Gbadegesin Taiwo
Vision transformers for automated detection of pig interactions in groups
Taiwo, Gbadegesin; Vadera, Sunil; Alameer, Ali
Authors
Prof Sunil Vadera S.Vadera@salford.ac.uk
Professor
Dr Ali Alameer A.Alameer1@salford.ac.uk
Lecturer in Artificial Intelligence
Abstract
The interactive behaviour of pigs is an important determinant of their social development and overall well-being. Manual observation and identification of contact behaviour can be time-consuming and potentially subjective. This study presents a new method for the dynamic detection of pig head to rear interaction using the Vision Transformer (ViT). The ViT model achieved a high accuracy in detecting and classifying specific interaction behaviour as trained on the pig contact datasets, capturing interaction behaviour. The model's ability to recognize contextual spatial data enables strong detection even in complex contexts, due to the use of Gaussian Error Linear Unit (GELU) an activation function responsible for introduction of non-linear data to the model and Multi Head Attention feature that ensures all relevant details contained in a data are captured in Vision Transformer. The method provides an efficient method for monitoring swine behaviour for instance, contact between pigs, facilitating better livestock management and livestock welfare. The ViT can represent a significant improvement on current automated behaviour detection, opening new possibilities for accurate animal design and animal behaviour assessment with an accuracy and F1 score of 82.8 % and 82.7 %, respectively, while we have an AUC of 85 %.
Citation
Taiwo, G., Vadera, S., & Alameer, A. (2025). Vision transformers for automated detection of pig interactions in groups. #Journal not on list, 10, Article 100774. https://doi.org/10.1016/j.atech.2025.100774
Journal Article Type | Article |
---|---|
Acceptance Date | Jan 6, 2025 |
Online Publication Date | Jan 7, 2025 |
Publication Date | 2025-03 |
Deposit Date | Jan 16, 2025 |
Publicly Available Date | Jan 16, 2025 |
Journal | Smart Agricultural Technology |
Electronic ISSN | 2772-3755 |
Peer Reviewed | Peer Reviewed |
Volume | 10 |
Article Number | 100774 |
DOI | https://doi.org/10.1016/j.atech.2025.100774 |
Files
Published Version
(6.7 Mb)
PDF
Publisher Licence URL
http://creativecommons.org/licenses/by-nc-nd/4.0/
You might also like
Explainable fault prediction using learning fuzzy cognitive maps
(2023)
Journal Article
Development of an evolutionary cost sensitive decision tree induction algorithm
(2022)
Presentation / Conference
Cost-sensitive meta-learning framework
(2021)
Journal Article
Case studies in applying data mining for churn analysis
(2017)
Journal Article
Downloadable Citations
About USIR
Administrator e-mail: library-research@salford.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search