The performance of VCS(volume, conductivity, light scatter) parameters in distinguishing latent tuberculosis and active tuberculosis by using machine learning algorithm

Table 4 The parameters selection in the predictive models

Models	Tuning parameter
LR	Penalty = l2 C (Cost) = 100 max_iter = 100 intercept_scaling = 10
SVM	Probability = True Kernel = linear Max_iter = 100
RF	Random_state = 42 N_estimators = 150
KNN	N_neighbors = 3

Abbreviations: LR logistic regression, SVM support vector Machiner, RF random forest, KNN k-nearest neighbors classifier

ISSN: 1471-2334