Estimation of Resistance Training RPE using Inertial Sensors and Electromyography

2025-10-03

AI Summary

Subjective Rating of Perceived Exertion (RPE) lacks objective, real-time quantification during resistance training, hindering personalized feedback and injury prevention. Method: We propose a wearable multimodal sensing framework integrating inertial measurement unit (IMU) and surface electromyography (sEMG) signals to predict RPE. Time-domain statistical features are extracted from both modalities, and machine learning models—including random forest—are employed for multi-level RPE classification. Contribution/Results: Evaluated on a custom dataset comprising 69 participant sessions and over 1,000 repetitions of unilateral dumbbell bicep curls, the framework identifies eccentric-phase repetition duration as the strongest RPE predictor. In a stringent four-class classification task, the model achieves 41.4% accuracy; with ±1 RPE tolerance, accuracy improves to 85.9%. This work presents the first systematic validation of IMU-sEMG fusion for objective fatigue monitoring in resistance training, demonstrating its feasibility and effectiveness for real-time exertion assessment.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Accurate estimation of rating of perceived exertion (RPE) can enhance resistance training through personalized feedback and injury prevention. This study investigates the application of machine learning models to estimate RPE during single-arm dumbbell bicep curls, using data from wearable inertial and electromyography (EMG) sensors. A custom dataset of 69 sets and over 1000 repetitions was collected, with statistical features extracted for model training. Among the models evaluated, a random forest classifier achieved the highest performance, with 41.4% exact accuracy and 85.9% $pm1$ RPE accuracy. While the inclusion of EMG data slightly improved model accuracy over inertial sensors alone, its utility may have been limited by factors such as data quality and placement sensitivity. Feature analysis highlighted eccentric repetition time as the strongest RPE predictor. The results demonstrate the feasibility of wearable-sensor-based RPE estimation and identify key challenges for improving model generalizability.

Problem

• Estimating resistance training RPE using inertial and EMG sensors
• Applying machine learning to predict exertion during bicep curls
• Identifying key predictors and challenges for wearable RPE estimation

Innovation

• Used inertial sensors and EMG for data collection
• Applied random forest classifier for RPE estimation
• Identified eccentric repetition time as key predictor