Estimation of the factors affecting lactation milk yield of Holstein cattle by the adaptive neuro-fuzzy inference system

The aim of this study is to estimate lactation milk yield of Holstein cattle using first calving age, lactation period, and service period with (ANFIS) adaptive neuro-fuzzy inference system. The input variables for the system in the study were first calving age, lactation period, and service period. The output variable from the system was lactation milk yield. Predicted values obtained from the ANFIS were compared with the observed values. Twenty-seven rule functions are used to obtain the best model and 1000 epochs are used to estimate the accuracy of the training and testing error. The relations between the output and input variables are shown with 3D graphics. R2 , RMSE, and MAPE evaluation criteria were used to check the accuracy of the system’s estimations. As a result, ANFIS estimates of lactation milk yield were quite close to the observed values and a positive correlation (r: 0.848) was found between them. The results showed that ANFIS can be successfully applied to estimate the lactation milk yield.

PDF

___

1. Erdem H, Atasever S, Kul E. Gökhöyük tarım işletmesinde yetiştirilen Siyah Alaca sığırların süt ve döl verim özellikleri 1. süt verim özellikleri. Anadolu Tarım Bilimleri Dergisi 1997; 22 (1): 41-46 (in Turkish).
2. Arıtürk E, Yalçın BC. Hayvan yetiştirmede seleksiyon. Ankara Üniversitesi Veteriner Fakültesi Yayınları 1966; Yayın no: 194 (in Turkish).
3. Mundan D, Karabulut O, Sehar Ö. Holştayn ineklerde laktasyon süt verimini tahmin eden en iyi doğrusal regresyon modelinin belirlenmesi. Fırat Üniversitesi Sağlık Bilimleri Veteriner Dergisi 2009; 23 (3): 129-134 (in Turkish).
4. Bakhtyar R, Bakhtiary AY, Ghaheri A. Application of neurofuzzy approach in prediction of runup in Swash Zone. Applied Ocean Research 2008; 30 (1): 17-27. doi: 10.1016/j. apor.2008.02.004
5. Pitalúa N, Penaloza UC, Ruz-Hernandez JA, Jimenez RL. Introducción a los sistemas inteligentes. Departamento de Editorial Universitaria (UABC), Mexicali, Baja California, Mexico 2008; ISBN: 978-607-7753-47-6 (in Spanish).
6. Jang JS. ANFIS: Adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics 1993; 23 (3): 665-685.
7. Fahimifard SM, Homayounifar M, Sabouhi M, Moghaddamnia AR. Comparison of Anfis, Ann, Garch and Arima techniques to exchange rate forecasting. Journal of Applied Sciences 2009; 9 (20): 3641-3651.
8. Wang WC, Chau KW, Cheng CT, Qiu L. A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. Journal of Hydrology 2009; 374 (3-4): 294-306. Doi: 10.1016/j.jhydrol.2009.06.019
9. Vural Y, Ingham DB, Pourkashanian M. Performance prediction of a proton exchange membrane fuel cell using the Anfis model. International Journal of Hydrogen. Energy 2009; 34 (22): 9181-9187. doi: 10.1016/j.ijhydene.2009.08.096
10. Esen H, Inalli M. Ann and Anfis models for performance evaluation of a vertical ground source heat pump system. Expert Systems with Applications 2010; 37 (12): 8134-8147. doi: 10.1016/j.eswa.2010.05.074
11. Sitkowska B, Piwczyński D, Lach Z, Kolenda M. Relationship between primiparas first 100-days lactation and their lifetime milk production in polish Holstein-Friesian cattle. Journal of Central European Agriculture 2015; 16 (3): 1-12. doi: 10.5513/ jcea.v16i3.3637.
12. Görgülü O. Prediction of 305 days milk yield from early records in dairy cattle using on fuzzy inference system. The Journal of Animal and Plant Sciences 2018; 28 (4): 996-1001.
13. Olori VE, Brotherstone S, Hill WG, McGuirk BJ. Fit of standard models of the lactation curve to weekly records of milk production of cows in a single herd. Livestock Production Science 1999; 58 (1): 55-63.
14. Görgülü O. Path analysis on effective factors affecting 305- d milk yield in Simmental cattle. International Journal of Agriculture and Biology 2011; 13 (3): 381-385.
15. Moore RK, Kennedy BW, Schaeffer LR, Moxley JE. Relationships between age and body weight at calving and production in first lactation Ayrshires and Holsteins. Journal of Dairy Science 1991; 74: 269-278
16. Pirlo G, Miglior F, Speroni M. Effect of age at first calving on production traits and on difference between milk yield returns and rearing costs in Italian Holsteins. Journal of Dairy Science 2000; 83: 603-608
17. Bayram B, Yanar M, Akbulut O. The effect of average daily gain and age at first calving on reproductive and milk production traits of Brown Swiss and Holstein Friesian cattle. Bulgarian Journal of Agricultural Science 2009; 15: 453-462.
18. Salazar-Carranza M, Castillo-Badilla G, Murillo-Herrera J, Hueckmann-Voss F, Romero-Zuniga JJ. Effect of age at first calving on first lactation milk yield in Holstein cattles from Costa Rican specialized dairy herds. Open Journal of Veterinary Medicine 2014; 4: 197-203. doi: 10.4236/ojvm.2014.49023
19. Hutchison JL, Van Raden DJ, Cole JB, Bickhartt DM. Genomic evaluation of age at first calving. Journal of Dairy Science 2017; 100: 1-9. Doi: 10.3168/jds.2016-12060
20. Grzesiak W, Lacroix R, Wójcik J, Blaszczyk P. A comparison of neural network and multiple regression predictions for 305- day lactation yield using partial lactation records. Canadian Journal of Animal Science 2003; 83 (1): 307-310.
21. Ranjan SK, Lakhera ML, Singh M. Development of prediction equations for 300 days milk yield from part yields, cumulative part and sequential monthly records in Sahiwal cows. International Journal of Agriculture and Biology 2005; 7 (4): 574-578.
22. Njubi DM, Wakhungu JW, Badamana MS. Use of test day records to predict first lactation 305 day milk yield using artificial neural network in Kenyan Holstein-Friesian dairy cows. Tropical Animal Health and Production 2010; 42 (4): 639-644. doi: 10.1007/s11250-009-9468-7