EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Conformer-Based Time–Frequency Decoupling Network for Pig Vocalization Behavior Classification

Jianping Wang iD, Yuqing Liu, Siao Geng, Feng Wei, Haoyu Wu iD, Yuzhen Song, Yingying Lv, Shugang Li, Qian Li

Animals · 27.04.2026 · 16 (9) · 1337

DOI: 10.3390/ani16091337 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 27.04.2026. Verfasst von Jianping Wang und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Henan Institute of Science and Technology, Xinxiang 453003, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Key Scientific and Technological Project of Henan Province, he Key Scientific and Technological Project of Henan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Continuous monitoring of pig behavior is essential for timely health management and welfare assessment in commercial production systems. Although vision-based methods have been widely studied, their practical application in commercial barns is often limited by variable lighting, frequent occlusion, and high stocking density. Acoustic sensing offers a non-contact alternative that is independent of lighting conditions; however, reliable behavior classification from pig vocalizations remains challenging in commercial environments because of background noise and temporal variability in sound patterns. In this study, an attention-guided acoustic framework, termed ATF-Conformer, was developed for pig vocalization classification under farm conditions. A five-class vocalization dataset was collected from finishing Landrace pigs and multiparous sows on a commercial farm, including cough, scream, estrus, feeding, and normal behavior sounds. The proposed framework combined spectrogram denoising with interactive attention to enhance behavior-related acoustic information, while a time-frequency-decoupled Conformer encoder was introduced to improve feature representation under noisy conditions. Final classification was performed using mask-based temporal pooling with an additive angular margin Softmax objective. In five-fold grouped cross-validation, ATF-Conformer achieved an accuracy of 97.34% ± 0.42 and outperformed several existing acoustic models across multiple evaluation metrics. A similar accuracy of 97.38% was obtained on an independent test set, indicating stable performance across datasets. These results suggest that the proposed method can support continuous, non-invasive pig vocalization-based behavior monitoring and may assist farm owners or workers in pen-level screening of frequent cough or abnormal vocal events, thereby supporting targeted on-site inspection in precision livestock farming.

Schlagwörter

Stichwörter der Autor:innen

ATF-Conformeracoustic monitoringbehavioral vocalizationspig behaviorprecision livestock farmingvocalization classification

Autor:innen und Institutionen

  • School of Computer Science and Technology, Henan Institute of Science and Technology, Xinxiang 453003, China.
  • School of Foreign Studies, Henan Agricultural University, Zhengzhou 450002, China.
  • School of Computing, Xinxiang Vocational and Technical College, Xinxiang 453006, China.

ORCID-Profile: Jianping Wang, Haoyu Wu

Förderung

  • the Key Scientific and Technological Project of Henan Province
  • he Key Scientific and Technological Project of Henan Province

Zitieren

APA

Wang, J., Liu, Y., Geng, S., Wei, F., Wu, H., Song, Y., Lv, Y., Li, S., & Li, Q. (2026). A Conformer-Based Time–Frequency Decoupling Network for Pig Vocalization Behavior Classification. Animals, 16(9), 1337. https://doi.org/10.3390/ani16091337

Vancouver

Wang J, Liu Y, Geng S, Wei F, Wu H, Song Y, et al. A Conformer-Based Time–Frequency Decoupling Network for Pig Vocalization Behavior Classification. Animals. 2026;16(9):1337. doi:10.3390/ani16091337

BibTeX
@article{Wang2026,
  author = {Wang, Jianping and Liu, Yuqing and Geng, Siao and Wei, Feng and Wu, Haoyu and Song, Yuzhen and Lv, Yingying and Li, Shugang and Li, Qian},
  title = {A Conformer-Based Time–Frequency Decoupling Network for Pig Vocalization Behavior Classification},
  journal = {Animals},
  year = {2026},
  volume = {16},
  number = {9},
  pages = {1337},
  doi = {10.3390/ani16091337}
}
Kostenlos starten →