Unsupervised Anomaly Detection with Continuous-Time Model for Pig Farm Environmental Data

Heng Zhou, Seyeon Chung, Malik Muhammad Waqar, Muhammad Ibrahim Zain Ul Abideen, Arsalan Ahmad, Muhammad Ans Ilyas, Hyongsuk Kim and Sangcheol Kim ()
Additional contact information
Heng Zhou: Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
Seyeon Chung: Core Research Institute of Intelligent Robots, Jeonbuk National University, Jeonju 54896, Republic of Korea
Malik Muhammad Waqar: Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
Muhammad Ibrahim Zain Ul Abideen: Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
Arsalan Ahmad: Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
Muhammad Ans Ilyas: Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea
Hyongsuk Kim: Core Research Institute of Intelligent Robots, Jeonbuk National University, Jeonju 54896, Republic of Korea
Sangcheol Kim: Core Research Institute of Intelligent Robots, Jeonbuk National University, Jeonju 54896, Republic of Korea

Agriculture, 2025, vol. 15, issue 13, 1-20

Abstract: Environmental air anomaly detection is crucial for ensuring the healthy growth of livestock in smart pig farming systems. This study focuses on four key environmental variables within pig housing: temperature, relative humidity, carbon dioxide concentration, and ammonia concentration. Based on these variables, it proposes a novel encoder–decoder architecture for anomaly detection based on continuous-time models. The proposed framework consists of two embedding layers: an encoder module built around a continuous-time neural network, and a decoder composed of multilayer perceptrons. The model is trained in a self-supervised manner and optimized using a reconstruction-based loss function. Extensive experiments are conducted on a multivariate multi-sequence dataset collected from real-world pig farming environments. Experimental results show that the proposed architecture significantly outperforms existing transformer-based methods, achieving 92.39% accuracy, 92.08% precision, 85.84% recall, and an F 1 score of 88.19%. These findings highlight the practical value of accurate anomaly detection in smart farming systems; timely identification of environmental irregularities enables proactive intervention, reduces animal stress, minimizes disease risk, and ultimately improves the sustainability and productivity of livestock operations.

Keywords: smart farming; anomaly detection; continuous-time model (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/13/1419/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/13/1419/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:15:y:2025:i:13:p:1419-:d:1691579

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().