PriMera Scientific Engineering (ISSN: 2834-2550)

Research Article

Volume 5 Issue 2

Adaptive Deep Learning for Image-Based Estrus Prediction and Detection in Dairy Cows

Watchara Ninphet, Noppadol Amdee and Adisak Sangsongfa*

July 16, 2024

DOI : 10.56831/PSEN-05-143

View PDF

Abstract

Artificial intelligence (AI) technology is significant in modern daily life.  It is so influential that many consider technology the cornerstone of this era.  Even in agriculture, there is a new concept known as Smart Farming.  In a recent study, deep learning was adapted for predicting and detecting estrus in cows by adjusting the parameters of the deep learning model.  A Convolutional Neural Network utilizing the Artificial Immunity System algorithm was employed to optimize the hyperparameters.  The results of this optimization showed an accuracy of 98.361%.  YOLOv5 deep learning was also used to detect real-time estrus, with mAP50 = 0.995, mAP50-95 = 0.887, and F1-Score averages = 0.993.

Keywords: dairy cows; deep learning; estrus prediction; image

References

  1. ETDA. “Artificial intelligence in government services”.  I knowledge Sharing (2024).
  2. SAS. “What is deep learning? and how important is it?”. Deep Learning (2024).
  3. TECHSAUCE. “Get to know ai, machine learning, deep learning in an easy to understand version”. Knowledge Sharing Platform (2024).
  4. FE Streib., et al. “An introductory review of deep learning for prediction models with big data”. Frontiers in Artificial Intelligence 33 (2020): 1-23.
  5. M Fintz, M Osadchy and U Hertz. “Using deep learning to predict human decisions and using cognitive models to explain deep learning models”. Scientific Report 12.1 (2022): 4736.
  6. R Arablouei., et al. “Animal behavior classification via deep learning on embedded systems”. Computers and Electronics in Agriculture 207 (2023): 1-14.
  7. SS Khan., et al. “Hybrid deep learning approach for enhanced animal breed classification and prediction”. International Information and Engineering Technology Association 40.5 (2023): 2087-2099.
  8. T. encyclopedia for youth. “Rural agricultural development/consumption and dairy industry”. Thai Junior Encyclopedia Foundation by His Majesty King Bhumibol Adulyadej the Great 12.5 (2024): 1-5.
  9. DDP. “World dairy situation and thai 2019”. World and Thai dairy cows in 2019 raise farm standards to keep up with disease (2019).
  10. KSD Cooperative. “What is the knowledge about dairy farming?”. Knowledge (2024).  
  11. D. of Livestock. Beef cattle health care. Bangkok Thailand: Livestock Development and Technology Transfer Office Department of Livestock Development 1 (2006).
  12. VV Andrade., et al. “Estrus prediction models for dairy gyr heifers”. Animals (Basel) 11.11 (2021): 3103.
  13. W Ninphet, N Amm-Dee and A Sangsongfa. “Prediction cows estrus images using convolutional neural network with optimized parameters by the artificial immune system algorithm.” Proceedings of the 20th International Conference on Computing and Information Technology (IC2IT 2024). Springer Link 973 (2024): 105-120.
  14. R Miura., et al. “Prediction of the spontaneous estrus expression period based on large (≥ 10 mm) follicle numbers in lactating holstein dairy cows”. Veterinary Sciences, MDPI 10.3 (2023): 231.
  15. AK Yildiz and MM Ozguven. “Determination of estrus in cattle with artificial neural networks using mobility and environmental data”. Journal of Agricultural Faculty of Gaziosmanpasa University 39.1 (2022): 40-45.
  16. J Wang., et al. “Using machine-learning technique for estrus onset detection in dairy cows from acceleration and location data acquired by a neck-tag”. Biosystems Engineering 214 (2022): 193-206.
  17. I Kunakorntum. “Image detection using YOLOv5”. Medium (2021).
  18. E Zvornicanin. “What is yolo algorithm?” Baeldung (2024).
  19. S Kanoktipsatharpron. “What is the convolutional neural network ?”. BUA Lab (2019).
  20. Z Kelta. “An introduction to convolutional neural networks (cnns),” Datacamp (2023).
  21. N Karlupia., et al. “A genetic algorithm-based optimized convolutional neural network for face recognition”. Int. J. Appl. Math. Comput  33.1 (2023): 21-31.
  22. A Zafar., et al. “An optimization approach for convolutional neural network using non-dominated sorted genetic algorithm-ii”. Computers Materials and Continua 74.3 (2023): 5641-5659.
  23. Kalaiarasi P., et al. “Optimizing convolutional neural network using particle swarm optimization for face recognition”. Turkish Journal of Computer and Mathematics Education 12.11 (2021): 3672-3679.
  24. K Aguerchi., et al. “A cnn hyperparameters optimization based on particle swarm optimizationfor  mammography breast  cancer classification.” Journal  of Imaging 10.2.30 (2024): 1-17
  25. D Watnakornbuncha, N AM-DEE and A Sangsongfa. “Adaptive deep learning with optimization hybrid convolutional neural network and recurrent neural network for prediction lemon fruit ripeness.” Przeglad Elektrotechniczny 2024.3 (2024): 202-211.