Skip to main content
. 2022 Jun 7;60(8):2245–2255. doi: 10.1007/s11517-022-02591-3

Table 7.

Performance of ChaosFEX+SVM for the binary class classification problem using LOOCV

ChaosFEX+SVM Random forest SVM
Classification Class-0 Class-1 Class-0 Class-1 Class-0 Class-1
measures
SE 1.0 1.0 1.0 0.990 1.0 1.0
SP 1.0 1.0 0.990 1.0 1.0 1.0
ACC 1.0 1.0 0.999 0.999 1.0 1.0
PPV 1.0 1.0 0.999 1.0 1.0 1.0
NPV 1.0 1.0 1.0 0.999 1.0 1.0
FPR 0 0 0.009 0 0 0
FDR 0 0 0.0002 0 0 0
FNR 0 0 0 0.009 0 0
F1-score 1.0 1.0 0.999 0.995 1.0 1.0

In the case of random forest, the first three significant values of the performance metric are used. This is done in order to avoid misinterpretation since several metric values close to 1.0 would be rounded to 1.0