Fig. 2 | Scientific Reports

Fig. 2

From: Monitoring of ultra-high performance concrete manufacturing for reproducible quality and waste reduction

Fig. 2

Model training and evaluation workflow. The outer loop uses leave-one-out cross-validation (LOOCV), holding out one sample per iteration to estimate performance on unseen data. The inner loop performs 10-fold cross-validation on the training set to optimize hyperparameters. Held-out predictions from all LOOCV folds are concatenated to compute the coefficient of determination (\(R^2\)), mean absolute error (MAE), and mean absolute percentage error (MAPE). (BPM: best-performing model).

Back to article page