Skip to main content
. 2023 Dec 1;10(12):1386. doi: 10.3390/bioengineering10121386

Figure 2.

Figure 2

Model selection using Bayesian grid search, performed for each endpoint. Pre-processed data of the selected features is used by the Bayesian grid search algorithm for each of the three classifier types. In each cycle, the model is tested using 10-fold cross-validation and the hyperparameters are automatically adjusted. After a pre-defined number of iterations, the process returns the final model. MLP: multilayer perceptron; RF: random forest; XGB: extreme gradient boosting.