An efficient hardware implementation for a motor imagery brain computer interface system

Document Type : Article

Authors

Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran

Abstract

Brain Computer Interface (BCI) systems, which are based on motor imagery, enable human to command artificial peripherals by merely thinking to the task. There is a tremendous interest in implementing BCIs on portable platforms, such as Field Programmable Gate Arrays (FPGAs) due to their low-cost, low-power and portability characteristics. This article presents the design and implementation of a Brain Computer Interface (BCI) system based on motor imagery on a Virtex-6 FPGA. In order to design an accurate algorithm, the proposed method avails statistical learning methods such as Mutual Information (MI), Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM). It also uses Separable Common Spatio Spectral Pattern (SCSSP) method in order to extract features. Simulation results prove achieved performances of 73.54% for BCI Competition III-dataset V, 67.2% for BCI Competition IV-dataset 2a with all four classes, 80.55% for BCI Competition IV-dataset 2a with the first two classes, and 81.9% for captured signals. Moreover, the final reported hardware resources determine its efficiency as a result of using retiming and folding techniques from the VLSI architecture perspective. The complete proposed BCI system not only achieves excellent recognition accuracy but also remarkable implementation efficiency in terms of portability, power, time, and cost.

Keywords


1. Wolpaw, J.R., Birbaumer, N., McFarland, D.J., Pfurtscheller, G., and Vaughan, T.M. Braincomputer interfaces for communication and control", Clin. Neurophysiol., 113(6), pp. 767-791 (2002). 2. Duchowski, A.T., Eye Tracking Methodology: Theory and Practice, Springer International Publishing AG, 3rd Ed., ISBN 978-3-319-57881-1, ISBN 978-3-
319-57883-5 (eBook) (2017). DOI 10.1007/978-3-319- 57883-5 3. Ferracuti, F., Freddi, A., Iarlori, S., Longhi, S., and Peretti, P. Auditory paradigm for a p300 BCI system using spatial hearing", In Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on, IEEE, pp. 871-876 (2013). 4. Kathner, I., Ruf, C.A., Pasqualotto, E., Braun, C.,
Birbaumer, N., and Halder, S. A portable auditory P300 brain-computer interface with directional cues", Clinical Neurophysiology, 124(2), pp. 327-338 (2013). 5. Kim, D.-W., Hwang, H., Lim, J.-H., Lee, Y.-H., Jung, K.-Y., and Im, C.-H. Classi cation of selective attention to auditory stimuli: toward vision-free braincomputer interfacing", Journal of Neuroscience Methods, 197(1), pp. 180-185 (2011). 6. Pfurtscheller, G., Brunner, C., Schlogl, A., and Da
Silva, F.H.L. Mu rhythm (de) synchronization and EEG single-trial classi cation of di erent motor imagery
tasks", NeuroImage, 31(1), pp. 153-159 (2006). 7. Khurana, K., Gupta, P., Panicker, R.C., and Kumar, A. Development of an FPGA-based real-time P300 speller", 22nd International Conference on Field Programmable Logic and Applications (FPL), Oslo, pp. 551-554 (2012). 8. Xu, B., Song, A., and Wu, J. Algorithm of imagined left-right hand movement classi cation based on wavelet transform and AR parameter model", Bioinformatics and Biomedical Engineering, The 1st International Conference on. IEEE (2007). 9. Schlogl, A., The Electroencephalogram and the Adaptive Autoregressive Model: Theory and Applications, Germany: Shaker (2000). 10. Pfurtscheller, G., Neuper, C., Schlogl, A., and Lugger, K. Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters", in IEEE Transactions on Rehabilitation Engineering, 6(3), pp. 316-325 (Sept. 1998). 11. Schlogl, A., Lugger, K., and Pfurtscheller, G. Using
adaptive autoregressive parameters for a braincomputer- interface experiment", Proceedings 19th International
Conference IEEE/EMBS (1997). 12. Dharmasena, S., Lalitharathne, K., Dissanayake, K., Sampath, A., and Pasqual, A. Online classi cation of 92 A. Malekmohammadi et al./Scientia Iranica, Special Issue on: Socio-Cognitive Engineering 26 (2019)   72{94 imagined hand movement using a consumer grade EEG device", Industrial and Information Systems (ICIIS),
8th IEEE International Conference on. IEEE (2013). 13. Alomari, M.H., Samaha, A., and AlKamha, K. Automated classi cation of L/R hand movement EEG signals using advanced feature extraction and machine learning", International Journal of Advanced Computer Science and Applications, 4(6), pp. 207-212 (2013). 14. Xu, Q., Zhou, H., Wang, Y., and Huang, J. Fuzzy support vector machine for classi cation of EEG signals using wavelet-based features", Medical Engineering
& Physics, 31(7), pp. 858-865 (2009). 15. Ebrahimpour, R., Babakhani, K., and Mohammad- Noori, M. EEG-based motor imagery classi cation using wavelet coecients and ensemble classi ers", Arti cial Intelligence and Signal Processing (AISP),
16th CSI International Symposium on. IEEE (2012). 16. Carrera-Leon, O., Ramirez, J.M., Alarcon-Aquino, V., Baker, M., D'Croz-Baron, D., and Gomez-Gil, P. A motor imagery BCI experiment using wavelet analysis and spatial patterns feature extraction", Engineering Applications (WEA), 2012 Workshop on. IEEE (2012). 17. Jahankhani, P., Kodogiannis, V., and Revett, K. EEG signal classi cation using wavelet feature extraction and neural networks", John Vincent Atanaso 
2006 International Symposium on Modern Computing (JVA'06), IEEE (2006). 18. Subasi, A. Automatic recognition of alertness level from EEG by using neural network and wavelet coef-  cients", Expert Systems with Applications, Elsevier,
28(4), pp. 701-711 (2015). 19. Ting, W., et al. EEG feature extraction based on wavelet packet decomposition for brain computer interface", Measurement, Elsevier, 41(6), pp. 618-625 (2008). 20. Subasi, A. EEG signal classi cation using wavelet feature extraction and a mixture of expert model", Expert Systems with Applications, 32(4), pp. 1084-
1093 (2007). 21. Lotte, F., Guan, C., and Ang, K.K. Comparison of designs towards a subject-independent brain-computer
interface based on motor imagery", Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Minneapolis, MN, pp. 4543-4546 (2009). 22. Ramoser, H., Mller-Gerking, J., and Pfurtscheller, G. Optimal spatial  ltering of single trial EEG during imagined hand movement", IEEE Transactions on Rehabilitation Engineering, 8(4), pp. 441-446 (2000). 23. Suk, H.-I. and Lee, S.-W. A probabilistic approach to spatiospectral  lters optimization in brain-computer interface", International Conference on Systems, Man, and Cybernetics (SMC), IEEE, pp. 19-24 (2011).
24. Lemm, S., Blankertz, B., Curio, G., and Mller, K. Spatio-spectral  lters for improving the classi cation of single trial EEG", IEEE Transactions on Biomedical Engineering, 52(9), pp. 1541-1548 (2005). 25. Dornhege, G., Blankertz, B., Krauledat, M., Losch, F., Curio, G., and Muller, K.R. Combined optimization of spatial and temporal  lters for improving braincomputer
interfacing", IEEE Transactions on Biomedical Engineering, 53(11), pp. 2274-2281 (2006). 26. Wu, W., Gao, X., Hong, B., and Gao, S. Classifying single-trial EEG during motor imagery by iterative spatio-spectral patterns learning (ISSPL)",
IEEE Transactions on Biomedical Engineering, 55(6), pp. 17331743 (2008). 27. Zhang, H., Chin, Z.Y., Ang, K.K., Guan, C., and
Wang, C. Optimum spatio-spectral  ltering network for brain-computer interface", IEEE Transactions on Neural Networks, 22(1), pp. 52-63 (2011). 28. Ang, K.K., Chin, Z.Y., Wang, C., Guan, C., and Zhang, H. Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b", Frontiers in Neuroscience, 6(39), pp. 1-9 (2012). 29. Ang, K.K. and Guan, C. EEG-based strategies to detect motor imagery for control and rehabilitation", IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(4), pp. 392-401 (2017). 30. Aghaei, A.S., Mahanta, M.S., and Plataniotis, K.N.
Separable common spatio-spectral pattern algorithm for classi cation of EEG signals", Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. IEEE (2013). 31. Lotte, F. and Guan, C. Regularizing common spatial patterns to improve BCI designs: uni ed theory and new algorithms", IEEE Transactions on Biomedical Engineering, 58(2), pp. 355-362 (2011). 32. Sotiris, B., Kotsiantis, I., and Zaharakis, P. Pintelas, Supervised machine learning: A review of classi cation techniques", Proceedings of the 2007 Conference on Emerging Arti cial Intelligence, pp. 3-24 (2007).
33. Wu, S.-L., Wu, C.-W., Pal, N.R., Chen, C.-Y., Chen, S.-A., and Lin, C.-T. Common spatial pattern and linear discriminant analysis for motor imagery classi   cation", In Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), 2013 IEEE Symposium on, IEEE, pp. 146-151 (2013). 34. Pfurtscheller, G., Neuper, C., Schlogl, A., and Lugger,
K. Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters", IEEE transactions on Rehabilitation Engineering, 6(3), pp. 316-325 (1998). 35. Ince, N.F., Goksu, F., Tew k, A.H., and Arica,
S. Adapting subject speci c motor imagery EEG patterns in spacetimefrequency for a brain computer interface", Biomedical Signal Processing and Control, 4(3), pp. 236-246 (2009). 36. Lal, T.N., Schroder, M., Hinterberger, T., Weston,
J., Bogdan, M., Birbaumer, N., and Scholkopf, B. Support vector channel selection in BCI", IEEE Transactions on Biomedical Engineering, 51(6), pp.  1003-1010 (2004). A. Malekmohammadi et al./Scientia Iranica, Special Issue on: Socio-Cognitive Engineering 26 (2019) 72{94 93 37. Garcia, G.N., Ebrahimi, T., and Vesin, J.-M. Support vector EEG classi cation in the Fourier and time-frequency correlation domains", In Neural Engineering, 2003. Conference Proceedings. First International IEEE EMBS Conference on, IEEE, pp. 591-594 (2003).38. Subasi, A. and Gursoy, M.I. EEG signal classi cation
using PCA, ICA, LDA and support vector machines", Expert Systems with Applications, 37(12), pp. 8659- 8666 (2010).
39. Bennett, K.P. and Campbell, C. Support vector machines: hype or hallelujah?", ACM SIGKDD Explorations Newsletter, 2(2), pp. 1-13 (2000). 40. Lotte, F., Congedo, M., Lecuyer, A., Lamarche, F., and Arnaldi, B. A review of classi cation algorithms for EEG-based brain-computer interfaces", Journal of Neural Engineering, 4(2), pp. R1-R13 (2007).
41. Nicolas-Alonso, L.F. and Gomez-Gil, J. Brain computer interfaces, a review", Sensors, 12(2), pp. 1211- 1279 (2012).
42. Bhattacharyya, S., Khasnobish, A., Chatterjee, S., Konar, A., and Tibarewala, D.N. Performance analysis of LDA, QDA and KNN algorithms in left-right limb movement classi cation from EEG data", In Systems in Medicine and Biology (ICSMB), 2010 International Conference on, IEEE, pp. 126-131 (2010). 43. Kayikcioglu, T. and Aydemir, O. A polynomial  tting and k-NN based approach for improving classi cation of motor imagery BCI data", Pattern Recognition
Letters, 31(11), pp. 1207-1215 (2010).  44. Shyu, K.-K., Chiu, Y.-J., Lee, P.-L., Lee, M.-H., Sie, J.-J., Wu, C.-H., Wu, Y.-T., and Tung, P.-C. Total design of an FPGA-based braincomputer interface control hospital bed nursing system", IEEE Transactions on Industrial Electronics, 60(7), pp. 2731-2739 (2013). 45. Feng, C.-W., Hu, T.-K., Chang, J.-C., and Fang, W.-
C. A reliable brain computer interface implemented on an FPGA for a mobile dialing system", 2014 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE (2014). 46. Shyu, K.-K., Lee, P.-L., Lee, M.-H., Lin, M.-H., Lai, R.-J., and Chiu, Y.-J. Development of a lowcost FPGA-based SSVEP BCI multimedia control system", IEEE Transactions on Biomedical Circuits and Systems, 4(2), pp. 125-132 (2010). 47. Kais, B., Gha ari, F., Romain, O., and Djemal, R. An embedded implementation of home devices control  system based on brain computer interface", 26th International Conference on Microelectronics (ICM), IEEE (2014). 48. Belwa , K., Gha ari, F., Djemal, R., and Romain, O. A hardware/software prototype of EEG-based BCI system for home device control", Journal of Signal Processing Systems, pp. 1-17 (2016). 49. Liao, L.-D., Wang, I.-J., Chang, C.-J., Lin, B.- S., Lin, C.-T., and Tseng, K.C. Human cognitive
application by using wearable mobile brain computer interface", In 2010 IEEE Region 10 Conference TENCON, pp. 346-351 (2010). https://ieeexplore. ieee.org/abstract/document/5686646 50. Shyu, K.-K., Lee, P.-L., Lee, M.-H., Lin, M.-H.,
Lai, R.-J., and Chiu, Y.-J. Development of a lowcost FPGA-based SSVEP BCI multimedia control system", IEEE Transactions on Biomedical Circuits and Systems, 4(2), pp. 125-132 (2010). 51. Gao, X., Xu, D., Cheng, M., and Gao, S. A
BCI-based environmental controller for the motiondisabled", IEEE Transactions on Neural Systems and Rehabilitation Engineering, 11(2), pp. 137-140 (2003). 52. Shyu, K.-K., Chiu, Y.-J., Lee, P.-L., Lee, M.-H., Sie, J.-J., Wu, C.-H., Wu, Y.-T., and Tung, P.-C. Total design of an FPGA-based braincomputer interface control hospital bed nursing system", IEEE Transactions on Industrial Electronics, 60(7), pp. 2731-2739 (2013). 53. BCI Competitions: http://www.bbci.de/competition.
54. http://www.bbci.de/competition/iii/results/ 55. http://www.bbci.de/competition/iv/results/ 56. Niedermeyer, E. and da Silva, F.L., Electroencephalography: Basic Principles, Clinical Applications, and Related Fields, Lippincot Williams and Wilkins (2004). 57. Yates, R. and Lyons, R. DC Blocker Algorithms [DSP Tips & Tricks]", IEEE Signal Processing Magazine,
25(2), pp. 132-134 (2008). 58. Babiloni, F., Cincotti, F., Carducci, F., Rossini, P.M., and Babiloni, C. Spatial enhancement of EEG data by surface Laplacian estimation: the use of magnetic resonance imaging-based head models", Clin Neurophysiol,  112(5), pp. 724-727 (2001). 59. Murugappan, M., Nagarajan, R., and Yaacob, S. Combining spatial  ltering and wavelet transform for classifying human emotions using EEG Signals", Journal of Medical and Biological Engineering, 31(1), pp. 45-51 (2011). 60. Pfurtscheller, G. and Da Silva, F.H.L event-related EEG/MEG synchronization and  esynchronization:  asic principles", Clinical Neurophysiology, 110(11), pp. 1842-1857 (1999).  61. Hashimoto, Y. and Ushiba, J. EEG-based classi cation of imaginary left and right foot movements using  beta rebound", Clinical Neurophysiology, 124(11), pp.2153-2160 (2013). 62. Dennis, J., McFarland, Lynn M., McCane, Stephen V,. David, Jonathan R., Wolpaw, Spatial  lter selection for EEG-based communication", Electroencephalography and Clinical Neurophysiology, pp. 386-394 (1997). 63. Tian, L., Erdogmus, D., Adami, A., Pavel, M., and Mathan, S., Salient EEG channel selection in brain
computer interfaces by mutual information maximization", in Proc. IEEE/ EMBS, pp. 7064-7067 (2005). 64. Shadvar, A. Dimension Reduction by Mutual Information FEATURE EXTRACTION", International Journal of Computer Science & Information Technology (IJCSIT), 4(3), pp. 13-24 (June 2012). 94 A. Malekmohammadi et al./Scientia Iranica, Special Issue on: Socio-Cognitive Engineering 26 (2019) 72{94 65. Balagani, K.S. and Phoha, V.V. On the feature selection criterion based on an approximation of multidimensional mutual information", in IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(7), pp. 1342-1343 (July 2010). 66. Friedman, J., Hastie, T., and Tibshirani, R., The Elements
of Statistical Learning, Data Mining, Inference, and Prediction, Springer, Second Edition (2008). 67. Nicolas-Alonso, L.F. and Gomez-Gil, J. Brain computer interfaces, a review", Sensors, Molecular Diversity Preservation International, 12(2), pp. 1211-1279 (2012). 68. Burges, C.J.C. A tutorial on support vector machines for pattern recognition", Data Min. Knowl. Discov., 2, p. 121167 (1998). 69. Allison, B., Graimann, B., and Pfurtscheller, G. Brain-computer interfaces: Revolutionizing humancomputer interaction", a chapter of Digital Signal Processing and Machine Learning, Springer Science & Business Media (2010).