Table 8 Results of the McNemar’s Test performed on the individual models of the ensemble, on both datasets: Null hypothesis is rejected for all cases.

From: Fuzzy rank-based fusion of CNN models using Gompertz function for screening COVID-19 CT-scans

McNemar’s Test

p value

Compared with

SARS-COV-2

Harvard Dataverse

VGG-11

4.49E-02

9.50E-03

Wide ResNet-50-2

1.05E-04

1.93E-15

Inception v3

2.88E-02

8.40E-03

Back to article page