2022
DOI: 10.1016/j.animal.2022.100658
|View full text |Cite
|
Sign up to set email alerts
|

Prediction of first test day milk yield using historical records in dairy cows

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
5
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(6 citation statements)
references
References 25 publications
1
5
0
Order By: Relevance
“…The calculated performance of all models demonstrates the potential of using historical production data to predict milk production and milk components in young cows. The MPIs observed in all models are similar to the results of Dallago et al (2019) and Salamone et al (2022), including RMSEs that fall within the margins of the theoretical minimum of 6 kg proposed by Cole et al (2012) for predicting daily milk production. This is due to variability resulting from environmental and health changes, as explained by Cole et al (2012).…”
Section: Discussionsupporting
confidence: 85%
See 1 more Smart Citation
“…The calculated performance of all models demonstrates the potential of using historical production data to predict milk production and milk components in young cows. The MPIs observed in all models are similar to the results of Dallago et al (2019) and Salamone et al (2022), including RMSEs that fall within the margins of the theoretical minimum of 6 kg proposed by Cole et al (2012) for predicting daily milk production. This is due to variability resulting from environmental and health changes, as explained by Cole et al (2012).…”
Section: Discussionsupporting
confidence: 85%
“…The small differences in MPIs in our case can be explained in part by the limited contribution of the characteristics of Tunisian herds raised, for the most part, in low‐input systems, which limits prediction. In such situations, Salamone et al (2022) suggest including less parametrized models to assess when a real difference can be observed. According to Olori, Hill, and Brotherstone (1999), improved fit can also be achieved through more accurate RV estimation when more independent estimates at different stages of lactation are allowed with the removal of the constraint on variation, especially at the beginning and end of lactation.…”
Section: Discussionmentioning
confidence: 99%
“…Model evaluation was carried out on test data with four metrics frequently used in similar research: coefficient of determination (R 2 ), RMSE, the mean absolute error (MAE) and the mean absolute percentage error (MAPE) ( 45–47 ). R 2 indicates the proportion of the variance of decay-305 explained by the independent variables.…”
Section: Methodsmentioning
confidence: 99%
“…Salamone et al [37] aimed to predict the milk yield on the first test day, starting with the routine data of previous lactations. They employed the random forest regression (RFR) algorithm on three different datasets to denote the best configuration for achieving higher results in terms of root mean squared error (RMSE), mean absolute error (MAE), and R 2 .…”
Section: Prediction Of Performancementioning
confidence: 99%
“…Several works reported the main limitations of their analysis. For example, Salamone et al [37] noted that the main limitation of their work is the absence of a high-quality disease registration dataset. The latter condition has negatively influenced the quality of their results.…”
Section: Limitation and Obstacles In Machine Learningmentioning
confidence: 99%