A Review of Electroencephalography Brain-Machine Interfaces of Dynamic Modeling

Öz

The rapid development of neural activity imaging and analysis techniques in neuroscience in recent years has helped us to understand how information is processed in neural networks in the brain. Thanks to the new approaches and developments related to the organization and functioning of neural networks, medical neurological conditions that seem impossible to solve can be treated, and radical new communication systems and medical prostheses can be made that can improve the quality of life for thousands of people with motor and communication deficiencies. Brain-Machine or Brain-Computer Interfaces (BBA) is a new field of research that has made rapid progress in the last 10-15 years. Noninvasive electroencephalography (EEG) imaging, functional magnetic resonance imaging, and visual memory of subjects were found to be successful. Since statistical neural activity dynamic models have been successful in the analysis and interpretation of neural activity in the brain in basic neuroscience, this study focused on the dynamic modeling used in EEG BBA neural activity data. In the future, both in the international arena with the study of health used in Turkey, civilian and military applications with walking prosthesis, decision making systems or semi-automatic robot and help to control devices such as camera systems or provides high-level control of complete BBA solution developed in Turkey to will contribute.

Anahtar Kelimeler

• Brain-computer interface, electroencephalography, neuroprosthetics, neuroimaging, machine learning, computational neuroscience, scientific computing

Elektroensefalografi Beyin-Makine Arayüzlerin Modellemesi

Öz

Nörobilimdeki nöral aktivite görüntüleme ve analiz tekniklerinin son yıllarda hızlı gelişimi, bilginin beyindeki sinir ağlarında nasıl işlendiğini anlamamıza yardımcı olmuştur. Sinir ağlarının düzeni ve işleyişi hakkında elde edilen yeni yaklaşımlar ve bunlara bağlı gelişmeler sayesinde çözümlenmesi imkansız gibi görünen tıbbi nörolojik durumlar tedavi edilebilecek, motor ve iletişim yetersizliği olan binlerce insan için hayat kalitesini iyileştirebilecek radikal yeni iletişim sistemleri ve tıbbi protezler yapılabilecektir. Beyin-Makine ya da Beyin-Bilgisayar Arayüzleri (BBA) son 10-15 yılda hızlı ilerlemeler kaydeden yeni bir araştırma alanıdır. Noninvaziv elektroensefalografi (EEG) görüntüleme, fonksiyonel manyetik rezonans görüntüleme, deneklerin görsel hafızaları üzerinde başarılı sonuçlar verebileceği görülmüştür. Bu çalışmada, EEG beyin aktivite görüntüleme tekniğini kullanan BBA sistemlerinin pratik uygulamaları ve etkinliğini artırmak için için verimli istatistiksel nöral veri analiz teknikleri ve BBA deneysel tasarımları incelenmiştir. İstatistiksel nöral aktivite dinamik modelleri, temel nörobilimde beyindeki nöral aktivite analizi ve yorumlanmasında son yıllarda başarılı olduğundan bu çalışmada EEG BBA nöral aktivite verilerin kullanan dinamik modelleme üzerinde yoğunlaşılmıştır. Bu çalışma hem uluslararası alanda hem de Türkiye’de kullanılan sağlık, sivil ve askeri uygulamalar ile yürüme protezleri, karar verme sistemleri veya yarı otomatik robot ve makine sistemleri gibi cihazların kontrolüne yardımcı veya yüksek seviye kontrolü sağlayan komple BBA çözümlerinin Türkiye’de geliştirilmesine katkıda bulunacaktır.

Anahtar Kelimeler

• elektroensefalografi
• Beyin-bilgisayar arayüzeyi
• sinirsel protezler
• makine öğrenme
• bilgisayarlı nörobilim

Kaynakça

1. [1] Weigel, M., Yavorskii, T. GPU accelerated Monte Carlo simulations of lattice spin models, Physics Procedia 15,92-96. 2011.
2. [2] Arampatzis, G., Katsoulakis, M. A., Plecháč, P., Taufer, M., Xu, L. Hierarchical fractional-step approximations and parallel kinetic Monte Carlo algorithms, Journal of Computational Physics 231, 7795-7814, 2012.
3. [3] Ciresan, D., Meier, U., Schmidhuber, J., in Computer Vision and Pattern Recognition, 2012 Proceedings. IEEE Conference on, pp. 3642-3649. 2012.
4. [4] Huang, G.-B., Wang, D. H., Lan, Y., Extreme learning machines: a survey, International Journal of Machine Learning and Cybernetics 2, 107-122. 2011.
5. [5] Ma, X., Huang, X., Shen, Y., Qin, Z., Ge, Y., Chen, Y., EEG based topography analysis in string recognition task. Physica A: Statistical Mechanics and its Applications, 469, 531-539, 2017.
6. [6] Makeig, S., Onton, J., in Oxford Handbook of Event-Related Potential Components, Oxford, New York, NY, 2009.
7. [7] Wu, W., Chen, Z., Gao, S., Brown, E. A hierarchical Bayesian approach for learning sparse spatio-temporal decompositions of multichannel EEG, Neuroimage 56, 1929-1945. 2011.
8. [8] Jones, L. M., Fontanini, A., Sadacca, B. F., Miller, P. D., Katz, B. Natural stimuli evoke dynamic sequences of states in sensory cortical ensembles, Proceedings of National Academy of Sciences 104, 18772-18777. 2007.

9. [9] Katz, D. B. in The Dynamic Brain: An Exploration of Neuronal Variability and Its Functional Significance, M. Ding, D. Glanzman, Eds. Oxford Scholarship Online, 2011.
10. [10] Miller, P., Katz, D. B. Stochastic transitions between neural states in taste processing and decision-making, Journal of Neuroscience 30, 2559-2570, 2010.
11. [11] Huys, Q. J. M. Q., Ahrens, M. B. M., Paninski, L. Efficient estimation of detailed single-neuron models, Journal of Neurophysiology 96, 872-890. 2006.
12. [12] Paninski ve ark., L. A new look at state-space models for neural data, Journal of computational neuroscience 29, 107-126, 2010.
13. [13] Pillow ve ark., J. W. Spatio-temporal correlations and visual signalling in a complete neuronal population, Nature 454, 995-999, 2008.
14. [14] Pillow, J. W., Paninski, L., Uzzell, V. J., Simoncelli, E. P., Chichilnisky, E. Prediction and decoding of retinal ganglion cell responses with a probabilistic spiking model, Journal of Neuroscience 25, 11003. 2005.
15. [15] Fetz, E. E., Operant conditioning of cortical unit activity, Science 163, 955-8, 1969.
16. [16] Gupta, N., Gupta, S., Khare, V., Jain, C.K., Akhter, S. An Efficient Model to Decipher the Electroencephalogram Signals Using Machine Learning Approach, IFMBE Proceedings 21, 782-785, 2008.
17. [17] Jurcak, V., Tsuzuki, D., Dan, I. 10/20, 10/10, and 10/5 Systems Revisited: Their Validity As Relative Head-Surface-Based Positioning Systems., NeuroImage 34, 1600-11. 2007.
18. [18] McFarland, D.J., Sarnacki, W., Wolpaw, J.R. Electroencephalographic, EEG control of three-dimensional movement., Journal of neural engineering 7, 036007, 2010.
19. [19] Kaya, M., Cömert, M., Mishchenko, Y., Beyin bilgisayar arayüzü için dvm makine öğrenme yöntemi kullanılarak eeg verilerinden sağ ve sol el hareket düşüncelerinin tespiti, TÜBAV, 10:3, 1-20, 2017.
20. [20] Blankertz, B., Dornhege, G., Krauledat, M., Müller, K., Curio, G. The non-invasive Berlin Brain–Computer Interface: Fast acquisition of effective performance in untrained subjects, Neuroimage 37, 539-50. 2007.
21. [21] Blankertz ve ark., B. The Berlin Brain-Computer Interface: EEG-based communication without subject training, IEEE Trans. on Neural Systems and Rehabilitation Engineering 14, 147-152, 2006.
22. [22] Barbosa, A. O., Diaz, G. D. R. A., Vellasco, M. M. B. R., Meggiolaro, M. A., Tanscheit, R. Mental Tasks Classification for a Noninvasive BCI Application, Lecture Notes in Computer Science 5769, 495–504 .2009.
23. [23] Wu, L.W., Liao, H.C., Hu, J.S., Lo, P. C. Brain-controlled robot agent: an EEG-based eRobot agent, Industrial Robot: An International Journal 35, 507–519. 2008.
24. [24] Chae, Y., Jeong, J., Jo, S. Toward Brain-Actuated Humanoid Robots: Asynchronous Direct Control Using an EEG Based BCI, IEEE Transactions on Robotics 28, 1131-1144. 2012.
25. [25] Cincotti ve ark., F. Non-invasive brain-computer interface system: towards its application as assistive technology., Brain research bulletin 75, 796-803. 2008.
26. [26] Benevides, A. B., Filho, T. F. B., Sarcinelli-Filho, M., Pseudo-Online Classification of Mental Tasks Using Kullback-Leibler Symmetric Divergence, Journal of Medical and Biological Engineering 32, 411-416. 2012.
27. [27] Benevides, A. B., Bastos, T. F., Sarcinelli-Filho, M. in 2011 IEEE International Symposium on Circuits and Systems, IEEE, pp. 81-84, 2011
28. [28] Rodríguez-Bermúdez, G., García-Laencina, P. J., Roca-González, J., Roca-Dorda, J. Efficient feature selection and linear discrimination of EEG signals, Neurocomputing 115, 161–165. 2013.
29. [29] Cho, H, Ahn, M, Ahn, S, Kwon, M, ve Jun, S. EEG datasets for motor imagery brain computer interface, Gigascience, 2017.
30. [30] Ferreira ve ark., A. Improvements of a Brain-Computer Interface Applied to a Robotic Wheelchair, Communicationsin Computer and Information Science 52, 64–73. 2010.
31. [31] Ergün, E., Aydemir Ö., Etkin epoklar ile motor hayaline dayalı EEG işaretlerinin sınıflandırma doğruluğunun artırılması, Pamukkale Univ Muh Bilim Derg, 24(5), 817-823, 2018.
32. [32] Belwafi, K., Gannouni, S., Aboalsamh, H., Mathkour, H., Belghith, A. (2019). A dynamic and self-adaptive classification algorithm for motor imagery EEG signals, Journal of Neuroscience Methods, 327
33. [33] Tarana, S., Bajaja, V., Sharmaa, D., Siulyb, S., Sengurc, A. (2018). Features based on analytic IMF for classifying motor imagery EEG signals in BCI applications, Measurement, 116, 68–76
34. [34] Zhua, X., Lia, P., Lia, C., Yaoa, D., Zhangd, R., Xu, P. (2019). Separated channel convolutional neural network to realize the training free motor imagery BCI systems, Biomedical Signal Processing and Control 49, 396–403
35. [35] Kaura, B., Singha, D., Royb, P. P., EEG Based Emotion Classification Mechanism in BCI, Procedia Computer Science, 132, 752–758, 2018
36. [36] Özmen, N. G., Durmuş, E., Sadreddini, Z., Müzik siniflandirmasi beyin bilgisayar arayüzü uygulamalari için bir alternatif olabilir mi?, Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, 22: 2, 2017.
37. [37] Boyd, S. Convex Optimization, Cambridge University Press, 2009, p. 716.
38. [38] Burges, C. J. CA Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and KnowledgeDiscovery 2, 121–167. 1998.
39. [39] Mcfarland, D. J., Wolpaw, J. R. Sensorimotor rhytm-based brain-computer interface.BCI: model order selectionfor autoregressive spectral analysis, Journal of Neural Engineering 5, 155–162. 2008.
40. [40] Friedrich ve ark., E. V. C. A scanning protocol for sensorimotor rhytm-based brain computer interface, BiologicalPsychology 80, 169–175, 2009.
41. [41] MacKay, D. Information Theory, Inference and Learning Algorithms. Cambridge University Press, 2003, 628.
42. [42] Zaffalon, M., Hutter, M. in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence, 2002, pp. 577–584.
43. [43] Wand, M., Jones, M. C. Kernel Smoothing, Chapman & Hall/CRC, London, 1995.
44. [44] Erkan, E., Akbaba, M. (2018). A study on performance increasing in SSVEP based BCI application, Engineering Science and Technology an International Journal, 21, 421–427
45. [45] Peng, H., Long, F., Ding, C. Feature selection based on mutual information criteria of max-dependency, maxrelevance and min-redundancy., IEEE transactions on pattern analysis and machine intelligence 27, 1226–1238. 2005.
46. [46] Wolpaw, J. R., McFarland, D. J. Control of a two-dimensional movement signal by a noninvasive brain-computer inter face in humans., Proceedings of the National Academy of Sciences of the United States of America 101, 17849-54, 2004.
47. [47] Bradberry, T. J., Gentili, R. J., Contreras-Vidal, J. L. Reconstructing Three-Dimensional Hand Movements from Noninvasive Electroencephalographic Signals, The Journal of Neuroscience 30, 3432–3437, 2010.
48. [48] Bradberry, T. J., Gentili, R. J., Contreras-Vidal, J. L. Fast attainment of computer cursor control with noninvasively acquired brain signals, Journal of neural engineering 8, 036010, 2011.
49. [49] Bell, C. J., Shenoy, P., Chalodhorn, R., Rao, R. P. N. Control of a humanoid robot by a noninvasive brain-computer interface in humans., Journal of neural engineering 5, 214–20. 2008.
50. [50] Perrin, X., Chavarriaga, R., Colas, F., Siegwart, R., Millán, J. D. R. Brain-coupled interaction for semi-autonomousnavigation of an assistive robot, Robotics and Autonomous Systems 58, 1246–1255. 2010.
51. [51] Bastos, T.F., Muller, S.M.T.A.B. Benevides, M. Sarcinelli Filho, in Conference proceedings : Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, 2011, pp.4753-4756.
52. [52] Chung, M., Cheung, W., S cherer, R., Rao, R. P. N. in Proceedings of the 5th Int. IEEE EMBS Conf. on Neural Engineering, 2011, pp. 330–333.
53. [53] Zhang, Y., Yin, E., Li, F., Zhang, Y., Guo, D., Yao, D.,Xu, P. (2019). Hierarchical feature fusion framework for frequency recognition in SSVEP-based BCIs, Neural Networks, 119, 1–9.
54. [54] Kayikçioğlu T., Maleki, M., Ketenci S., Beyin-Bilgisayar Arayüzü, TMMOB Elektrik Mühendisleri Odası, Biyomedikal Mühendisliği ve Uygulamaları, 2018
55. [55] Ron-Angevin, R., Velasco-Alvarez, F., Sancha-Ros, Silva-Sauer, S. L. in IEEE International Conference on Rehabilitation Robotics, 1–6, 2011 [56] Schmidt, E. M. Single neuron recording from motor cortex as a possible source of signals for control of external devices, Annals of Biomedical Engineering 8, 339–49, 1980.
56. [57] Jia ve ark., W. in IEMBS’04. 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Societ, 5–8, 2004
57. [58] Anemuller, J., Sejnowski, T. J., Makeig, S. Complex independent component analysis of frequency-domainelectroencephalographic data, Neural Networks 16, 1311. 2003.
58. [59] Oostendorp, T., Delbeke, J., Stegeman, D. The conductivity of the human skull: results of in vivo and in vitromeasurements., IEEE Transactions on Biomedical Engineering 47, 1487–1492. 2000.
59. [60] Amari, S. Dynamics of pattern formation in lateral-inhibition type neural fields, Biological Cybernetics 27, 77–87. 1977.
60. [61] Bressloff, P. C. Spatiotemporal dynamics of continuum neural fields, Journal of Physics A, 45, 033001. 2012.
61. [62] Izhikevich, E. M., Edelman, G. M., Large-scale model of mammalian thalamocortical systems, Proceedings of National Academy of Sciences 105, 3593-3598. 2008.
62. [63] Shah ve ark., A. S. Neural Dynamics and the Fundamental Mechanisms of Event-related Brain Potentials, Cerebral Cortex 14, 476–483. 2004.
63. [64] Amari, S., Field Theory of Self-Organizing Neural Nets Field Theory of Self-Organizing Neural Nets, IEEETRans. on Systems, Man, and Cybernetics 13, 741. 1983.
64. [65] Bressloff, P., Webber, C. M., Neural field model of binocular rivalry waves, Journal of computational neuroscience 32, 233-52, 2012.
65. [66] Rabiner, L. A tutorial on hidden Markov models and selected applications in speech recognition, Proceedings of the IEEE 77, 257-286. 1989.[1] Weigel, M., Yavorskii, T. GPU accelerated Monte Carlo simulations of lattice spin models, Physics Procedia 15,92-96. 2011.
66. [67] Rabiner, L., Juang, B. An introduction to hidden Markov models., ASSP Magazine, IEEE 3, 4-16. 1986.
67. [68] Bilmes, J. A. A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for GaussianMixture and Hidden Markov Models, International Computer Science Institute 4, 1-13. 1998.
68. [69] Minka, T. P. in Uncertainty in Artificial Intelligence, Citeseer, 2001, 17, pp. 362-369.
69. [70] Ng, B., Pfeffer, A., Dearden, R., Brenda, N. D. in International Joint Conference on Artificial Intelligence, Citeseer, 2005, 19, pp. 1360.
70. [71] Fearnhead, P., Clifford, P. On-line inference for hidden Markov models via particle filters, Journal of the RoyalStatistical Society. Series B, Statistical Methodology 65, 887–899, 2003.
71. [72] Paninski ve ark., L. A new look at state-space models for neural data, Journal of computational neuroscience 29, 07-126, 2010.
72. [73] Mishchenko, Y., Vogelstein, J., Paninski, L. A Bayesian approach for inferring neuronal connectivity from calciumfluorescent imaging data, Annals of Applied Statistics 5, 1229-1261, 2011.