Cyber-Physical System Control Based on Brain-Computer Interface
The study describes approaches of direct and supervisory control of cyber-physical systems based on a brain-computer interface. The interface is the main component of the control system, performing electroencephalographic signal decoding, which includes several steps: filtering, artefact detection, feature extraction, and classification. In this study, a classifier based on deep neural networks was developed and applied. Description of the classifiers based on convolutional neural network is given. The developed classifier demonstrated accuracy 73 ± 5% of decoding four classes of imaginary movements. Prospects of using non-invasive brain-computer interface for control of cyber-physical systems, in particular, mobile robots for maintenance of immobilized patients and devices for rehabilitation of post-stroke patients are discussed.
KeywordsBrain-computer interface Neural networks Classifying
The work was financially supported by RFBR grant 16-29-08296.
- 3.Frolov, A.A., Roshin, V.U.: Brain-computer interface. Reality and perspectives. In: Scientific Conference on Neuroinformatic MIFI 2008. Lections on Neuroinformatic (2008). (in Russian). http://neurolectures.narod.ru/2008/Frolov-2008.pdf
- 4.Kaplan, A.Ya., Kochetkov, A.G., Shishkin, S.L., et al.: Experimental-theoretic bases and practical realizations of technology “Brain-computer interface”. Sibir. Med. Bull. 12(2), 21–29 (2013). (in Russian)Google Scholar
- 5.Brunner, C., et al.: BNCI Horizon 2020: towards a roadmap for BCI community / Brain-Computer Interfaces. Taylor&Fransis Group (2015). ( https://doi.org/10.1080/232623x.2015.1008956)
- 6.Frolov, A.A., et al.: Principles of motor recovery in post-stroke patients using hand exoskeleton controlled by the brain-computer interfaces based on motor imagery. CNU FIS (2017). ( https://doi.org/10.14311/nnw.2017.27.006)
- 8.Duvinage, M., et al.: Performances of Emotive Epoc headset for P-300 based applications. BioMed. Eng. Online 12, 56 (2013). (https://www.biomedical-engineering-online.com/content/12/1/56)
- 12.Muhi, C., et al.: Bacteria Hunt. J. Multimodal User. Interfaces 4, 11–25 (2010)Google Scholar
- 13.Cincotti, F., Mattia, D., Aloise, F., Bufalari, S., Schalk, G., Oriolo, G.: Non-invasive brain-computer interface system: towards its application as assistive technology. Brain Res. Bull. 75, 796–803 (2008). https://doi.org/10.1016/j.brainresbull.2008.01.007CrossRefGoogle Scholar
- 14.Conradi, J., Blankertz, B., Tangermann, M., Kunzmann, V., Curio, G.: Brain-computer interfacing in tetraplegic patients with high spinal cord injury. Int. J. Bioelectromagn. 11, 65–68 (2009)Google Scholar
- 18.Ball, T., et al.: Deep Learning with convolution neural networks for brain mapping and decoding of movement-related information from the human EEG. Preprint arXiv:1703.05051v5 [cs.LG] 8 June 2018
- 19.Stankevich, L.A., Sonkin, K.M., Shemyakina, N.V., Nagornova, Zh.V., Khomenko, Ju.G., Perts, D.S., Koval, A.V.: Development of the real-time brain-computer interface based on the neurological committee of EEG signal classifiers. In: Proceedings of the XVIII International Conference “Neuroinformatics-2016”, Moscow, 25–29th April 2016, vol. 3, pp. 172–183 (2016). (in Rus)Google Scholar
- 20.Sonkin, K.M., Stankevich, L.A., Khomenko, Ju.G., Nagornova, Zh.V., Shemyakina, N.V., Koval, A.V., Perets, D.S.: Neurological classifier committee based on artificial neural networks and support vector machine for single-trial eeg signal decoding. In: Advances in Neural Networks, pp. 100–107. ISNN-2016 (2016)Google Scholar
- 21.Stankevich, L., Sonkin, K.: Human-robot interaction using brain-computer interface based on EEG signal decoding. In: First International Conference, ICR-2016. Budapest, Hungary, 24–26 April, 2016. Lecture Notes on AI, vol. 9812, pp. 99–106. Springer (2016)Google Scholar