IRO Journals
Journal of Electronics and Informatics

Low-Cost AI-Based Wearable Rehabilitation Monitoring System for Upper-Limb Stroke Patients

Open Access
Published: 14 October, 2026
Pages: 389-403
  • Anisha N. , Anisha N.
    Research Scholar, Department of Biomedical Engineering, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, India
    Research Scholar, Department of Biomedical Engineering, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, India
  • Ushus S Kumar Ushus S Kumar
    Associate Professor, Department of Biomedical Engineering, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, India
    Associate Professor, Department of Biomedical Engineering, SRM Institute of Science and Technology, Ramapuram Campus, Chennai, India
view PDF
view PDF

How to Cite

N., Anisha, and Ushus S Kumar. 2026. “Low-Cost AI-Based Wearable Rehabilitation Monitoring System for Upper-Limb Stroke Patients”. Journal of Electronics and Informatics 8 (4): 389-403. https://doi.org/10.36548/jei.2026.4.006.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Stroke Rehabilitation
9-DOF IMU
Compensatory Movement Detection
LSTM-Based Classification
Quaternion Orientation Estimation
Wearable Motion Monitoring
Real-Time Rehabilitation

Abstract

The low cost wearble monitoring framework for the automatic evaluation of exercises for stroke recovery of the upper limb with special attention to discrimination between the intended and compensatory motion of the elbow joint is designed. The monitoring framework utilizes a 9 degrees-of-freedom IMU combined with the ESP32-based data acquisition and transmission device to obtain the motion of the forearm at 100 Hz. The signals are processed using the fourth order Butterworth filter, orientation estimation by Madgwick algorithm, quaternion representation, fixed window segmentation, and features extraction. A stacked 128- and 64-unit LSTM network is used to identify the characteristics of movements for the four classes of correct elbow flexion, correct elbow extension, compensatory flexion, and compensatory extension. The proposed system obtains an accuracy of 93.25%, precision of 93.3%, recall of 93.25%, F1-Score of 93.2%, and an AUC-ROC macro average of 0.822. Processing time and communication time are estimated at 312 ms, and the estimated cost for wearable hardware is USD 27.40. The system combines movement classification and correction feedback and offers an efficient system for inexpensive rehabilitation monitoring.

References

  1. Oubre, Brandon, Jean-Francois Daneault, Hee-Tae Jung, Kallie Whritenour, Jose Garcia Vivas Miranda, Joonwoo Park, Taekyeong Ryu, Yangsoo Kim, and Sunghoon Ivan Lee. "Estimating upper-limb impairment level in stroke survivors using wearable inertial sensors and a minimally-burdensome motor task." IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2020, vol. 28, no. 3: 601-611.
  2. Okita, Shusuke, Diogo Schwerz De Lucena, Vicky Chan, and David J. Reinkensmeyer. "Measuring movement quality of the stroke-impaired upper extremity with a wearable sensor: toward a smoothness metric for home rehabilitation exercise programs." In 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE, 2021, 6691-6694.
  3. Pohl, Johannes, Alain Ryser, Janne Marieke Veerbeek, Geert Verheyden, Julia Elisabeth Vogt, Andreas Rüdiger Luft, and Chris Awai Easthope. "Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke." Frontiers in physiology, 2022, vol. 13: 952757.
  4. Subash, Tanya, Ann David, StephenSukumaran ReetaJanetSurekha, Sankaralingam Gayathri, Selvaraj Samuelkamaleshkumar, Henry Prakash Magimairaj, Nebojsa Malesevic et al. "Comparing algorithms for assessing upper limb use with inertial measurement units." Frontiers in Physiology, 2022, vol. 13: 1023589.
  5. Parnandi, Avinash, Aakash Kaku, Anita Venkatesan, Natasha Pandit, Audre Wirtanen, Haresh Rajamohan, Kannan Venkataramanan, Dawn Nilsen, Carlos Fernandez-Granda, and Heidi Schambra. "PrimSeq: A deep learning-based pipeline to quantitate rehabilitation training." PLOS Digital Health, 2022, vol. 1, no. 6: e0000044.
  6. Das, Neha, Satoshi Endo, Sabrina Patel, Carmen Krewer, and Sandra Hirche. "Online detection of compensatory strategies in human movement with supervised classification: a pilot study." Frontiers in Neurorobotics, 2023, vol. 17: 1155826.
  7. Li, Mingqi, Gabrielle Scronce, Christian Finetto, Kristen Coupland, Matthew Zhong, Melanie E. Lambert, Adam Baker, Feng Luo, and Na Jin Seo. "Application of deep learning algorithm to monitor upper extremity task practice." Sensors, 2023, vol. 23, no. 13: 6110.
  8. Hwang, Yi-Ting, Yu-Qian Tung, Chun-Shu Chen, and Bor-Shing Lin. "B-spline modeling of inertial measurements for evaluating stroke rehabilitation effectiveness." IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, vol. 31: 4008-4016.
  9. Oh, Youngmin, Sol-A. Choi, Yumi Shin, Yeonwoo Jeong, Jongkuk Lim, and Sujin Kim. "Investigating activity recognition for hemiparetic stroke patients using wearable sensors: A deep learning approach with data augmentation." Sensors, 2023, vol. 24, no. 1: 210.
  10. Seo, Na Jin, Kristen Coupland, Christian Finetto, and Gabrielle Scronce. "Wearable sensor to monitor quality of upper limb task practice for stroke survivors at home." Sensors, 2024, vol. 24, no. 2: 554.
  11. Ding, Kangjia, Jiping Wang, Xiaojun Wang, Linfu Zhou, Daxi Xiong, and Liquan Guo. "System for detection and quantitative evaluation of compensatory movement in post-stroke patients based on wearable sensor and machine learning algorithm." IEEE Sensors Journal, 2024, vol. 24, no. 14: 22830-22842.
  12. Zhou, Weinan, Diyang Fu, Zhiyu Duan, Jiping Wang, Linfu Zhou, and Liquan Guo. "Achieving precision assessment of functional clinical scores for upper extremity using IMU-Based wearable devices and deep learning methods." Journal of NeuroEngineering and Rehabilitation, 2025, vol. 22, no. 1: 84.
  13. World Health Organization, “The top 10 causes of death,” WHO, Geneva, Switzerland, 2020. Available: https://www.who.int/
  14. Pavan, Nagashree, and Praveen Kumar Reddy. 2026. “Neuroflex: A Real-Time, Wearable Neuro-Muscular Rehabilitation System Using Soft Robotics”. Journal of Electronics and Informatics 8 (4): 317-29.
  15. Harish, Neela, Deepa S., Uma Loganathan, Kavitha J., and Praveen Kumar. 2026. “Wearable Gyroscope-Based Motion Tracking and Hand Gesture Recognition Using ANOVA for Feature Discrimination”. Journal of Innovative Image Processing 8 (4): 1393-1412.
  16. Gomez-Arrunategui JP, Eng JJ, Hodgson AJ. Monitoring Arm Movements Post-Stroke for Applications in Rehabilitation and Home Settings. IEEE Trans Neural System Rehabil Engineering. 2022, 30:2312-2321. Available: https://pubmed.ncbi.nlm.nih.gov/35947559/