Skip to main content
. 2021 Jul 1;11:13642. doi: 10.1038/s41598-021-93056-4

Figure 4.

Figure 4

Comparison of the performance [false negative error (FN.ERR), false positive error (FP.ERR) and total error (TOT.ERR)] of eight machine learning methods [Classification and Regression Trees (CART), Generalized Linear Model (GLM) with logit link function, k-Nearest Neighbors (kNN), Linear Discriminant Analysis (LDA), Naïve Bayes (NB), Neural Network (NN), Random Forest (RF) and Support Vector Machines (SVM)] run on the validation set, in prediction of udder health status of dairy cows according to somatic cell count below or above 200,000 cells/mL from cow’s and milk data recorded at the previous test-day record.