Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 13, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

BAE-LiteNet: a lightweight behavior-aware network with diffusion-based augmentation for sow estrus vocalization

Yingying Lv1, Jianping Wang1, Yuzhen Song1

  • 1School of Computer Science and Technology, Henan Institute of Science and Technology, Xinxiang, China.

Journal of Animal Science
|May 11, 2026
PubMed
Summary

Related Concept Videos

Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

CFR-YOLO: A Novel Cow Face Detection Network Based on YOLOv7 Improvement.

Sensors (Basel, Switzerland)·2025
Same author

Effect of Asymmetric Corneal Curvature on Optical Zone Decentration and Refractive Outcomes in SMILE for Myopic Astigmatism.

Journal of refractive surgery (Thorofare, N.J. : 1995)·2025
Same author

LWheatNet: a lightweight convolutional neural network with mixed attention mechanism for wheat seed classification.

Frontiers in plant science·2025
Same author

SGSNet: a lightweight deep learning model for strawberry growth stage detection.

Frontiers in plant science·2024
Same author

Experimental data simulating lithium battery charging and discharging tests under different external constraint pressure conditions.

Data in brief·2024
Same author

CNN-Bi-LSTM: A Complex Environment-Oriented Cattle Behavior Classification Network Based on the Fusion of CNN and Bi-LSTM.

Sensors (Basel, Switzerland)·2023

This study introduces BAE-LiteNet, an efficient AI model for recognizing sow estrus vocalizations. It achieves high accuracy even with limited data and noise, aiding livestock reproductive management.

Area of Science:

  • Agricultural Science
  • Artificial Intelligence
  • Bioacoustics

Background:

  • Accurate sow estrus detection is crucial for efficient pig farming, but faces challenges like limited data and background noise.
  • Existing methods for recognizing sow vocalizations are often constrained by data scarcity and environmental interference.

Purpose of the Study:

  • To develop an efficient and accurate model for sow estrus vocalization recognition.
  • To address data imbalance and noise issues in livestock audio monitoring.

Main Methods:

  • Proposed BAE-LiteNet, integrating diffusion-based data augmentation with a lightweight, behavior-aware recognition model.
  • Utilized a conditional diffusion model for generating high-fidelity estrus audio samples to overcome data scarcity.
  • Employed a multi-scale convolutional front-end and a behavior-aware deep feedforward sequential memory network (BA-DFSMN) for recognition.
Keywords:
acoustic behavior recognitionbehavior-aware temporal modelingdiffusion-based data augmentationlightweight neural networksow estrus detection

Related Experiment Videos

Last Updated: May 13, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Main Results:

  • BAE-LiteNet achieved 98.18% accuracy and 98.17% F1-score with only 0.75 million parameters.
  • Demonstrated robustness in noisy and imbalanced conditions through comparative and ablation studies.
  • Generated high-fidelity audio samples, reducing annotation costs while preserving behavioral features.

Conclusions:

  • BAE-LiteNet offers a non-invasive and efficient solution for sow estrus monitoring in livestock farming.
  • The model's performance highlights the potential of diffusion models for data augmentation in bioacoustics.
  • The lightweight and behavior-aware design makes BAE-LiteNet suitable for practical deployment in pig farming environments.