Prediction of Cattle Weight Using Machine Learning

• Vítor L. G. Silva UFV
• Roniel Barbosa UFV
• Jhonata Costa UFV
• Nathália Souza UFV
• Érica Schultz UFV
• Mario Chizzoti UFV
• Ricardo Ferreira UFV
• José A. M. Nacif UFV

DOI: https://doi.org/10.5753/wcama.2024.2446

Abstract

The agribusiness, which accounted for 24% of the Brazilian GDP in 2023, stands out as a robust sector. The livestock branch, contributing 6.6% to this indicator, reinforces its significant economic presence. With that said, efficient cattle-raising activity becomes crucial for the sustainability of this sector. Conventional weighing, conducted on high-cost industrial scales, induces stress in animals and workers, negatively impacting meat quality. Faced with the challenge of predicting weight, we propose an approach that utilizes machine learning with hyperparameter optimization and image segmentation before extracting essential geometric characteristics such as height and width. The best algorithm employed in the developed methodology achieved promising results in prediction: MAE of 11.12 kg and RMSE of 14.58 kg.

References

Abreu, B. A., Magalhães, C. J., Duayer, E., Machado, S. H. M., and Silva, D. A. (2015). Variação da medida torácica obtida com a fita métrica tradicional com fator de correção e com a fita de pesagem para bovinos. Acta Biomedica Brasiliensia, 6:42–48.

Agatonovic-Kustrin, S. and Beresford, R. (2000). Basic concepts of artificial neural network (ann) modelling and its application in pharmaceutical research. J. Pharmac. Biomed. Anal., 22:717–727.

Akaike, H. (2011). Akaike’s Information Criterion, pages 25–25. Springer Berlin Heidelberg, Berlin, Heidelberg.

Bergstra, J. and Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(10):281–305.

Bradski, G. (2000). The OpenCV Library. Dr. Dobb’s Journal of Software Tools.

Breiman, L. (2001). Random forests. Machine Learning, 45:5–32.

CEPEA, Centro de Estudos Avançados em Economia Aplicada e CNA, C. N. d. A. e. P. (2023). Pib do agronegócio brasileiro de 1996 a 2023. [link].

Franco, M. O., Marcondes, M. I., Campos, J. M. S., Freitas, D. R., Detmann, E., and Valadares Filho, S. C. (2017). Evaluation of body weight prediction equations in growing heifers. Acta Scientiarum. Animal Sciences, 39:201–206.

Frank, E. and Bouckaert, R. R. (2009). Conditional density estimation with class probability estimators. In Zhou, Z.-H. and Washio, T., editors, Advances in Machine Learning, pages 65–81, Berlin, Heidelberg. Springer Berlin Heidelberg.

Gjergji, M., de Moraes Weber, V., Otávio Campos Silva, L., da Costa Gomes, R., Luís Alves Campos de Araújo, T., Pistori, H., and Alvarez, M. (2020). Deep learning techniques for beef cattle body weight prediction. In 2020 International Joint Conference on Neural Networks (IJCNN), pages 1–8.

He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep residual learning for image recognition. CoRR, abs/1512.03385.

Melo, A. (2016). Fatores que influenciam na qualidade da carne bovina: Revisão. Pubvet, 10(10).

Miller, G. A., Hyslop, J. J., Barclay, D., Edwards, A., Thomson, W., and Duthie, C.A. (2019). Using 3d imaging and machine learning to predict liveweight and carcass characteristics of live finishing beef cattle. Frontiers in Sustainable Food Systems, 3.

Mnih, V., Heess, N., Graves, A., and kavukcuoglu, k. (2014). Recurrent models of visual attention. In Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., and Weinberger, K., editors, Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.

Sales, M. F. L., Paulino, M. F., Valadares Filho, S. d. C., Paulino, P. V. R., Porto, M. O., and Couto, V. R. M. (2009). Composição corporal e requisitos energéticos de bovinos de corte sob suplementação em pastejo. Revista Brasileira de Zootecnia, 38(7):1355–1362.

Siddique, N., Paheding, S., Elkin, C. P., and Devabhaktuni, V. (2021). U-net and its variants for medical image segmentation: A review of theory and applications. IEEE Access, 9:82031–82057.

Skalski, P. (2019). Make Sense. [link].

Smola, A. J. and Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14:199–222.

Tan, M. and Le, Q. V. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. CoRR, abs/1905.11946.

Wang, Z., Shadpour, S., Chan, E., Rotondo, V., Wood, K. M., and Tulpan, D. (2021). ASAS-NANP SYMPOSIUM: Applications of machine learning for livestock body weight prediction from digital images. Journal of Animal Science, 99(2):skab022.

Weber, V. A. d. M., Weber, F. d. L., Gomes, R. d. C., Oliveira Junior, A. d. S., Menezes, G. V., Abreu, U. G. P. d., Belete, N. A. d. S., and Pistori, H. (2020). Prediction of girolando cattle weight by means of body measurements extracted from images. Revista Brasileira de Zootecnia, 49:e20190110.