novtexmechМехатроника, автоматизация, управлениеMekhatronika, Avtomatizatsiya, Upravlenie1684-64272619-1253Commercial Publisher «New Technologies»10.17587/mau.25.415-424novtexmech-1604Research ArticleРОБОТЫ, МЕХАТРОНИКА И РОБОТОТЕХНИЧЕСКИЕ СИСТЕМЫROBOT, MECHATRONICS AND ROBOTIC SYSTEMSАрхитектура, модели и алгоритмы обработки информации мобильной тренажерной системы для опорно-двигательной реабилитацииArchitecture, Models and Algorithms for Information Processing of a Mobile Training System for Musculoskeletal RehabilitationОбуховА. Д.ObukhovA. D.

д-р техн. наук, вед. науч. сотр.

Tambov, 392000

obuhov.art@gmail.comНазароваА. О.NazarovaA. O.

мл. науч. сотр.

Tambov, 392000

nazarova.al.ol@yandex.ruВолковА. А.VolkovA. A.

мл. науч. сотр.

Tambov, 392000

didim@eclabs.ruПатутинК. И.PatutinK. I.

мл. науч. сотр.

Tambov, 392000

kirill-patutin@mail.ruНикитниковЮ. В.NikitnikovYu. V.

студент

Tambov, 392000

unikitnikov@gmail.comМасловК. А.MaslovK. A.

студент

Tambov, 392000

kirill.MaslovTsu@yandex.ruТамбовский государственный технический университетРоссияTambov State Technical UniversityRussian Federation202409082024258415424Copyright © Commercial Publisher «New Technologies», 20242024Commercial Publisher «New Technologies»Commercial Publisher «New Technologies»https://mech.novtex.ru/jour/about/submissions#copyrightNoticehttps://mech.novtex.ru/jour/article/view/1604

Рассматривается разработка мобильной тренажерной системы для опорно-двигательной реабилитации. Анализ существующих исследований показал, что применение мобильных устройств позволяет осуществить мониторинг и оценку качества выполняемых упражнений в период амбулаторной реабилитации. Выделены основные направления реализации мобильных тренажерных систем, поставлена задача организации опорно-двигательной реабилитации с использованием мобильных устройств. Для решения поставленной задачи на первом этапе разработана архитектура мобильной тренажерной системы, проанализированы необходимые программные инструменты. Разработана модель обработки информации об упражнениях опорно-двигательной реабилитации, включающая формализацию процессов оценки упражнений и преобразования исходных данных от системы инерциальной навигации мобильного устройства для расчета скорости и траектории движения. Представлен алгоритм обработки информации, включающий необходимый перечень операций для устранения существенных недостатков мобильных датчиков (большая погрешность, шумы, накопление ошибки). Проведены экспериментальные исследования, подтверждающие эффективность реализованного алгоритма. Реализован алгоритм функционирования мобильной тренажерной системы, включающий основные этапы ее работы для организации процесса опорно-двигательной реабилитации. Проведена апробация алгоритмов обработки информации мобильной тренажерной системы, доказана их применимость для мониторинга упражнений. Научная новизна исследования заключается в разработке архитектуры, моделей и алгоритмов обработки информации в мобильной тренажерной системе для опорно-двигательной реабилитации, отличающейся учетом технических особенностей мобильных устройств. Полученные теоретические результаты (архитектура, модель и алгоритмы) использованы для программной реализации мобильной тренажерной системы для операционной системы Android. Практическая ценность проведенного исследования заключается в организации процесса амбулаторной опорно-двигательной реабилитации с применением мобильных устройств и разработанных алгоритмов обработки данных, которые позволили обеспечить достаточную точность измерения выполняемых действий.

The article discusses the development of a mobile training system for musculoskeletal rehabilitation. Analysis of existing research shows that the use of mobile devices allows for monitoring and evaluating the quality of exercises performed during outpatient musculoskeletal rehabilitation. The main directions for implementing mobile training systems were identified, and the task of organizing musculoskeletal rehabilitation using mobile devices was set. To address this task, an architecture for a mobile training system was developed, and necessary software tools were analyzed. A model for processing information about exercises in musculoskeletal rehabilitation was developed, including formalizing the processes of exercise assessment and transforming raw data from the inertial navigation system of the mobile device to calculate speed and trajectory of movement. An information processing algorithm was presented, including a list of necessary operations to eliminate significant drawbacks of mobile sensors (high error rate, noise, and error accumulation). Experimental studies were conducted to confirm the effectiveness of the algorithm. The functioning algorithm of the mobile training system, including its main stages for organizing the musculoskeletal rehabilitation process, was implemented. The algorithms for processing information from the mobile training system were tested, demonstrating their applicability for monitoring exercises. The scientific novelty of the research lies in the development of architecture, models, and information processing algorithms in the mobile training system for musculoskeletal rehabilitation, taking into account the technical characteristics of mobile devices. The theoretical results obtained (architecture, model, and algorithms) were used for the software implementation of the mobile training system for musculoskeletal rehabilitation on the Android operating system. The practical value of the conducted research lies in organizing the process of outpatient musculoskeletal rehabilitation using mobile devices and developing data processing algorithms, which have ensured sufficient accuracy in measuring actions performed.

опорно-двигательная реабилитациямобильная тренажерная системаалгоритмы обработки данныхсистемы инерциальной навигациимобильное устройствоmusculoskeletal rehabilitationmobile training systemdata processing algorithmsinertial navigation systemsmobile deviceReferencesHartford W. et al. Stroke survivors’ experiences of team support along their recovery continuum // BMC Health Services Research. 2019. Vol. 19, N. 1. P. 1—12.Hartford W., Lear S., Nimmon L. Stroke survivors’ experiences of team support along their recovery continuum, BMC Health Services Research, 2019, vol. 19, no. 1, pp. 1—12.Глушко Т. В. и др. Психоэмоциональное состояние у постинсультных пациентов // Сибирский вестник психиатрии и наркологии. 2010. № 2. С. 89—92.Glushko T. V., Drobysheva A. M., Galeva K. V., Kupriyanova I. E., Repin A. N. State in post-stroke patients, Siberian herald of psychiatry and addiction psychiatry, 2010, no. 2, pp. 89—92 (in Russian).Lobo E. H. et al. Information, involvement, self-care and support—The needs of caregivers of people with stroke: A grounded theory approach // Plos one. 2023. Vol. 18, N. 1. P. e0281198.Lobo E. H., Frølich A., Abdelrazek M., Rasmussen L. J., Grundy J., Livingston P. M., Kensing F. Information, involvement, self-care and support—The needs of caregivers of people with stroke: A grounded theory approach, Plos one, 2023, vol. 18, no. 1, e0281198 p.Musuka T. D. et al. Diagnosis and management of acute ischemic stroke: speed is critical // Cmaj. 2015. Vol. 187, N. 12. P. 887—893.Musuka T. D., Wilton S. B., Traboulsi M., Hill M. D. Diagnosis and management of acute ischemic stroke: speed is critical, Cmaj, 2015, vol. 187, no. 12, pp. 887—893.Langan J. et al. Reported use of technology in stroke rehabilitation by physical and occupational therapists // Disability and Rehabilitation: Assistive Technology. 2018. Vol. 13, N. 7. P. 641—647.Langan J., Subryan H., Nwogu I., Cavuoto L. Reported use of technology in stroke rehabilitation by physical and occupational therapists, Disability and Rehabilitation, Assistive Technology, 2018, vol. 13, no. 7, pp. 641—647.Li K. H. C. et al. The current state of mobile phone apps for monitoring heart rate, heart rate variability, and atrial fibrilla-tion: narrative review // JMIR mHealth and uHealth. 2019. Vol. 7, N. 2. P. e11606.Li K. H. C., White F. A., Tipoe T., Liu T., Wong M. C., Jesuthasan A., Yan B. P. The current state of mobile phone apps for monitoring heart rate, heart rate variability, and atrial fibrillation: narrative review, JMIR mHealth and uHealth, 2019, vol. 7, no. 2, e11606 p.Martins J., Cardoso J. S., Soares F. Offline computeraided diagnosis for Glaucoma detection using fundus images targeted at mobile devices // Computer Methods and Programs in Biomedicine. 2020. Vol. 192. P. 105341.Martins J., Cardoso J. S., Soares F. Offline computer-aided diagnosis for Glaucoma detection using fundus images targeted at mobile devices, Computer Methods and Programs in Biomedicine, 2020, vol. 192, 105341 p.Back S. et al. Robust skin disease classification by distilling deep neural network ensemble for the mobile diagnosis of Herpes zoster // IEEE Access. 2021. Vol. 9. P. 20156—20169.Back S., Lee S., Shin S., Yu Y., Yuk T., Jong S., Lee K. Robust skin disease classification by distilling deep neural network ensemble for the mobile diagnosis of Herpes zoster, IEEE Access, 2021, vol. 9, pp. 20156—20169.Mikolajczyk T. et al. Advanced technology for gait rehabilitation: An overview // Advances in Mechanical Engineering. 2018. Vol. 10, N. 7. P. 1687814018783627.Mikolajczyk T., Ciobanu I., Badea D. I., Iliescu A., Pizzamiglio S., Schauer T., Berteanu M. Advanced technology for gait rehabilitation: An overview, Advances in Mechanical Engineering, 2018, vol. 10, no. 7, pp. 1687814018783627.Qiu S. et al. Body sensor network-based gait quality assessment for clinical decision-support via multi-sensor fusion // Ieee Access. 2019. Vol. 7. P. 59884—59894.Qiu S., Liu L., Wang Z., Li S., Zhao H., Wang J., Tang K. Body sensor network-based gait quality assessment for clinical decision-support via multi-sensor fusion, Ieee Access, 2019, vol. 7, pp. 59884-59894.Yen C. T., Liao J. X., Huang Y. K. Human daily activity recognition performed using wearable inertial sensors combined with deep learning algorithms // Ieee Access. 2020. Vol. 8. P. 174105—174114.Yen C. T., Liao J. X., Huang Y. K. Human daily activity recognition performed using wearable inertial sensors combined with deep learning algorithms, Ieee Access, 2020, vol. 8, pp. 174105—174114.Šlajpah S. et al. Time-Based and Path-Based Analysis of Upper-Limb Movements during Activities of Daily Living // Sensors. 2023. Vol. 23, N. 3. P. 1289.Šlajpah S., Čebašek E., Munih M., Mihelj M. Time-Based and Path-Based Analysis of Upper-Limb Movements during Activities of Daily Living, Sensors, 2023, vol. 23, no. 3, pp. 1289.Singh A. K., Kumbhare V. A., Arthi K. Real-time human pose detection and recognition using mediapipe // International Conference on Soft Computing and Signal Processing. Singapore: Springer Nature Singapore, 2021. P. 145—154.Singh A. K., Kumbhare V. A., Arthi K. Real-time human pose detection and recognition using mediapipe, International Conference on Soft Computing and Signal Processing, Singapore, Springer Nature Singapore, 2021, pp. 145—154.LaPiana N. et al. Acceptability of a mobile phone—based augmented reality game for rehabilitation of patients with upper limb deficits from stroke: Case study // JMIR rehabilitation and assistive technologies. 2020. Vol. 7, N. 2. P. e17822.LaPiana N., Duong A., Lee A., Alschitz L., Silva R. M., Early J., Mourad P. Acceptability of a mobile phone—based augmented reality game for rehabilitation of patients with upper limb deficits from stroke: Case study, JMIR rehabilitation and assistive technologies, 2020, vol. 7, no. 2, e17822 p.Vahlberg B. et al. Effects on walking performance and lower body strength by short message service guided training after stroke or transient ischemic attack (the STROKEWALK study): a randomized controlled trial // Clinical rehabilitation. 2021. Vol. 35, N. 2. P. 276—287.Vahlberg B., Lundström E., Eriksson S., Holmbäck U., Cederholm T. Effects on walking performance and lower body strength by short message service guided training after stroke or transient ischemic attack (the STROKEWALK study): a randomized controlled trial, Clinical rehabilitation, 2021, vol. 35, no. 2, pp. 276—287.Fasel B. et al. An inertial sensor-based system for spatiotemporal analysis in classic cross-country skiing diagonal technique // Journal of biomechanics. 2015. Vol. 48, N. 12. P. 3199—3205.Fasel B., Favre J., Chardonnens J., Gremion G., Aminian K. An inertial sensor-based system for spatiotemporal analysis in classic cross-country skiing diagonal technique, Journal of biomechanics, 2015, vol. 48, no. 12, pp. 3199—3205.Bavan L. et al. Adherence monitoring of rehabilitation exercise with inertial sensors: A clinical validation study // Gait & posture. 2019. Vol. 70. P. 211—217.Bavan L., Surmacz K., Beard D., Mellon S., Rees J. Adherence monitoring of rehabilitation exercise with inertial sensors: A clinical validation study, Gait & posture, 2019, vol. 70, pp. 211—217.Alfian R. I., Ma’arif A., Sunardi S. Noise reduction in the accelerometer and gyroscope sensor with the Kalman filter algorithm // Journal of Robotics and Control (JRC) 2021. Vol 2. P. 180—189.Alfian R. I., Ma’arif A., Sunardi S. Noise reduction in the accelerometer and gyro-scope sensor with the Kalman filter algorithm, Journal of Robotics and Control (JRC), 2021, vol. 2, pp. 180—189.Labbe R. Kalman and bayesian filters in python // Chap. 2014. Vol. 7, N. 246. P. 4.Labbe R. Kalman and bayesian filters in python, Chap, 2014, vol. 7, no. 246, pp. 4.Yan W. et al. A modified kalman filter for integrating the different rate data of gyros and accelerometers retrieved from android smartphones in the GNSS/IMU coupled navigation // Sensors. 2020. Vol. 20, N. 18. P. 5208.Yan W., Zhang Q., Wang L., Mao Y., Wang A., Zhao C. A modified kalman filter for integrating the different rate data of gyros and accelerometers retrieved from android smartphones in the GNSS/IMU coupled navigation, Sensors, 2020, vol. 20, no. 18, 5208 p.Seo W., Baek K. R. Indoor dead reckoning localization using ultrasonic anemometer with IMU // Journal of Sensors. 2017. P. 2017.Seo W., Baek K. R. Indoor dead reckoning localization using ultrasonic anemometer with IMU, Journal of Sensors, 2017, pp. 2017.Wang Y., Chernyshoff A., Shkel A. M. Error analysis of ZUPT-aided pedestrian inertial navigation // 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN). IEEE, 2018. P. 206—212.Wang Y., Chernyshoff A., Shkel A. M. Error analysis of ZUPT-aided pedestrian inertial navigation, 2018 International Conference on Indoor Positioning and In-door Navigation (IPIN), IEEE, 2018, pp. 206—212.Peng C. et al. A new type of tri-axial accelerometers with high dynamic range MEMS for earthquake early warning // Computers & Geosciences. 2017. Vol. 100. P. 179—187.Peng C., Chen Y., Chen Q., Yang J., Wang H., Zhu X., Zheng Y. A new type of tri-axial accelerometers with high dynamic range MEMS for earthquake early warning, Computers & Geosciences, 2017, vol. 100, pp. 179—187.Li P., Zhou J. Tracking of Gymnast’s Limb Movement Trajectory Based on MEMS Inertial Sensor // Applied Bionics and Biomechanics. 2022. Vol. 2022.Li P., Zhou J. Tracking of Gymnast’s Limb Movement Trajectory Based on MEMS Inertial Sensor, Applied Bionics and Biomechanics, 2022, vol. 2022.Ikbal M. S. et al. Dynamic pose tracking performance evaluation of htc vive virtual reality system // IEEE Access. 2020. N. 9. P. 3798—3815.Ikbal M. S., Ramadoss V., Zoppi M. Dynamic pose tracking performance evaluation of htc vive virtual reality system, IEEE Access, 2020, vol. 9, pp. 3798—3815.Hellsten T. et al. The potential of computer vision-based marker-less human motion analysis for rehabilitation // Rehabilitation Process and Outcome. 2021. N. 10. P.11795727211022330.Hellsten T., Karlsson J., Shamsuzzaman M., Pulkkis G. The potential of computer vision-based marker-less human motion analysis for rehabilitation, Rehabilitation Process and Outcome, 2021, vol. 10, 11795727211022330 p.

The authors declare that there are no conflicts of interest present.