EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mamba-YOLO-SRC: An Automatic Deep Learning Framework for Respiratory Behavior Detection in the Chinese Giant Salamander

Dingwei Mao, Yan Zhou, Chenyang Shi, Xinyuan Zhang, Guanglin Chen, Yuanqiong Chen iD, Qinghua Luo iD

Animals · 22.06.2026 · 16 (12) · 1923

DOI: 10.3390/ani16121923 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 22.06.2026. Verfasst von Dingwei Mao und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Jishou University, Jishou 416000, China. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Excellent Youth Project of the Hunan Provincial Department of Education, Zhangjiajie Talent.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Chinese giant salamander (Andrias davidianus), a species of high ecological and conservation value, shows abnormal respiratory behaviors as early signs of health decline. Accurate assessment of its pulmonary respiration is crucial for improving captive breeding and post-breeding parental care—key strategies for its survival and population recovery. However, its nocturnal and cave-dwelling nature makes traditional observation extremely difficult. Manual monitoring suffers from poor visibility at night, while conventional detection methods often miss subtle respiratory movements, limiting behavioral and health research. To address these challenges, this study presents the first automated method for monitoring respiratory behaviors in this species. We propose Mamba-YOLO-SRC, a novel hybrid detection framework that combines Mamba and YOLO architectures to accurately identify four key behaviors: diving (Dive), head-raising (HeadUP), inhalation (Inhale), and exhalation (Exhale). The proposed model achieves a mean average precision (mAP@0.5) of 0.944, with per-class average precision scores of 0.975 for Dive, 0.925 for HeadUP, 0.948 for Exhale, and 0.928 for Inhale. Mamba-YOLO-SRC provides a feasible and referable technical solution for advancing research on the Chinese giant salamander in both captive and natural settings.

Schlagwörter

Stichwörter der Autor:innen

Andrias davidianusYOLOdeep learninghybrid detection modelrespiratory behavior

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Jishou University, Jishou 416000, China.
  • College of Life Sciences, Jishou University, Jishou 416000, China.
  • Hunan Engineering Technology Research Center for Amphibian and Reptile Resource Protection and Product Processing, College of Biological and Chemical Engineering, Changsha University, Changsha 410017, China.

ORCID-Profile: Yuanqiong Chen, Qinghua Luo

Förderung

  • National Natural Science Foundation of China
  • Excellent Youth Project of the Hunan Provincial Department of Education
  • Zhangjiajie Talent
  • Research on Precision Identification Technology of Chinese Giant Salamander Germplasm Resources in Zhangjiajie
  • Changsha University

Zitieren

APA

Mao, D., Zhou, Y., Shi, C., Zhang, X., Chen, G., Chen, Y., & Luo, Q. (2026). Mamba-YOLO-SRC: An Automatic Deep Learning Framework for Respiratory Behavior Detection in the Chinese Giant Salamander. Animals, 16(12), 1923. https://doi.org/10.3390/ani16121923

Vancouver

Mao D, Zhou Y, Shi C, Zhang X, Chen G, Chen Y, et al. Mamba-YOLO-SRC: An Automatic Deep Learning Framework for Respiratory Behavior Detection in the Chinese Giant Salamander. Animals. 2026;16(12):1923. doi:10.3390/ani16121923

BibTeX
@article{Mao2026,
  author = {Mao, Dingwei and Zhou, Yan and Shi, Chenyang and Zhang, Xinyuan and Chen, Guanglin and Chen, Yuanqiong and Luo, Qinghua},
  title = {Mamba-YOLO-SRC: An Automatic Deep Learning Framework for Respiratory Behavior Detection in the Chinese Giant Salamander},
  journal = {Animals},
  year = {2026},
  volume = {16},
  number = {12},
  pages = {1923},
  doi = {10.3390/ani16121923}
}
Kostenlos starten →