Skip to main content

Table 3 Values of tuned hyper-parameters of five ML algorithms using ten-fold cross validation

From: Classification of failure modes of pipelines containing longitudinal surface cracks using mechanics-based and machine learning models

Algorithm

Tuned hyper-parameters

NB

priors = [0.357, 0.643]a

SVM

C = 230; γG = 1.3

DT

min_samples_split = 7; min_samples_leaf = 1; max_depth = 21

RF

n_estimators = 106; min_samples_split = 2; min_samples_leaf = 1; max_features = 2; max_depth = 25

GB

n_estimators = 167; min_samples_split = 7; min_samples_leaf = 4; max_depth = 5; learning_rate = 0.5