Artificial neural networks for predicting first-lactation 305-day milk yield in crossbred cattle
DOI:
https://doi.org/10.4314/sajas.v55i1.01Keywords:
Bayesian regularisation, milk, multiple linear regression, Vrindavani cattleAbstract
This study was conducted using the first-lactation records of 1092 Vrindavani crossbred cattle to compare the relative efficiency of an artificial neural network (ANN) versus multiple linear regression for predicting the first-lactation 305-day milk yield (FL305DMY). The two input sets used for predicting FL305DMY in the study were input set-1: first four monthly test-day milk yields, age at first calving, and peak milk yield; and input set-2: first four monthly milk yields, age at first calving, and peak milk yield. The ANN was trained using a backpropagation algorithm based on Bayesian regularisation, and the algorithm was tested using four sets of training and test data at ratios of 66.67:33.33, 75:25, 80:20, and 90:10. The results revealed that the coefficient of determination showed no regular trend with decreasing the test dataset. Nevertheless, the observed values were highest for the 90:10 ratio of training-test data for both input sets, with the lowest root mean square error. The ANN model outperformed the multiple linear regression model when predicting FL305DMY, with an accuracy of 79.09% for input set-1 and 83.67% for input set-2, with the lowest root mean square error values for both input sets. Therefore, the ANN model can be used as an alternative technique to predict FL305DMY in Vrindavani cows.
Submitted 30 June 2024; Accepted 20 December 2024; Published January 2025
------------------------------------------------------------------
Significance of research to South African science
The research demonstrates the potential of artificial neural networks (ANNs) to enhance dairy herd management through accurate early prediction of first-lactation 305-day milk yield in crossbred cattle. The study compares ANN and multiple linear regression models, showing that ANNs provide superior predictive accuracy and lower error margins. This has important implications for local dairy farming systems, particularly in data-limited environments, as it offers a practical tool for early identification of high- and low-producing cows. By enabling data-driven selection and culling decisions, the approach supports improved productivity, genetic progress, and economic efficiency in the South African livestock sector.
References
Abd El-Hack, M.E., Abdelnour, S.A., Swelum, A.A., & Arif, M., 2018. The application of gene marker-assisted selection and proteomics for the best meat quality criteria and body measurements in Qinchuan cattle breed. Mol. Biol. Rep., 45, 1445–1456. doi 10.1007/s11033-018-4211-y
Abdelnour, S.A., Abd El-Hack, M.E., Khafaga, A.F., Arif, M., Taha, A.E., & Noreldin, A.E., 2019. Stress biomarkers and proteomics alteration to thermal stress in ruminants: A review. J. Therm. Biol., 79, 120–134. doi 10.1016/j.jtherbio.2018.12.013
Bhosale, M.D. & Singh, T.P., 2015. Comparative study of feed-forward neuro-computing with multiple linear regression model for milk yield prediction in dairy cattle. Curr. Sci., 108(12), 2257–2260. doi 10.18520/cs/v113/i05/951-955
Chandrakar, J., 2018. Prediction of 305 days milk yield using test day milk records in crossbred cattle. MSc thesis, Deemed University, Indian Veterinary Research Institute, Bareilly, India.
Dongre, V.B., Gandhi, R.S., Singh, A., & Ruhil, A.P., 2012. Comparative efficiency of artificial neural networks and multiple linear regression analysis for prediction of first lactation 305-day milk yield in Sahiwal cattle. Livest. Sci., 147(1–3), 192–197. doi 10.1016/j.livsci.2012.04.002
Foresee, F.D. & Hagan, M.T., 1997. Gauss-Newton approximation to Bayesian regularization. In: Proceedings of the IEEE International Joint Conference on Neural Networks, vol. 3, 1930–1935. doi 10.1109/ijcnn.1999.831145
Gabriel, J., 2016. Artificial Intelligence: Artificial Intelligence for Humans (1st ed). CreateSpace Independent Publishing Platform, USA. doi 10.1093/wentk/9780190602383.003.0001
Gandhi, R.S., Monalisa, D., Dongre, V.B., Ruhil, A.P., Singh, A., & Sachdeva, G.K., 2012. Prediction of first lactation 305-day milk yield based on monthly test day records using artificial neural networks in Sahiwal cattle. Indian J. Dairy Sci., 65(3), 229–233. doi 10.18805/ijar.b-3963
Gandhi, R.S., Raja, T., Ruhil, A.P., & Kumar, A., 2009. Prediction of lifetime milk production using artificial neural network in Sahiwal cattle. Indian J. Anim. Sci., 79, 1038–1040. doi 10.56093/ijans.v85i5.48567
Gandhi, R.S., Raja, T., Ruhil, A.P., & Kumar, A., 2010. Artificial neural network versus multiple regression analysis for prediction of lifetime milk production in Sahiwal Cattle. J. Appl. Anim. Res., 38, 233–237. doi 10.1080/09712119.2010.10539517
Ghedira, H. & Bernier, M., 2004. The effect of some internal neural network parameters on SAR texture classification performance. In: Proceedings of the IEEE International Geosciences and Remote Sensing Symposium, 6, Anchorage, Alaska, USA. pp: 3845–3848. doi 10.1109/igarss.2004.1369962
Gorgulu, O., 2012. Prediction of 305-day milk yield in Brown Swiss cattle using artificial neural networks. S. Afr. J. Anim. Sci., 42(3), 208–287. doi 10.4314/sajas.v39i1.43540
Grzesiak, W., Błaszczyk, P., & Lacroix, R., 2006. Methods of predicting milk yield in dairy cows—Predictive capabilities of Wood’s lactation curve and artificial neural networks (ANNs). Comp. Electron. Agric., 54(2), 69–83. doi 10.1016/j.compag.2006.08.004
Grzesiak, W., Lacroix, R., Wójcik, J., & Blaszczyk, P., 2003. A comparison of neural network and multiple regression predictions for 305-day lactation yield using partial lactation records. Canadian J. Anim. Sci., 83(2), 307–310. doi 10.4141/a02-002
Hagan, M.T. & Menhaj, M.B., 1994. Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neur. Net., 5(6), 989–993. doi 10.1109/72.329697
Kominakis, A.P., Abas, Z., Maltaris, I., & Rogdakis, E., 2002. A preliminary study of the application of artificial neural networks to prediction of milk yield in dairy sheep. Comp. Electron. Agric., 35(1), 35–48. doi 10.1016/s0168-1699(02)00051-0
Lacroix, R., Salehi, F., Yang, X.Z., & Wade, K.M., 1997. Effects of data pre-processing on the performance of artificial neural network for dairy yield prediction and cow culling classification. Trans. American Soc. Agric. Engin., 40, 839–846. doi 10.13031/2013.21294
Lacroix, R., Wade, K.M., Kok, R., & Hayes, J.F., 1995. Prediction of cow performance with a connectionist model. Trans. American Soc. Agric. Engin., 38, 1573–1579. doi 10.13031/2013.27984
Mundhe, U.T., Gandhi, R.S., Das, D.N., Dongre, V.B., & Gupta, A., 2015. Genetic and non-genetic factors affecting monthly part lactation milk yields in Sahiwal cattle. Indian J. Anim. Sci., 85(5), 517–518. doi 10.56093/ijans.v85i5.48586
Njubi, D.M., Wakhungu, J.W., & Badamana, M.S., 2010. Use of test-day records to predict first lactation 305-day milk yield using artificial neural network in Kenyan Holstein–Friesian dairy cows. Trop. Anim. Health Prod., 42, 639–644. doi 10.1007/s11250-009-9468-7
Nosrati M., Hafezian S.H., & Gholizadeh M., 2021. Estimating heritabilities and breeding values for real and predicted milk production in Holstein dairy cows with artificial neural network and multiple linear regression models. Iranian J. Appl. Anim. Sci., 11(1), 67–78. doi 10.31274/rtd-180816-3754
Raza, S.H.A., Kaster, N., Khan, R., Abdelnour, S.A., El-Hack, M.E.A., Khafaga, A.F., Taha, A., Ohran, H., Swelum, A.A., Schreurs, N.M., & Zan, L., 2020b. The role of microRNAs in muscle tissue development in beef cattle. Genes, 11(3), 295. doi 10.3390/genes11030295
Raza, S.H.A., Khan, S., Amjadi, M., Abdelnour, S.A., Ohran, H., Alanazi, K.M., Abd El-Hack, M.E., Taha, A.E., Khan, R., Gong, C., Schreurs, N.M., Zhao, C., Wei, D., & Zan, L., 2020a. Genome-wide association studies reveal novel loci associated with carcass and body measures in beef cattle. Arch. Biochem. Biophys., 694, 108543. doi 10.1016/j.abb.2020.108543
Saini, T., Gahlot, G.C., & Kachwaha, R.N., 2005. Prediction of 300 days lactation yield on the basis of test day milk yield in Rathi Cows. Indian J. Anim. Sci., 75(9), 1087–1089. doi 10.18805/ijar.b-3963
Salehi, F., Lacroix, R., & Wade, K.M., 1998. Effects of learning parameters and data presentation on the performance of back-propagation networks for milk yield prediction. Trans. American Soc. Agric. Engin., 41, 253–259. doi 10.13031/2013.17144
Sanzogni, L. & Kerr, D., 2001. Milk production estimates using feed forward artificial neural networks. Comp. Electron Agric., 32(1), 21–30. doi 10.1016/s0168-1699(01)00151-x
Sharma, A.K., Sharma, R.K., & Kasana, H.S., 2006. Empirical comparisons of feed forward connectionist and conventional regression models for prediction of first lactation 305-day milk yield in Karan Fries dairy cows. Neur. Comp. Appl., 15, 359–365. doi 10.1007/s00521-006-0037-y
Sharma, A.K., Sharma, R.K., & Kasana, H.S., 2007. Prediction of first lactation 305-day milk yield in Karan Fries dairy cattle using ANN modelling. Appl. Soft Comp., 7, 1112–1120. doi 10.1016/j.asoc.2006.07.002
Singh, R.R., Dutt, T., Kumar, A., Tomar, A.K.S., & Singh, M., 2011. On-farm characterization of Vrindavani cattle in India. Indian J. Anim. Sci., 81(3), 267–271. doi 10.56093/ijans.v83i12.35805
Youssef, N.H., El Gammal, M.H., Altaie, H.A., Qadhi, A., Tufarelli, V., Losacco, C., Abd El-Hack, M. E., & Abdelsalam, N. R., 2023. Mycotoxins in milk: Occurrence and evaluation of certain detoxification attempts. Food Sci. Nut., 11(6), 2751–2766. doi 10.1002/fsn3.3254
Published
Issue
Section
License
Copyright (c) 2025 SM Usman, A Kumar, A Sherasiya, IM Youssef, MM Abo Ghanima, J Chandrakar, R Tiwari, NP Singh, QS Sahib, T Dutt, AA Swelum (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
- Abstract 119
- PDF 22
- XML 2
