Abstract
New study results on artificial intell igence have been published. According to news originating from Potsdam, Germany, by NewsRx correspondents, research stated, "Missing data and class imbalance hi nder the accurate prediction of rare events such as dairy mastitis. Resampling a nd imputation are employed to handle these problems." Financial supporters for this research include Federal Office of Agriculture And Food. The news journalists obtained a quote from the research from Leibniz Institute f or Agricultural Engineering and Bioeconomy: "These methods are often used arbitr arily, despite their profound impact on prediction due to changes caused to the data structure. We hypothesize that their use affects the performance of ML mode ls fitted to automated milking systems (AMSs) data for mastitis prediction. We c ompare three imputations-simple imputer (SI), multiple imputer (MICE) and linear interpolation (LI)-and three resampling techniques: Synthetic Minority Oversamp ling Technique (SMOTE), Support Vector Machine SMOTE (SVMSMOTE) and SMOTE with E dited Nearest Neighbors (SMOTEEN). The classifiers were logistic regression (LR) , multilayer perceptron (MLP), decision tree (DT) and random forest (RF). We eva luated them with various metrics and compared models with the kappa score. A com plete case analysis fitted the RF (0.78) better than other models, for which SI performed best."
NETL
NSTL