V.V. Kapravchuk1, O.A. Strebkov2, A.A. Zotkina3, A.N. Briko4, M.M. Balashov5, M.Yu. Sintsov6

1,2,3,4,5,6 Center for Cybernetic Medicine and Neuroprosthetics, Federal Center of Brain Research and Neurotechnologies (Moscow, Russia)

1,2,3,4,5,6 Federal Medical Biological Agency (Moscow, Russia)

1,4 FSAEI HE “Bauman Moscow State Technical University” (Moscow, Russia)

1 kapravchuk@bmstu.ru

Multimodal biofeedback systems combining electromyography and electrical impedance myography are promising for the control of bionic prostheses. However, the quality of the recorded signals depends on individual anatomy, subcutaneous fat thickness, muscle displacement during contraction, and the degree of electrode pressure. Conventional sensor-positioning methods based on palpation or equidistant placement do not account for the morphofunctional characteristics of the tissues, thereby reducing gesture-recognition accuracy and requiring frequent system recalibration. To evaluate the effectiveness of ultrasound-assisted positioning of multimodal EMG and EIM sensors in improving the accuracy and reproducibility of gesture recognition, including fine motor movements. A study involving healthy volunteers was conducted. The electrode systems were initially placed equidistantly, after which their positions were adjusted based on ultrasound visualization of active muscle structures. Performance metrics of the biofeedback algorithm were calculated to assess gesture-classification quality. On the test dataset, ultrasound-assisted placement improved the calculated performance indicators by at least 5% compared with equidistant placement of the myographic sensors. The most pronounced increase in accuracy was observed in the recognition of finger movements. Ultrasound guidance enables personalized placement of electrode systems based on the user’s individual anatomy and improves the reliability of multimodal biofeedback interfaces. The proposed approach may be used as an additional diagnostic step when configuring bionic prostheses and other rehabilitation devices.

Kapravchuk V.V., Strebkov O.A., Zotkina A.A., Briko A.N., Balashov M.M., Sintsov M.Yu. Investigation of ultrasound-assistant electrode placement effects on gesture recognition in multimodal emg/eim systems // Biomedical Radioelectronics. 2026. V. 29. № 6. P. 80−84. DOI: https://doi.org/10.18127/j15604136-202606-14

1. Qiu F., Liu X., Ye X. Influence of electrode placement on the recognition of different gesture categories using high-density sEMG. Front. Neurosci. Frontiers. 2025. V. 19. P. 1750792.
2. Pale U. et al. Variability of muscle synergies in hand grasps: analysis of intra- and inter-session data. Sens. Multidisciplinary Digital Publishing Institute. 2020. V. 20. № 15. P. 4297.
3. Donnelly T. et al. A method for locating surface electromyography electrodes on the flexor carpi ulnaris. J. Electromyogr. Kinesiol. Elsevier, 2025. V. 82. P. 103010.
4. Olsen C.D. et al. Centimeter differences in wrist electrode placement significantly impact myoelectric performance. 2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE. 2025. P. 1–7.
5. Pelaez Murciego L. et al. Reducing the number of EMG electrodes during online hand gesture classification with changing wrist positions. J. NeuroEng. Rehabil. 2022. V. 19. № 1. P. 78.
6. Rostamjoud F. et al. Improving electromyography electrode placement accuracy in transtibial amputees: a comparative study of ultrasound and palpation methods. IEEE Trans. Neural Syst. Rehabil. Eng. IEEE. 2025. V. 33. P. 133–139.
7. Yoo H.-J., Park H., Lee B. Myoelectric signal classification of targeted muscles using dictionary learning. Sensors. MDPI, 2019. V. 19. № 10. P. 2370.
8. Ngo C. et al. A wearable, multi-frequency device to measure muscle activity combining simultaneous electromyography and electrical impedance myography. Sens. Multidisciplinary Digital Publishing Institute, 2022. V. 22. № 5. P. 1941.
9. Kapravchuk V. et al. An approach to using electrical impedance myography signal sensors to assess morphofunctional changes in tissue during muscle contraction. Biosensors. Multidisciplinary Digital Publishing Institute, 2024. V. 14. № 2. P. 76.
10. Briko A.N., Chibizov P.E., Mazeina V.S., Kapravchuk V.V., Kobelev A.V., Shchukin S.I. Ocenka effektivnosti sinteza sistem bionicheskogo upravleniya na osnove kompleksirovaniya signalov EMG, EI, MTG. Biomedicinskaya radioelektronika. 2024. T. 27. № 6. S. 20−29. DOI: https://doi.org/10.18127/j15604136-202406-02 (In Russian).