Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65209
Volume:
10 |
6 |
Jun 2026
Pages:
1-9
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Engineering
JSPM Narhe Technical Campus
Department of Computer Engineering
JSPM Narhe Technical Campus
Department of Computer Engineering
JSPM Narhe Technical Campus
Department of Computer Engineering
JSPM Narhe Technical Campus
Department of Computer Engineering
JSPM Narhe Technical Campus
The demand for remote physical therapy solutions has surged, yet verifying patient adherence at home remains a persistent challenge. Traditional telehealth applications struggle with monitoring real-time biomechanical accuracy, often relying on subjective self-reporting. This manuscript presents PhysioBuddy, an advanced web-based platform engineered to automate rehabilitation tracking. The proposed system integrates a decoupled architecture using React.js for the client interface and Django Channels configured with a Daphne ASGI server for stateful WebSocket data transmission. To achieve clinical-grade tracking without requiring high-end hardware, the platform employs a neuro-symbolic artificial intelligence pipeline. Google's MediaPipe Pose model acts as the perception layer to extract three-dimensional joint coordinates. These coordinates are subsequently processed by deterministic, mathematical state machines that calculate joint angles and validate exercise execution based on strict clinical thresholds. The deployment on zero-cost cloud tiers demonstrates the system's economic viability and low-latency performance. The findings indicate that this framework effectively translates physical motions into quantitative compliance metrics, offering a reliable and scalable solution for remote physiotherapy.
KEYWORDS
This research demonstrates the viability of integrating lightweight computer vision within asynchronous web frameworks to solve real-world healthcare challenges. The developed platform effectively eliminates the unreliability of self-reported physical therapy by providing verifiable, data-driven compliance metrics. Future iterations of this work aim to migrate the neural perception processing entirely to the client-side browser via WebAssembly, thereby further reducing server network payloads and enhancing user privacy.
1. A. Raza et al., "LogRF: An Approach to Human Pose Estimation Using Skeleton Landmarks for Physiotherapy Fitness Exercise Correction," IEEE Access, vol. 11, 2023.T. Maitray, U. Singh, V. Kukreja, A. Patel, and V. Sharma, "Exercise Posture Rectifier and Tracker Using MediaPipe and OpenCV," 2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), IEEE, 2023, pp. 141-144.W. N. Asmawi and S. P. Kumaresan, "Real-Time Posture Monitoring for Effective Exercise Using MediaPipe Python," Journal of Informatics and Web Engineering, vol. 5, no. 1, pp. 236–251, Feb. 2026.B. S. Cobb and F. Candan, "Improving Workplace Safety through Posture Monitoring Using Mediapipe and Machine Learning," 2023 International Conference on Innovations in Intelligent Systems and Applications (INISTA), IEEE, 2023, pp. 1-6.
Publication Date
6/20/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...