسی، دانشگاه اصفهان، اصفهان

2 دانشیار، گروه مهندسی پزشکی، دانشکده‌ی فنی مهندسی، دانشگاه اصفهان، اصفهان

10.22041/ijbme.2018.89353.1365

چکیده

در چند دهه‌ی اخیر، رابط مغز-رایانه‌ی مبتنی بر تصور حرکت به صورت گسترده برای کمک به افراد مبتلا به اختلال حرکتی، مورد توجه قرار‌ گرفته است. مزیت این نوع رابط، به عنوان سیستمی درون‌زاد، عدم نیازبه تحریک خارجی و کنترل طبیعی می‌باشد. یکی ‌از مشکلات اصلی در کاربردی‌کردن این سیستم­، نیاز به نصب تعداد زیادی الکترود روی سر است که سبب افزایش هزینه‌ی تجهیزات، افزایش حجم محاسبات و هم‌چنین دشوارتر شدن استفاده از آن برای کاربر، به دلیل زمان‌بر بودن نصب الکترودها، می‌شود. تحقیقات اخیر، در جهت کاهش تعداد الکترودهای مورد نیاز با حفظ کارایی سیستم بوده است. هدف از این پژوهش، بررسی ویژگی‌ها و انتخاب ترکیبی مناسب برای تشخیص تصور حرکت با استفاده از تنها دو کانال (C3و C4) برای ثبت سیگنال مغز بوده است. به این منظور، از روش توان باند، پارامترهای حوزه‌ی زمان و مدل خودبازگشتی تطبیقی، به عنوان ویژگی و از روش شناخته شده و ساده‌ی آنالیز افتراقی خطی جهت طبقه‌بندی استفاده شد. نتایج نشان داد که ویژگی‌هایتوان باند، بیش‌ترین سازگاری و اثربخشی را برای تفکیک دقیق وظایفتصور حرکتی چپ و راست دارند. هم‌چنین، الگوریتم پیشنهادی به صورت ترکیب ویژگی توان باندبا پارامترهای حوزه‌ی زمان ومدل خودبازگشتی تطبیقی، سبب بهبود عمل‌کرد طبقه‌بندی گردید. نتایج روی داده‌های سومین دوره‌ی مسابقات رابط مغز-رایانه توانست جایگاه دوم را بین رقابت‌کنندگان اصلی مسابقه، با بیشینه‌ی STMIبرابر 2582/0 به دست آورد. در پردازش نابرخط، وظایفتصور حرکتی دستچپ و راست با صحت متوسط برابر با 85 درصد و کاپای 70 درصد تشخیص داده شد، هم‌چنین نتایج بیان‌گر انتقال اطلاعات خروجی گسسته‌ی 39/0 و پیوسته‌ی 45/0 و سطح زیرمنحنی عملیاتی دریافت‌کنندهی 91/0 بود. نتایج این مقاله نشان می‌دهد که ویژگی‌های جدید، به طور برجسته در هنگام استفاده از ترکیب هر سه دسته‌ی ویژگی، به بهبود عمل‌کرد طبقه‎‌بندی سیستم واسط مغز-رایانه‌ی دو کاناله منجر می‌شود و در ضمن، الگوریتم پیشنهادی برای افراد جدید نیز کارایی قابل مقایسه‌ای را ارائه کرده است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

A Hybrid Algorithm for Detecting Motor Imagery of Left and Right Hands Using Only Two Channels of EEG

نویسندگان [English]

  • Fatemeh Ghomi 1
  • Amin Mahnam 2
  • Mohammad Reza Yazdchi 2

1 MS.c Student, Department of Biomedical Engineering, University of Isfahan, Isfahan, Iran

2 Associate Professor, Department of Biomedical Engineering, University of Isfahan, Isfahan, Iran

چکیده [English]

Over the past few decades, the brain-computer interfaces (BCI) based on motor imagery has been widely developed to help people with motor disability. The advantage of this type of BCI as an endogenous system is, no need for external stimulation, and natural control. One of the major challenges to make these systems practical is to reduce the number of recording electrodes. In this study, only two EEG channels (C3 and C4) were used for detecting the imagery of left and right-hand movements. The features used were band powers (BP), some time domain parameters (TDP) and an adaptive autoregressive model (AAR). For classification, linear discriminant analysis (LDA), a well-known and simple classifier was used.The data was taken from the third BCI Competition. Our results confirm that BP features provide the most robust and effective features for accurate recognition. It was shown that combining the BP with TDP and AAR features can improve the accuracy of classification. However, implementing BP and TDP features is proposed for online classification where short computational cost is important. A maximum steepness of the mutual information (STMI) of 0.2582 was achieved in this study that could win the second place in the BCI Competition III. Left and right motor imagery (MI) tasks can be discriminated with an average classification accuracy of 85% and Kappa of 70%.

کلیدواژه‌ها [English]

  • Brain Computer Interface
  • Motor Imagery
  • Frequency Band Power
  • Time Domain Parameters
  • Adaptive Autoregressive Model
  • Linear Discriminant Analysis

[1]     H. Do, P. T. Wang, C. E. King, A. Abiri and Z. Nenadic, "Brain-Computer Interface Controlled Functional Electrical Stimulation System for Ankle Movement," NeuroEngineering and Rehabilitation, vol. 8, no. 49, 2011.

[2]     H. Do, P. T. Wang, C. E. King, S. N. Chun and a. Z. Nenadic, "Brain-computer interface controlled robotic gait orthosis," NeuroEngineering and Rehabilitation, vol. 10, no. 111, 2013.

[3]     G. Pfurtscheller, B. Graimann and B. Allison, Brain-computer interfaces : revolutionizing human-computer interaction, Springer-Verlag, 2010.

[4]     S. Gao, Y. Wang, X. Gao and B. Hong, "Visual and Auditory Brain–Computer Interfaces," Biomedical engineering, IEEE Transactions on, vol. 61(5), pp. 1436-1447, 2014.

[5]     J. Wolpawa, N. Birbaumer, D. McFarlanda, G. Pfurtscheller and T. Vaughan, "Brain–computer interfaces for communication and control," Clinical Neurophysiology, vol. 113, pp. 767-791, 2002.

[6]     J. R. Wolpaw and a. D. J. McFarland, "Control of a two-dimensional movement signal by a noninvasive brain–computer interface in humans," Proceedings of the National Academy of Sciences, vol. 101, no. 51, p. 17849–17854, 2004.

[7]     D. McFarland, A. S. R Wolpaw and J. William, "Electroencephalographic (EEG) control of three-dimensional movement," NEURAL ENGINEERING, vol. 7, 2010.

[8]     Y. Chae, J. Jeong and S. Jo, "Toward brain-actuated humanoid robots: asynchronous direct control using an EEG-based BCI," IEEE TRANSACTIONS ON ROBOTICS, vol. 28, no. 5, pp. 1131-1144, 2012.

[9]     J. d. Millán, F. Renkens, J. Mouriño and W. Gerstner, "Noninvasive Brain-Actuated Control of a Mobile Robot by Human EEG," Biomedical engineering, IEEE Transactions on, vol. 51, pp. 1026-1033, 2004.

[10] G. Pfurtscheller, R. Lee, C.Keinrath, D. Friedman, C. Neuper, C. Guger and M. Slater, "Walking from thought," Brain Research, vol. 1071, p. 145 – 152, 2006.

[11] J. Long, Y. Li, H. Wang, T. Yu, J. Pan and F. Li, "A hybrid brain computer interface to control the direction and speed of a simulated or real wheel chair," Neural Systems and Rehabilitation Engineering, IEEE Transactions on, vol. 20, pp. 720-729, 2012.

[12] J. Li, J. Liang, Q. Zhao, J. Li, K. Hong and L. Zhang, "Design of assistive wheelchair system directly steered by human thoughts," International Journal of Neural Systems, vol. 23, 2013.

[13] G. Pfurtscheller, C. Brunner, A. Schlogl and F. da Silva, "Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks," NeuroImage, vol. 31, p. 153–159, 2006.

[14] Y. Li, X. Gao, H. Liu and S. Gao, "Classification of Single-Trial Electroencephalogram During Finger Movement," Biomedical engineering, IEEE Transactions on, vol. 51, 2004.

[15] S. Lemm, K.-R. M. ller and G. Curio, "A Generalized Framework for Quantifying the Dynamics of EEG Event-Related Desynchronization," PLoS Computational Biology, vol. 5, 2009.

[16] J. McFarland, R. Wolpaw and a. D. J., "Multichannel EEG-based brain-computer communication," Electroencephalography and Clinical Neurophysiology, vol. 90, p. 444–449, 1994.

[17] M.Pregenzer, G.Pfurtscheller, J.Kalcher, Ch.Neuper, G.Pfurtscheller, J.Kalcher and C. D.Flotzinger, "On-line EEG classification during externally-paced hand movements using a neural network-based classifier," Neurophysioligy, pp. 416-425, 1996.

[18] A. Schlogl, F. Lee, H. Bischof and G. Pfurtscheller, "Characterization of four-class motor imagery EEG data for the BCI-competition 2005," Journal of Neural Engineering, pp. 14-22, 2005.

[19] S. ,. R. C. ,. R. S. C. Vidaurre and G. Pfurtscheller, "Adaptive On-line Classification for EEG-based Brain Computer Interfaces with AAR parameters and band power estimates," Biomed. Technik, vol. 50, pp. 350-354, 2005.

[20] Vidaurre, N. Krämer, B. Blankertz and A. Schlögl, "Time Domain Parameters as a feature for EEG-based Brain-Computer Interfaces," Neural Networks, vol. 22, pp. 1313-1319, 2009.

[21] Z. Allison, C. Brunner, V. Kaiser, G. R. M. uller-Putz and C. Neuper, "Toward a hybrid brain–computer interface based on imagined movement and visual attention," Neural Engineering, vol. 7, 2010.

[22] W.-Y. HSU, "Single-trial motor imagery classification using asymmetry ratio, phase relation, wavelet-based fractal, and their selected combination.," Int J Neural Syst, vol. 23, 2013.

[23] J. Jiang, Z. Zhou, E. Yin, Y. Yu, Y. Liu and D. Hu, "A novel Morsecode-inspired method for multi class motor imagery brain–computer interface(BCI)design," Computers in Biology and Medicine, vol. 66, pp. 11-19, 2015.

[24] H. Z. Y. W. Qi Xu and J. Huang, "Fuzzy support vector machine for classification of EEG signals using wavelet-based features," Medical Engineering & Physics, vol. 31, pp. 858-865, 2009.

[25] Y. F. Minyou Chena and X. Zheng, "Phase space reconstruction for improving the classification of singlesingle trial EEG," Biomedical Signal Processing and Control, vol. 11, pp. 10-16, 2014.

[26] M. C. Yonghui Fang and X. Zheng, "Extracting features from phase space of EEG signals in brain-computer interfaces," Neurocomputing, 2015.

[27] H. M. Z. S. Mobarakeh, "Improvement of EEG-based motor imagery classification using ringtopology-based particle swarm optimization," Biomedical Signal Processing and Control, vol. 32, pp. 69-75, 2017.

[28] N. M. Hamidreza Abbaspour and S. M. Razavi, "An Effective Brain-Computer Interface System Based on the Optimal Timeframe Selection of Brain Signals," Int Clin Neurosci, vol. 5, pp. 35-42, 2018.

[29] W.-K. Tam, K.-y. Tong, F. Meng and a. S. Gao, "A Minimal Set of Electrodes for Motor Imagery BCI to Control an Assistive Device in Chronic Stroke Subjects: A Multi-Session Study," Neural Systems and Rehabilitation Engineering, IEEE Transactions on, vol. 19, no. 6, pp. 617-627, 2011.

[30] [Online]. Available: http://www.bbci.de/competition/iii/#data_set_iiib.

[31] N. Brodu, F. Lotte and A. Lécuyer, "Comparative Study of Band-Power Extraction Techniques for Motor Imagery Classification," in IEEE Symposium on Computational Intelligence,Cognitive Algorithms, Mind, and Brain,pp.1-6, Paris, France, 2011.

[32] XinMa, "The research of brain-computer interface based on AAR parameters and neural networks classifier," in International Conference on Computer Science and Network Technology, 2011.

[33] Y. &. G. X. &. H. b. &. G. S. Wang, " Practical Designs of Brain–Computer Interfaces Based on the Modulation of EEG Rhythms. Brain-Computer Interfaces," in The Frontiers Collection, Berlin Heid, Springer-Verlag, 2010, pp. 137-154.

[34] J. Yue, Z. Zhou, J. Jiang, Y. Liu and D. Hu, "Balancing a simulated inverted pendulum through motor imagery: An EEG-based real-time control paradigm," Neuroscience Letters, vol. 524, p. 95– 100, 2012.

[35] A. Schlogl, J. Kronegg, J. E. Huggins and S. G. Mason, "Evaluation Criteria for BCI Research," in Toward Brain-computer Interfacing, London, England, The MIT Press, 2007, pp. 327-342.

[36] J. Cohen, "A coefficient of agreement for nominal scales," Educational and Psychological Measurement, vol. 20, no. 1, pp. 37-46, 1960.

[37] Monge-Pereira, J. Ibañez-Pereda, I. Alguacil-Diego, J. Serrano, M. Spottorno-Rubio and F. Molina-Rueda, "Use of Electroencephalography Brain Computer Interface systems as a rehabilitative approach for upper limb function after a stroke. A systematic review," PM&R, vol. 9, no. 9, pp. 918-932, 2017.

[38] Iturrate, J. M Antelis, A. Kubler and J. Minguez, "A Noninvasive Brain-Actuated Wheelchair Based on a P300 Neurophysiological Protocol and Automated Navigation," Robatics, IEEE Transactions on, vol. 25, pp. 614-627, 2009.

[39] Lehtonen, P. Jylänki, L. Kauhanen and M. Sams, "Online Classification of Single EEG Trials During Finger Movements," Biomedical engineering, IEEE Transactions on, vol. 55, pp. 713-720, 2008.

[40] G. Onose, C. Grozea, A. Anghelescu, C. Daia, C. Sinescu, A. Ciurea, T. Spircu and A. Mirea, "On the feasibility of using motor imagery EEG-based brain–computer interface in chronic tetraplegics for assistive robotic arm control: a clinical test and long-term post-trialfollow-up," Spinal Cord, vol. 50, pp. 599-608, 2012.

[41] T. M. Mitchell, Machine learning, Boston: McGraw-Hill, 1997.