Computer-Aided Lung Nodule Recognition by SVM Classifier Based on Combination of Random Undersampling and SMOTE

Table 3

The average results of the four classifiers.

Evaluation index; classifier	TP	FN	FP	TN	Accuracy	-mean	-measure
SVM classifier	26	49	5	449	0.8979	0.5855	0.4906
Biased-SVM classifier	46	29	24	430	0.8998	0.7622	0.6344
SMOTE-SVM classifier	51	24	17	437	0.9225	0.8090	0.7133
RU-SMOTE-SVM classifier	58	17	16	438	0.9376	0.8638	0.7785