Method and Algorithms for Decoding Electrophysiological Signals in Biotechnical Systems of Rehabilitation Type

Purpose of research. Development of a method for decoding electromyosignals in control systems for exoskeletons with virtual reality, allowing to adapt the rehabilitation program of a robotic device to the functional state of the patient.

Methods. To restore the motor functions of the lower extremities of post-stroke patients, it is proposed to use a biotechnical system with a robotic device, the control of which is based on the analysis and classification of electromyosignals. The robotic device is controlled by a fuzzy neural network. The formation of the vector of informative features for the neural network is carried out by means of a multilevel comparator, the number of levels of which is determined by the dimension of the vector of informative features determined by averaging the outputs of the comparators in a sliding window. The electromyosignal decoder includes a series-connected block of comparators, a block for calculating informative features, a multiplexer, a first neural network, a memory block and a second neural network, the outputs of which are intended to be connected to a servo motor controller, and a synchronizer connected by an output to the control inputs of the multiplexer, memory unit and servo motor controller.

Results. A classifier of electromyosignals has been developed, which is characterized by the use of multiple duplicate channels of EMG signals associated with a muscle or muscle groups that control the movement of the same joint of the extremities, as a result of which, at the output of the classifier of each channel, we obtain a number corresponding to the confidence in the command to rotate the servo motor of the exoskeleton, all the outputs of the channel classifiers are fed to a fuzzy neural network, the defuzzifier of which generates a control signal to the servo motor controller. In the course of the work, a software application was written that can control the exoskeleton using the analysis of electromyosignals.

Conclusion. The study showed that it is possible to change the indicators of clinical outcome in patients with subacute stroke experience after 12 sessions of BPS training. A biotechnical system with fuzzy control of a robotic device allows for an individual strategy for the rehabilitation of post-stroke patients (including targeted walking training).

1. Al'-Bareda A. Ya. S., Brezhneva A. N., Tomakova R. A. Algoritmy sinteza optimal'nogo upravleniya v biotekhnicheskikh sistemakh reabilitatsionnogo tipa na osnove tekhnologii neironnykh setei [Algorithms for the synthesis of optimal control in biotechnical systems of rehabilitation type based on neural network technologies]. Sistemnyi analiz i upravlenie v biomeditsinskikh sistemakh = Systems Analysis and Control in Biomedical Systems, 2018, vol. 17, no. 3. pp. 750-754.

2. Trifonov A. A, Petrunina E. V., Filist S. A., Kuz'min A. A., Zhilin V. V. Biotekhnicheskaya sistema s virtual'noi real'nost'yu v reabilitatsionnykh kompleksakh s iskusstvennymi obratnymi svyazyami [Biotechnical system with virtual reality in rehabilitation complexes with artificial feedbacks]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering, 2019, vol. 9, no. 4, pp. 46-66.

3. Trifonov A., Filist S., Degtyarev S., Serebrovsky V., Shatalova O. Human-Machine Interface of Rehabilitation Exoskeletons with Redundant Electromyographic Channels. Zavalishin’s Readings. Proceedings of 15th International Conference on Electromechanics and Robotics. Ufa, 2020, pp. 237-247. https://doi.org/10.1007/978-981-15-5580-0_19

4. Filist S. A., Petrunina E. V., Trifonov A. A., Serebrovskii A. V. Kodovye obrazy signalov ehlektroehntsefalogrammy dlya upravleniya robototekhnicheskimi ustroistvami posredstvom interfeisa mozg-komp'yuter [Code images of electroencephalogram signals for controlling robotic devices via the brain-computer interface]. Modelirovanie, optimizatsiya i informatsionnye tekhnologii. Nauchnyi zhurnal = Modeling, Optimization and Information Technology. Scientific Journal, 2019, vol. 7, no. 1, pp. 67-79. https://doi.org/10.26102/2310- 6018/2019.24.1.025

5. Filist S. A., Shatalova O. V., Efremov M. A. Gibridnaya neironnaya set' s makrosloyami dlya meditsinskikh prilozhenii [Hybrid neural network with macro layers for medical applications]. Neirokomp'yutery. Razrabotka i primenenie = Neurocomputers: Development, Application, 2014, no. 6, pp. 35-39.

6. Efremov M. A., Shatalova O. V., Fedyanin V. V., Shutkin A. N. Gibridnye mnogoagentnye klassifikatory v biotekhnicheskikh sistemakh diagnostiki zabolevanii i monitoringa lekarstvennykh naznachenii [Hybrid multi-agent classifiers in biotechnical systems for the diagnosis of diseases and monitoring of medicinal prescriptions]. Neirokomp'yutery: razrabotka, primenenie = Neurocomputers: Development, Application, 2015, no. 6, pp. 42-47.

7. Trifonov A. A., Filist S. A., Kuz'min A. A., Zhilin V. V., Petrunina E. V. Dvukhurovnevaya neirosetevaya model' deshifratora ehlektromiosignala v sisteme upravleniya vertikalizatsiei ehkzoskeleta [A two-level neural network model of an electromyosignal decoder in an exoskeleton verticalization control system]. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Control and High Technologies, 2020, no. 4 (52), pp. 99-111.

8. Petrova T. V., Filist S. A., Degtyarev S. V., Kiselev A. V., Shatalova O. V. Prediktory sinkhronnosti sistemnykh ritmov zhivykh sistem dlya klassifikatorov ikh funktsional'nykh sostoyanii [Predictors of synchronicity of system rhythms of living systems for classifiers of their functional states]. Sistemnyi analiz i upravlenie v biomeditsinskikh sistemakh = Systems Analysis and Control in Biomedical Systems, 2018, vol. 17, no. 3, pp. 693-700.

9. Trifonov A. A., Kuzmin A. A., Filist S. A., Petrunina E. V. Neural network model in the exoscelete verticalization control system. Journal of Phisics: Conference Series, 2020, no. 1679, p. 032036. https://doi.org/10.1088/1742-6596/1679/3/032036.

10. Budko R. Yu., Starchenko I. B. Sozdanie klassifikatora mimicheskikh dvizhenii na osnove analiza elektromiogrammy [Creating a classifier of facial movements based on the analysis of an electromyogram]. Trudy SPIIRAN = Proceedings SPIIARAS, 2016, is. 46, pp. 76-89.

11. Kassim K. D. A., Filist S. A., Rybochkin A. F. Komp'yuternye tekhnologii obrabotki i analiza biomedicinskikh signalov i dannykh [Computer technologies for processing and analyzing biomedical signals and data]. Kursk, Southwest State University Publ., 2016. 290 p.

12. Ivanyuk N. M., Karimov V. R., Budko R.Yu., Gronskii P. V., Kleiman S. M. Sposob i sistema upravleniya intellektual'noi bionicheskoi konechnost'yu [Method and system of intelligent bionic limb control]. Patent RF, no. 2635632, 2017.

13. Molteni F., eds. Wearable robotic exoskeleton for overground gait training in subacute and chronic hemiparetic stroke patients: preliminary results. European Journal of Physical and Rehabilitation Medicine, 2017, vol. 53, no. 5, pp. 676-684. https://doi.org/ 10.23736/S1973-9087.17.04591-9.