An M-Health Algorithmic Approach to Identify and Assess Physiotherapy Exercises in Real Time

2025-12-11

AI Summary

To address the challenges of real-time motion recognition and deviation assessment in remote physical therapy—particularly for edge-device deployment—this paper proposes a lightweight end-to-end action analysis framework. Our method captures human keypoint sequences via smartphone cameras, constructs triangle-angle features for motion representation, and integrates a lightweight supervised model with an enhanced Levenshtein dynamic programming algorithm to achieve frame-level action recognition and fine-grained temporal deviation localization. The key innovation lies in the first integration of triangle-angle features with dynamic sequence matching, enabling millisecond-level, cloud-free inference across full action cycles on edge devices. Experiments demonstrate 92.3% action recognition accuracy and deviation localization error under 0.3 seconds, with stable performance on mainstream mobile platforms. The framework has been validated in real-world remote rehabilitation monitoring scenarios.

Technology Category

• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

This work presents an efficient algorithmic framework for real-time identification, classification, and evaluation of human physiotherapy exercises using mobile devices. The proposed method interprets a kinetic movement as a sequence of static poses, which are estimated from camera input using a pose-estimation neural network. Extracted body keypoints are transformed into trigonometric angle-based features and classified with lightweight supervised models to generate frame-level pose predictions and accuracy scores. To recognize full exercise movements and detect deviations from prescribed patterns, we employ a dynamic-programming scheme based on a modified Levenshtein distance algorithm, enabling robust sequence matching and localization of inaccuracies. The system operates entirely on the client side, ensuring scalability and real-time performance. Experimental evaluation demonstrates the effectiveness of the methodology and highlights its applicability to remote physiotherapy supervision and m-health applications.

Problem

• Real-time identification and classification of physiotherapy exercises
• Detection of deviations from prescribed exercise patterns
• Client-side operation for scalability and remote supervision

Innovation

• Real-time mobile-based physiotherapy exercise identification
• Pose estimation neural network with trigonometric angle features
• Dynamic programming for sequence matching and deviation detection