AI Rehabilitation planner
AI Personalized Rehabilitation Planner is a web-based computer software application that helps patients perform physiotherapy exercises at home. It accepts smartphone accelerometer and gyroscope data, resamples it, splits it into sliding windows, extracts motion features, and uses machine-learning models (XGBoost and Random Forest) to recognise the exercise being performed. It then groups predictions into exercise sets, counts repetitions, and calculates an exercise quality score with personalised corrective feedback. The system includes user registration and login with secure password hashing, a database layer for storing sessions, sets and goals, a recovery-progress dashboard with streaks, and downloadable PDF progress reports. It is written in Python, with a FastAPI backend and an HTML/CSS frontend.
Authors
- Sharma Dhruva Ramprasad
Institutions
- University of Mumbai (IN)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-12
- DOI
- https://doi.org/10.5281/zenodo.24151422
- Primary Topic
- Context-Aware Activity Recognition Systems
- Type
- preprint