Advances in Wearable Technology for Intelligent Rehabilitation and Motion Analysis

Gongwen Gao; Ziqi Ling; Lang Yang

doi:10.54097/nn5rp906

Authors

Gongwen Gao
Ziqi Ling
Lang Yang

DOI:

https://doi.org/10.54097/nn5rp906

Keywords:

Ai-assisted wearables, rehabilitation, motion monitoring.

Abstract

The integration of artificial intelligence (AI) with wearable technology is creating a transformative paradigm in healthcare, particularly within rehabilitation and motion monitoring. This review systematically explores this convergence, highlighting how AI-enhanced wearables address critical limitations of conventional methods, such as discontinuous observation and delayed response in hospital or home-care settings. By leveraging continuous, real-time data collection from diverse sensors, these devices offer an unparalleled platform for remote patient management. This capability is increasingly vital against a backdrop of global demographic shifts, including aging populations and a rising prevalence of chronic conditions, which amplify the demand for advanced, accessible rehabilitation solutions. The article delves into specific technological foundations, including sensor-based and vision-aided monitoring systems, and their data processing pipelines powered by AI algorithms. Subsequently, it examines cutting-edge applications across key domains: gait and upper-limb rehabilitation, the use of intelligent exoskeletons, and the emerging field of vision-language-action (VLA) models for holistic intervention. The discussion extends to motion monitoring for athletic recovery and managing musculoskeletal disorders. By synthesizing these developments, this review aims to provide a foundational framework and offer directive insights for future technical innovation, product design, and scholarly research, thereby accelerating the advancement of personalized and proactive healthcare.

Downloads

Download data is not yet available.

References

[1] Su Bingtian, Li Jianliang, Xu Huihua, Xu Ze, Meng Jianxin, Chen Xiaoping, Li Fengyu. Scientific Training Assistance: Application of Flexible Wearable Sensors in Motion Monitoring. Science China: Information Sciences, 2022.

[2] Fortino G.,et alWearable Body Sensor Newtwoerks for Human Health Monitoring. IEEE Reviews in Biomedical Engineering, 2010,3:231-250.

[3] Nordiic Semiconductor. Next-Generation Wearable Devices and Edge AI Improve Motion Performance Analysis, 2025.

[4] Tencent Cloud Developer Community. Application of Wearable Devices in the Sports Field: Technology Makes Sports Smarter, 2025.

[5] CSDN Blog. [SCI] [Motion Tracking] Research on Motion Tracking Method Based on Inertial Sensorss (Matlab Code Implementation), 2024.

[6] Meng L, Pang J, Research on a Five-Dimensional Evaluation Model for Early Parkinson's Disease Based on Multi-Joint IMU Sensors, Institute of Medical Engineering and Translational Medicine, Tianjin University, 2022.

[7] Research Team of Nanjing Medical University. Research on Electromyographic Biomarkers of Freezing of Gait in Parkinson's Disease Based on sEMG, 2023.

[8] Reseacrh Team of the University of Oxford. Clinical Research on Detecting the Progression of Parkinson's Disease Using Wearable Devices (IMU), 2021.

[9] IBM, Pfizer Inc. IBM Collaborates with Pfizer to Develop AI Algorithm for Remote Diagnosis of Parkinson's Disease Severity, 2022.

[10] Zhang Shuai, Hong Ao, Hu Hengrui, et al. Interactive Rehabilitation Training System for Neuromyelitis Optica Based on AI Motion Capture Technology. Journal of Graphics, 2025, 46(04): 783-792.

[11] Chen Xilai. Monitoring the Rehabilitation Training Status of Injured Soldiers Using Wearable Sensors. Zhejiang University, 2022.

[12] Ramanujam E, Perumal T, Padmavathi S. Human activity recognition with smartphone and wearable sensors using deep learning techniques: A review. IEEE Sensors Journal, 2021, 21(12): 13029-13040.

[13] Li Jiaming. A Wearable Sensor-Based Scoliosis Rehabilitation Training System. Guangdong University of Technology, 2024.

[14] Levinger P, Lai D T H, Begg R K, et al. The application of support vector machines for detecting recovery from knee replacement surgery using spatio-temporal gait parameters. Gait & posture, 2009, 29(1): 91-96.

[15] Venkatesan S, Karthick T, Khan M F. Enhancing Patient Recovery Outcomes: The Role of Random Forest Algorithms in Predictive Analytics. International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024). Atlantis Press, 2025: 1368-1377.

[16] Allen J H, Tang A R, Hajdu K S, et al. Predicting early versus late recovery from sport-related concussion using decision tree analysis. Journal of Neurosurgery: Pediatrics, 2023, 32(1): 9-18.

[17] Shahrestani S, Chan A K, Bisson E F, et al. Develo** nonlinear k-nearest neighbors classification algorithms to identify patients at high risk of increased length of hospital stay following spine surgery. Neurosurgical focus, 2023, 54(6): E7.

[18] Leng Hansong, Zhang Fengduo, Ren Lijie, et al. Research on Human Motion Recognition Using Random Forest Algorithm and Triboelectric Sensors. Journal of Hebei University of Water Resources and Electric Power, 2022,32(02): 29-34.

[19] Sahoo K K, Ghosh R, Mallik S, et al. Wrapper-based deep feature optimization for activity recognition in the wearable sensor networks of healthcare systems. Scientific Reports, 2023, 13(1): 965.

[20] Zhang S, Li Y, Zhang S, et al. Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors, 2022, 22(4): 1476.

[21] Athota R K, Sumathi D. Human activity recognition based on hybrid learning algorithm for wearable sensor data. Measurement: Sensors, 2022, 24: 100512.

[22] M. Wang, Z. Yan, T. Wang, P. Cai, S. Gao, Y. Zeng, C. Wan, H. Wang, L. Pan, J. Yu, S. Pan, K. He, J. Lu, X. Chen, Nat. Electron. 2020, 3, 563.

[23] A. Riera, A. Soria-Frisch, A. Albajes-Eizagirre, P. Cipresso, C. Grau, S. Dunne, G. Ruffini, Stud. Health Technol. Inform. 2012, 181, 228.

[24] Xiao Kai, Zou Renling. Advances in Surface Electromyography-Based Human Motion Recognition Algorithms. Bioinformatics, 2018,16(02):76-82.

[25] R. San-Segundo, H. Blunck, J. Moreno-Pimentel, A. Stisen, M. Gil-Martín, Robust human activity recognition using smartwatches and smartphones, Eng. Appl. Artif. Intell. 2018, 72: 190-202.

[26] Zhao Ju, Zheng Jianli. Personalized Fall Detection Using Multi-Sensor and Bi-LSTM. Intelligent Computer and Applications, 2022,12(04):146-150+158.

[27] Gupta S. Deep learning based human activity recognition (HAR) using wearable sensor data. International Journal of Information Management Data Insights, 2021, 1(2): 100046.