Boosting Automatic Exercise Evaluation Through Musculoskeletal Simulation-Based IMU Data Augmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Spilz, Andreas, Oppel, Heiko, Munz, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910975912837120
author Spilz, Andreas
Oppel, Heiko
Munz, Michael
author_facet Spilz, Andreas
Oppel, Heiko
Munz, Michael
contents Automated evaluation of movement quality holds significant potential for enhancing physiotherapeutic treatments and sports training by providing objective, real-time feedback. However, the effectiveness of deep learning models in assessing movements captured by inertial measurement units (IMUs) is often hampered by limited data availability, class imbalance, and label ambiguity. In this work, we present a novel data augmentation method that generates realistic IMU data using musculoskeletal simulations integrated with systematic modifications of movement trajectories. Crucially, our approach ensures biomechanical plausibility and allows for automatic, reliable labeling by combining inverse kinematic parameters with a knowledge-based evaluation strategy. Extensive evaluations demonstrate that augmented variants closely resembles real-world data, significantly improving the classification accuracy and generalization capability of neural network models. Additionally, we highlight the benefits of augmented data for patient-specific fine-tuning scenarios, particularly when only limited subject-specific training examples are available. Our findings underline the practicality and efficacy of this augmentation method in overcoming common challenges faced by deep learning applications in physiotherapeutic exercise evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24415
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Boosting Automatic Exercise Evaluation Through Musculoskeletal Simulation-Based IMU Data Augmentation
Spilz, Andreas
Oppel, Heiko
Munz, Michael
Machine Learning
Artificial Intelligence
Automated evaluation of movement quality holds significant potential for enhancing physiotherapeutic treatments and sports training by providing objective, real-time feedback. However, the effectiveness of deep learning models in assessing movements captured by inertial measurement units (IMUs) is often hampered by limited data availability, class imbalance, and label ambiguity. In this work, we present a novel data augmentation method that generates realistic IMU data using musculoskeletal simulations integrated with systematic modifications of movement trajectories. Crucially, our approach ensures biomechanical plausibility and allows for automatic, reliable labeling by combining inverse kinematic parameters with a knowledge-based evaluation strategy. Extensive evaluations demonstrate that augmented variants closely resembles real-world data, significantly improving the classification accuracy and generalization capability of neural network models. Additionally, we highlight the benefits of augmented data for patient-specific fine-tuning scenarios, particularly when only limited subject-specific training examples are available. Our findings underline the practicality and efficacy of this augmentation method in overcoming common challenges faced by deep learning applications in physiotherapeutic exercise evaluation.
title Boosting Automatic Exercise Evaluation Through Musculoskeletal Simulation-Based IMU Data Augmentation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.24415