Sensor Input Type and Location Influence Outdoor Running Terrain Classification via Deep Learning Approaches
Sensors · 2025
DOI: 10.3390/s25196203 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Gabrielle Thibault und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Kinesiology and Physical Education, McGill University, Montreal, QC H2W 1S4, Canada. Hauptthemen laut MEDLINE: Running, Deep Learning. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objective: Understanding the training effect in high-level running is important for performance optimization and injury prevention. This includes awareness of how different running surface types (e.g., hard versus soft) may modify biomechanics. Recent studies have demonstrated that deep learning algorithms, such as convolutional neural networks (CNNs), can accurately classify human activity collected via body-worn sensors. To date, no study has assessed optimal signal type, sensor location, and model architecture to classify running surfaces. This study aimed to determine which combination of signal type, sensor location, and CNN architecture would yield the highest accuracy in classifying grass and asphalt surfaces using inertial measurement unit (IMU) sensors.
Methods
Running data were collected from forty participants (27.4 years + 7.8 SD, 10.5 ± 7.3 SD years of running) with a full-body IMU system (head, sternum, pelvis, upper legs, lower legs, feet, and arms) on grass and asphalt outdoor surfaces. Performance (accuracy) for signal type (acceleration and angular velocity), sensor configuration (full body, lower body, pelvis, and feet), and CNN model architecture was tested for this specific task. Moreover, the effect of preprocessing steps (separating into running cycles and amplitude normalization) and two different data splitting protocols (leave-n-subject-out and subject-dependent split) was evaluated.
Results
In general, acceleration signals improved classification results compared to angular velocity (3.8%). Moreover, the foot sensor configuration had the best performance-to-number of sensor ratio (95.5% accuracy). Finally, separating trials into gait cycles and not normalizing the raw signals improved accuracy by approximately 28%.
Conclusion
This analysis sheds light on the important parameters to consider when developing machine learning classifiers in the human activity recognition field. A surface classification tool could provide useful quantitative feedback to athletes and coaches in terms of running technique effort on varied terrain surfaces, improve training personalization, prevent injuries, and improve performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Kinesiology and Physical Education, McGill University, Montreal, QC H2W 1S4, Canada.
ORCID-Profile: Philippe C Dixon
Zitieren
APA
Thibault, G., Dixon, P. C., & Pearsall, D. J. (2025). Sensor Input Type and Location Influence Outdoor Running Terrain Classification via Deep Learning Approaches. Sensors. https://doi.org/10.3390/s25196203
Vancouver
Thibault G, Dixon PC, Pearsall DJ. Sensor Input Type and Location Influence Outdoor Running Terrain Classification via Deep Learning Approaches. Sensors. 2025. doi:10.3390/s25196203
BibTeX
@article{Thibault2025,
author = {Thibault, Gabrielle and Dixon, Philippe C and Pearsall, David J},
title = {Sensor Input Type and Location Influence Outdoor Running Terrain Classification via Deep Learning Approaches},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25196203}
}
EUVIMED