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
89.17 ± 1.32
RBF
91.36 ± 1.69
Ten-fold cross-validation
89.91 ± 2.39
92.19 ± 1.58