Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms
Autor: | Cinzia Marchitelli, Hélène Soyeurt, Yves Brostaux, Clément Grelet, Alessandra Crisà, Eric Froidmont, Frédéric Dehareng, Anthony Tedde, Dirk Werling, HEDI HAMMAMI, Nicolas Gengler, Graham Plastow, Tine Rousing, Federica Signorelli, Mark Crowe, Leslie Foldager |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Mean squared error
Veterinary medicine Feature selection Article 03 medical and health sciences Milk yield feature selection SF600-1100 Statistics dairy cow bodyweight dairy cows Uncategorized 030304 developmental biology Mathematics dimensionality reduction 0303 health sciences General Veterinary Dimensionality reduction 0402 animal and dairy science External validation 04 agricultural and veterinary sciences veterinary(all) 040201 dairy & animal science Moment (mathematics) machine learning QL1-991 Feature (computer vision) mid infrared spectra Herd partial least square Animal Science and Zoology Zoology |
Zdroj: | Animals : an Open Access Journal from MDPI Animals, 11(5), 1. Multidisciplinary Digital Publishing Institute (MDPI) Tedde, A, Grelet, C, Ho, P N, Pryce, J E, Hailemariam, D, Wang, Z, Plastow, G, Gengler, N, Brostaux, Y, Froidmont, E, Dehareng, F, Bertozzi, C, Crowe, M A, Dufrasne, I, GplusE Consortium & Soyeurt, H 2021, ' Validation of dairy cow bodyweight prediction using traits easily recorded by dairy herd improvement organizations and its potential improvement using feature selection algorithms ', Animals, vol. 11, no. 5, 1288 . https://doi.org/10.3390/ani11051288 Animals Volume 11 Issue 5 Animals, Vol 11, Iss 1288, p 1288 (2021) |
ISSN: | 2076-2615 |
Popis: | Simple Summary First, the current work consisted of validating the feasibility of large-scale dairy cow bodyweight prediction from models involving the day in milk, milk yield, parity, and milk mid-infrared spectrum. Second, it aimed to improve the accuracy of predictive models by using feature selection algorithms to decrease the number of predictors to limit overfitting. The models, using accessible and low-cost measurements, provided highly reproducible predictions. These could be easily obtained on an individual basis throughout a cow’s productive life by dairy herd improvement organizations, thus providing potentially relevant information for the dairy farmer at three levels: economics (reproductive performance), animal welfare (disease detection), and environment (methane production). Abstract Knowing the body weight (BW) of a cow at a specific moment or measuring its changes through time is of interest for management purposes. The current work aimed to validate the feasibility of predicting BW using the day in milk, parity, milk yield, and milk mid-infrared (MIR) spectrum from a multiple-country dataset and reduce the number of predictors to limit the risk of over-fitting and potentially improve its accuracy. The BW modeling procedure involved feature selections and herd-independent validation in identifying the most interesting subsets of predictors and then external validation of the models. From 1849 records collected in 9 herds from 360 Holstein cows, the best performing models achieved a root mean square error (RMSE) for the herd-independent validation between 52 ± 2.34 kg to 56 ± 3.16 kg, including from 5 to 62 predictors. Among these models, three performed remarkably well in external validation using an independent dataset (N = 4067), resulting in RMSE ranging from 52 to 56 kg. The results suggest that multiple optimal BW predictive models coexist due to the high correlations between adjacent spectral points. |
Databáze: | OpenAIRE |
Externí odkaz: |