An autocoder of the electrical activity of the human brain

R. V. Meshcheryakov   ; D. A. Volf   ; Y. A. Turovsky

Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ, Matematika, mehanika, fizika, Tome 15 (2023) no. 1, pp. 34-42

Résumé

The authors identify hidden parameters of the function describing the electrical activity of the human brain, obtained using electroencephalography (EEG), with the help of an artificial neural network and deep machine learning. The compression of applied information, necessary to reduce the dimensionality of the feature space of the data in order to obtain a model of an artificial neural network-an autoencoder is formulated. The novelty of the general solution and the theoretical aspects and problems of existing compression methods are described. An experimental study is carried out, which consists in obtaining an autoencoder model using applied data EEG sequences containing visual evoked potentials. The compression problem is solved by decreasing the dimensionality of the multidimensional vector associated with the sample. The autoencoder encodes the original multi-dimensional vector into a vector of smaller dimensionality. Using deep machine learning, a coding function is found such that reverse decoding into the original vector can be performed. As a result of the empirical selection of the vector dimensionality, the best experimental model of the autoencoder was chosen, which compresses the feature space of dimensionality equal to 1260 (in the initial sense EEG signals of duration 0,2 s) to a 24-dimensional space, with the possibility of the reconstruction of the initial signal with losses of not more than 10 %.

Détail

Keywords: brain-computer interface, electroencephalogram, EEG, control, feature dimensionality reduction, evoked potentials, encoding.
Mots-clés : BCI, autoencoder

Bibliographie

[1] D.A. Novikov, “Kibernetika 2.0”, Problemy upravleniya, 2016, no. 1, 73–81

[2] S. Kharchenko, R. Meshcheryakov, Y. Turovsky, D. Volf, “Implementation of Robot-Human Control Bio-Interface when Highlighting Visual-Evoked Potentials Based on Multivariate Synchronization Index”, Smart Innovation, Systems and Technologies, 187 (2021), 225–236 | DOI

[3] L.A. Gridin, A.V. Bogomolov, Yu.A. Kukushkin, “Metodologicheskie osnovy issledovaniya fizicheskoi rabotosposobnosti cheloveka”, Aktualnye problemy fizicheskoi podgotovki silovykh struktur, 2011, no. 1, 10–19

[4] M.V. Gerven, J. Farquhar, R. Schaefer et al., “The Brain Computer Interface Cycle”, Journal of Neural Engineering, 6:4 (2009), 1–10 | DOI

[5] M.V. Dvornikov, Yu.A. Kukushkin, A.V. Bogomolov, T.V. Matyushev, “Tekhnologiya sinteza zakonov upravleniya cheloveko-mashinnymi sistemami, ekspluatiruemymi v usloviyakh vysokogo riska gipoksicheskikh sostoyanii cheloveka”, Dvoinye tekhnologii, 2014, no. 1 (66), 8–11

[6] A.O. Iskhakova, D.A. Volf, A.Yu. Iskhakov, “Neinvazivnyi neirokompyuternyi interfeis dlya upravleniya robotom”, Vysokoproizvoditelnye vychislitelnye sistemy i tekhnologii, 5:1 (2021), 166–171

[7] A.G. Guzii, A.V. Bogomolov, Yu.A. Kukushkin, “Teoreticheskie osnovy funktsionalno-adaptivnogo upravleniya sistemami «chelovek-mashina» povyshennoi avariinosti”, Mekhatronika, avtomatizatsiya, upravlenie, 2005, no. 1, 39–45

[8] A.O. Iskhakova, M.D. Alekhin, A.V. Bogomolov, “Vremya-chastotnye preobrazovaniya v analize patternov nestatsionarnykh kvaziperiodicheskikh biomeditsinskikh signalov dlya zadach identifikatsii akusticheskikh anomalii”, Informatsionno-upravlyayuschie sistemy, 2020, no. 1 (104), 15–23

[9] N. Tishby, C.P. Fernando, B. William, The information bottleneck method, 2000, arXiv: physics/0004057

[10] T. Tao, X. Yi, G. Xiaorong, G. Shangkai, “Chirp-Modulated Visual Evoked Potential as a Generalization of Steady State Visual Evoked Potential”, Journal of neural engineering, 9:1 (2011), 016008 | MR

[11] N.S. Kwak, K.R. Müller, S.W. Lee, “Toward Exoskeleton Control Based on Steady State Visual evoked potentials”, International Winter Workshop on Brain-Computer Interface, BCI 2014 (Gangwon, Korea, 2014)

[12] R. Balnytė, I. Uloziene, D. Rastenytė et al., “Diagnostic Value of Conventional Visual Evoked Potentials Applied to Patients With Multiple Sclerosis”, Medicina, 47:5 (2011), 263–269

[13] O. Markand, “Visual Evoked Potentials”, Clinical Evoked Potentials, 2020, 83–137, Springer, Cham | DOI

[14] U. Chaudhary, N. Birbaumer, M.R. Curado, “Brain-Machine Interface (BMI) in paralysis”, Annals of Physical and Rehabilitation Medicine, 58:1 (2015), 9–13 | DOI

[15] H. Nguyen, S. Bottone, K. Kim et al., “Adversarial Neural Networks for Error Correcting Codes”, 2021 IEEE Global Communications Conference (GLOBECOM) (7-11 December 2021, Madrid, Spain), 2021

[16] U. Köse, O. Deperlioglu, J. Alzubi, B. Patrut, “Diagnosing Parkinson by Using Deep Autoencoder Neural Network”, Deep Learning for Medical Decision Support Systems, Studies in Computational Intelligence, 909, Springer, Singapore, 2020, 73–93 | DOI

[17] V. Mirjalili, S. Raschka, A. Namboodiri, A. Ross, “Semi-adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images”, 2018 International Conference on Biometrics (ICB) (IEEE, Gold Coast, QLD, Australia, 2018), 82–89