End-to-end horse gait classification in uncontrolled environments using inertial sensors [r-libre/3750]

Gérard, Mahaut; Hanne-Poujade, Sandrine; Dubois, Guillaume; Chateau, Henry et Mezghani, Neila (2025). End-to-end horse gait classification in uncontrolled environments using inertial sensors. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3564324

Fichier(s) associé(s) à ce document :

PDF - MahautGérard2025.pdf
Contenu du fichier : Manuscrit accepté (révisé après évaluation)
Licence : Creative Commons CC BY.

Télécharger

Catégorie de document :	Articles de revues
Évaluation par un comité de lecture :	Oui
Étape de publication :	Publié
Résumé :	Locomotor injuries in horses are a major cause of underperformance and serious welfare issue. Veterinarians typically investigate horses’ lameness through visual examination at separate gaits (walk, trot, gallop). To evaluate lameness objectively, Inertial Measurement Units (IMU) based systems have been developed. It is necessary to accurately identify the gait of each stride as vertical displacement symmetry is assessed at a defined gait, essentially trot. This study aimed to classify gaits into 6 classes and to assess the training sample size required to maximize the performance. Unlike previous methods, we used raw IMU data without manually preselecting specific signal segments. Seven sensors were strategically placed on the limbs, head, withers, and pelvis of horses. 1440 horses were used in our unsupervised model and the gait of 110 horses was labelled using IMU data for our supervised models. We divided the 6 gaits classification task into two subtasks: a four-gaits classification and a gallop-specific classification. In the first subtask, we compared the performance of a machine learning (XGBoost), a deep learning (LSTM) and a transfer learning (ENCOD-CNN) model, depending on the labelled training sample size. Our results show that the transfer learning approach outperformed the other models, achieving test accuracy of 91.9%. Our gallop classification task achieves 97.1% accuracy and the total pipeline reaches 91.2% accuracy. Beyond improving gait classification in a real clinical setting, this research demonstrates the potential of transfer learning for time-series datasets and provides a quantitative assessment of the required labeled sample size for effective implementation.
Adresse de la version officielle :	https://ieeexplore.ieee.org/abstract/document/1097...
Déposant:	Ayena, Johannes
Responsable :	Johannes Ayena
Dépôt :	12 mai 2025 19:47
Dernière modification :	12 mai 2025 19:47

Actions (connexion requise)

RÉVISER