From: A comparative study of the svm and k-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals
Kernel
Validation method
Classification accuracy (%)
Linear
Conventional validation
86.91 ± 1.47
RBF
89.54 ± 0.39
Ten-fold cross-validation
90.13 ± 0.54
91.47 ± 1.66