Related Experiment Video
Updated: Aug 5, 2026
07:30
The Muscle Cuff Regenerative Peripheral Nerve Interface for the Amplification of Intact Peripheral Nerve Signals
Published on: January 13, 2022
Digital and Remote Interventions for Musculoskeletal Aging: Real-Time Muscle Strain Severity Detection Using
Zulaikha Fatima1,2, Abdullah1,3, Nida Hafeez1,3
1Center for Computing Research (CIC), Instituto Politecnico Nacional (IPN), Mexico City 07320, Mexico.
Biosensors
|July 27, 2026
Summary
This study introduces a low-cost machine learning framework using Internet of Things (IoT) devices to accurately classify muscle strain severity from posture and electromyography (EMG) signals, aiding in ergonomic feedback.
Area of Science:
- Digital Health
- Ergonomics
- Machine Learning
Background:
- Prolonged digital device use is linked to physical and mental health issues, including musculoskeletal discomfort from poor posture.
- Posture-related strain is often overlooked, leading to pain and potentially affecting sleep and stress levels.
- Existing solutions lack integrated posture and muscle strain monitoring in a unified, low-cost framework.
Purpose of the Study:
- To develop and validate a machine learning-based framework for advanced muscle strain severity classification.
- To integrate posture monitoring and muscle strain detection into a unified, low-cost Internet of Things (IoT) system.
- To provide real-time ergonomic feedback through alerts for improved user health.
Main Methods:
- Collected a novel dataset of electromyography (EMG) and posture signals in hospital and industrial settings.
- Designed a two-part hardware architecture (posture detection and strain detection) using readily available IoT components (NodeMCU ESP8266, ultrasonic sensor, EMG sensor).
- Developed a hybrid machine learning model combining Vision Transformer (ViT) and XGBoost for classifying strain severity into baseline, compensatory strain, and overload categories.
Main Results:
- Achieved a high classification accuracy of 99.0% (95% CI: 98.5-99.5%) for muscle strain severity.
- Demonstrated a low inference latency of 15.2 ms, suitable for real-time applications.
- Validated the framework against clinical assessment procedures, creating diverse muscle strain patterns.
Conclusions:
- The proposed low-cost IoT framework effectively classifies muscle strain severity using machine learning.
- This technology offers a promising solution for real-time ergonomic feedback and preventing posture-related health concerns.
- The study establishes a novel dataset and methodology for advancing digital health monitoring in occupational settings.
