Skip to main content
. 2021 Dec 17;141:105153. doi: 10.1016/j.compbiomed.2021.105153

Fig. 6.

Fig. 6

COVID-19 breath classification: An SVM classifier using bottleneck features (BNF) achieved the highest AUC of 0.942 when classifying COVID-19 breath. The Resnet50 with and without the transfer learning has achieved AUCs of 0.934 and 0.923 respectively, with higher σAUC for the latter (Table 7).