Pig behavior recognition and disease warning based on compressed sensing and long-short term memory network

Ren  Wang; Mingdong  Zhao

doi:10.6180/jase.202601_29(1).0010

Pig behavior recognition and disease warning based on compressed sensing and long-short term memory network

Ren Wang¹ and Mingdong Zhao²This email address is being protected from spambots. You need JavaScript enabled to view it.

¹Basic Department, Zhengzhou University of Science and Technology, Zhengzhou 450064 China

²School of Electronics and Electrical Engineering, Zhengzhou University of Science and Technology, Zhengzhou 450064 China

Received: March 15, 2025
Accepted: April 17, 2025
Publication Date: May 1, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202601_29(1).0010

In order to solve the problems of low precision and poor stability in pig behavior recognition process due to the deficiency of environment and hardware conditions such as complex lighting conditions, close color of target and background, poor camera Angle and parameters, a compressed sensing recognition algorithm via long and short term memory network for optimized feature extraction is proposed in this paper. By means of ellipse fitting based on the minimum cost function and target tracking based on the shortest distance matching, we design four motion information detection algorithms including motion displacement, motion velocity, motion acceleration and motion angular velocity. The preliminary application of detecting daily active state, activity pattern and behavior recognition of pigs based on motion information is further explored. The improved k-means clustering algorithm is combined with convolutional neural network and long and short term memory network to provide early warning for pig diseases. The experimental results show that the detection error rate is lower than 10%, the proposed model has relatively higher recognition and prediction accuracy than other models.

Keywords: Pig behavior recognition; disease warning; compressed sensing; long and short term memory network; k-means clustering; convolutional neural network

[1] R. Li, Y. Niu, S. R. Scott, C. Zhou, L. Lan, Z. Liang, and J. Li, (2021) “Using electronic medical record data for research in a Healthcare Information and Management Systems Society (HIMSS) Analytics Electronic Medical Record Adoption Model (EMRAM)stage7hospital in Beijing: cross-sectional study" JMIR Medical Informatics 9(8): e24405. DOI: 10.2196/24405.
[2] S. Hu, (2022) “Research on monitoring system of daily statistical indexes through big data" Recent Advances in Computer Science and Communications (Formerly: Recent Patents on Computer Science) 15(5): 731–740. DOI: 10.2174/2666255813999201113124021.
[3] L. S. dos Santos, P. H. R. F. Campos, W. C. da Silva, A. M. Veira, A. Z. Fraga, R. P. Caetano, and L. Hauschild, (2021) “Corrigendum to: Performance and carcass composition of pigs from two sire lines are affected differently by ambient temperature" Animal Production Science 61(6): 620–620. DOI: 10.1071/AN20078_CO.
[4] S.Stavrakakis, W.Li,J.H.Guy, G.Morgan, G.Ushaw, G. R. Johnson, and S. A. Edwards, (2015) “Validity of the Microsoft Kinect sensor for assessment of normal walking patterns in pigs" Computers and Electronics in Agriculture 117: 1–7. DOI: 10.1016/j.compag.2015.07.003.
[5] I. Camerlink, S. P. Turner, M. Farish, and G. Arnott, (2015) “Aggressiveness as a component of fighting ability in pigs using a game-theoretical framework" Animal Behaviour 108: 183–191. DOI: 10.1016/j.anbehav.2015.07.032.
[6] A. Yang, H. Huang, X. Zhu, X. Yang, P. Chen, S. Li, and Y. Xue, (2018) “Automatic recognition of sownursing behaviour using deep learning-based segmentation and spatial and temporal features" Biosystems Engineering 175: 133–145. DOI: 10.1016/j.biosystemseng.2018.09.011.
[7] A.Nasirahmadi, S. A. Edwards, and B. Sturm, (2017) “Implementation of machine vision for detecting behaviour of cattle and pigs" Livestock Science 202: 25–38. DOI: 10.1016/j.livsci.2017.05.014.
[8] D. Liu, M. Oczak, K. Maschat, J. Baumgartner, B. Pletzer, D. He, and T. Norton, (2020) “A computer vision-based method for spatial-temporal action recognition of tail-biting behaviour in group-housed pigs" Biosystems Engineering 195: 27–41. DOI: 10.1016/j.biosystemseng.2020.04.007.
[9] X. Meng, X. Wang, S. Yin, and H. Li, (2023) “Few-shot image classification algorithm based on attention mechanism and weight fusion" Journal of Engineering and Applied Science 70(1): 14. DOI: 10.1186/s44147-023 00186-9.
[10] M. Ju, Y. Choi, J. Seo, J. Sa, S. Lee, Y. Chung, and D. Park, (2018) “A Kinect-based segmentation of touching pigs for real-time monitoring" Sensors 18(6): 1746. DOI: 10.3390/s18061746.
[11] Z. Zhang, H. Zhang, Y. He, and T. Liu, (2022) “A review in the automatic detection of pigs behavior with sensors" Journal of Sensors 2022(1): 4519539. DOI: 10.1155/2022/4519539.
[12] R.Sidhu, J. Sachdeva, and D. Katoch, (2023) “Segmen tation of retinal blood vessels by a novel hybrid technique Principal Component Analysis (PCA) and Contrast Limited Adaptive Histogram Equalization (CLAHE)" Mi crovascular Research 148: 104477. DOI: 10.1016/j.mvr.2023.104477.
[13] Y. Fan, Y. Chen, X. Chen, H. Zhang, C. Liu, and Q. Duan, (2021) “Estimating the aquatic-plant area on a pond surface using a hue-saturation-component combi nation and an improved Otsu method" Computers and Electronics in Agriculture 188: 106372. DOI: 10.1016/j.compag.2021.106372.
[14] K. Kwon and D. Mun, (2022) “Iterative offset-based method for reconstructing a mesh model from the point cloud of a pig" Computers and Electronics in Agriculture 198: 106996. DOI: 10.1016/j.compag.2022.106996.
[15] M.vonBuelow, R. Tausch, M. Schurig, V. Knauthe, T. Wirth, S. Guthe, P. Santos, and D. W. Fellner, (2022) “Depth-of-field segmentation for near-lossless image com pression and 3d reconstruction" Journal on Computing and Cultural Heritage (JOCCH) 15(3): 1–16. DOI: 10.1145/3500924.
[16] Y. Wang, K. Luo, Z. Chen, L. Ju, and T. Guan, (2021) “Deepfusion: A simple way to improve traditional multi view stereo methods using deep learning" Knowledge Based Systems 221: 106968. DOI: 10.1016/j.knosys.2021.106968.
[17] B. Li, L. Liu, M. Shen, Y. Sun, and M. Lu, (2019) “Group-housed pig detection in video surveillance of overhead views using multi-feature template matching" Biosystems Engineering 181: 28–39. DOI: 10.1016/j.biosystemseng.2019.02.018.
[18] Y. Guo, W. Zhu, P. Jiao, and J. Chen, (2014) “Fore ground detection of group-housed pigs based on the com bination of Mixture of Gaussians using prediction mechanism and threshold segmentation" Biosystems Engineering 125: 98–104. DOI: 10.1016/j.biosystemseng.2014.07.002.
[19] R.Koju and S.R. Joshi, (2014) “Comparative analysis of color image watermarking technique in RGB, YUV, and YCbCr color channels" Nepal Journal of Science and Technology 15(2): 133–140. DOI: 10.3126/njst.v15i2.12130.
[20] Z. H. Al-Tairi, R. W. Rahmat, M. I. Saripan, and P. S. Sulaiman, (2014) “Skin segmentation using YUV and RGB color spaces" Journal of information processing systems 10(2): 283–299. DOI: 10.3745/JIPS.02.002.
[21] M. Kaseris, I. Mademlis, and I. Pitas. “Adversarial unsupervised video summarization augmented with dictionary loss”. In: 2021 IEEE International Conference on Image Processing (ICIP). IEEE. 2021, 2683–2687. DOI: 10.1109/ICIP42928.2021.9506088.
[22] L. Wang, Y. Shoulin, H. Alyami, A. A. Laghari, M. Rashid, J. Almotiri, H. J. Alyamani, and F. Alturise. Anovel deep learning-based single shot multibox detector model for object detection in optical remote sensing images. 2024. DOI: 10.1002/gdj3.162.