Cross-Species Behavioral Representation Learning Using Domain-Adversarial Adaptation on Wearable IMU Signals
Biomimetics · 15.07.2026 · 11 (7) · 496
DOI: 10.3390/biomimetics11070496 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomimetics, online erschienen am 15.07.2026. Verfasst von Çiğdem İnan Acı und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Mersin University, 33343 Mersin, Turkey. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Animal locomotion exhibits highly structured temporal dynamics despite significant inter-species biomechanical and anatomical discrepancies. While wearable inertial measurement unit (IMU) sensors and deep learning have advanced animal activity recognition, existing systems remain largely species-dependent, requiring large-scale labeled datasets for each deployment. To address this, we propose a biomimetic cross-species behavioral representation learning framework that extracts transferable locomotor structures from heterogeneous IMU signals. The proposed methodology integrates behavioral ontology harmonization, imbalance-aware augmentation, and semi-supervised domain-adversarial adaptation to reduce inter-species distributional discrepancies. Unlike conventional classification models, our dual-head architecture enables simultaneous processing of multi-label and single-label behavioral structures across anatomically diverse species. Extensive experiments conducted on dog, goat, and horse datasets demonstrate that the proposed framework significantly improves cross-species transferability, achieving a mean Macro-F1 score of 0.711 compared to 0.345 for direct transfer learning. Furthermore, we show that sparse target supervision is critical for stabilizing adversarial adaptation. K-Means head adaptation partially mitigated fully unsupervised negative transfer. However, its performance remained below semi-supervised Domain-Adversarial Neural Network (DANN), indicating that sparse target supervision is still necessary for stable cross-species adaptation. These findings suggest that biologically motivated locomotor similarity can support cross-species behavioral transfer, although external validation on additional species, sensor placements, and deployment conditions is still required.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Engineering, Mersin University, 33343 Mersin, Turkey.
- Department of Information Systems Engineering, Sakarya University, 54050 Sakarya, Turkey.
ORCID-Profile: Çiğdem İnan Acı, Furkan Say, Esin Ayşe Zaimoğlu
Zitieren
APA
Acı, Ç. İ., Say, F., & Zaimoğlu, E. A. (2026). Cross-Species Behavioral Representation Learning Using Domain-Adversarial Adaptation on Wearable IMU Signals. Biomimetics, 11(7), 496. https://doi.org/10.3390/biomimetics11070496
Vancouver
Acı Çİ, Say F, Zaimoğlu EA. Cross-Species Behavioral Representation Learning Using Domain-Adversarial Adaptation on Wearable IMU Signals. Biomimetics. 2026;11(7):496. doi:10.3390/biomimetics11070496
BibTeX
@article{Ac2026,
author = {Acı, Çiğdem İnan and Say, Furkan and Zaimoğlu, Esin Ayşe},
title = {Cross-Species Behavioral Representation Learning Using Domain-Adversarial Adaptation on Wearable IMU Signals},
journal = {Biomimetics},
year = {2026},
volume = {11},
number = {7},
pages = {496},
doi = {10.3390/biomimetics11070496}
}
EUVIMED