M.A. Petrov1, A.M. Akkanen2, A.N. Briko3

1,3 Center for Cybernetic Medicine and Neuroprosthetics, Federal Center of Brain Research and Neurotechnologies, Federal Medical Biological Agency (Moscow, Russia)

1,2,3 FSAEI HE “Bauman Moscow State Technical University” (Moscow, Russia)

1 elon.makc@gmail.com, 2 artem.akkanen@mail.ru, 3 briko@bmstu.ru

Modern methods for the medical rehabilitation of patients with spinal cord injuries require feedback algorithms. Despite the advantages of electrophysiological methods, a limitation is their incompatibility with stimulation-based rehabilitation technologies. This creates a need to develop methods for assessing rehabilitation efficacy and adaptive algorithms for electrical stimulation systems.

The aim of the study is to develop an algorithm for determining gait cycle phases based on kinematic data from inertial measurement units, enabling the identification of gait phase onset and the automatic segmentation of signals using recorded quaternions.

An algorithm was developed and validated for the automatic detection and labeling of gait cycle phases during walking on a flat, straight surface, based on quaternions obtained from inertial measurement units. Signal extrema corresponding to the onset of each gait phase were identified. Experiments with volunteers demonstrated the algorithm's effectiveness, versatility, and speed.

The developed algorithm can be integrated to provide feedback in rehabilitation systems that are incompatible with electrophysiological data recording methods.

Petrov M.A., Akkanen A.M., Briko A.N. Method for automatic determination and labeling of gait cycle phases based on inertial measurement units data // Biomedical Radioelectronics. 2026. V. 29. № 6. P. 126−130. DOI: https://doi.org/10.18127/j15604136-202606-21

1. Tao W., Liu T., Zheng R., Feng H. Gait analysis using wearable sensors. Sensors. 2012. V. 12. № 2. P. 2255–2283. DOI: 0.3390/s120202255.
2. Markov M.E., Varlashin V.V. Software development for identifying human gait phases.. In Nedelya Nauki SPbPU. 2020. P. 50–52.
3. Skvortsov D.V. Clinical Motion Analysis. Gait Analysis. Ivanovo. Russia: NPTs “Stimul”. 1996.
4. Perry J., Burnfield J. Gait Analysis: Normal and Pathological Function. Boca Raton, FL, USA: CRC Press, 2024. DOI: 10.1201/9781003525592.
5. Díaz S., Stephenson J.B., Labrador M.A. Use of wearable sensor technology in gait, balance, and range of motion analysis. Applied Sciences. 2019. V. 10. № 1. P. 234. DOI: 10.3390/app10010234.
6. Jiang X., Chu K.H.T., Khoshnam M., Menon C. A wearable gait phase detection system based on force myography techniques. Sensors. 2018. V. 18. № 4. P. 1279. DOI: 10.3390/s18041279.
7. Gujarathi T., Bhole K. Gait analysis using IMU sensor. In 2019 10th International Conference on Computing. Communication and Networking Technologies (ICCCNT). Piscataway. NJ, USA: IEEE. 2019. P. 1–5. DOI: 10.1109/ICCCNT45670.2019.8944545.
8. González-Islas J.C., Domínguez-Ramírez O.A., López-Ortega O. Biped gait analysis based on forward kinematics modeling using quaternions algebra. Revista Mexicana de Ingeniería Biomédica. 2020. V. 41. № 3. DOI: 10.17488/rmib.41.3.4.
9. Sprager S., Juric M.B. Inertial sensor-based gait recognition: A review. Sensors, 2015.V. 15. № 9. P. 22089–22127. DOI: /10.3390/s150922089.