Research Article

Ensemble Deep Learning and Internet of Things-Based Automated COVID-19 Diagnosis Framework

Table 2

Testing analysis (%) of the proposed IoT-enabled deep ensemble model for automated diagnosis of COVID-19 suspected cases on the four-class chest CT dataset when training to testing ratio is 65 : 35.

ModelAccuracyF-measureAUCRecallPrecision

JLM [16]97.4697.8497.6597.9898.08
WSDL [17]96.9697.1797.0697.4697.88
IPCNN [18]97.9597.5597.7598.0398.03
DeCNN [19]97.3697.3697.1897.2798.11
DLCRD [20]98.1398.1298.1498.1997.63
PARL [22]97.1197.5297.3197.7897.93
AGGDF [24]97.7397.4497.5897.7597.47
GCNN [25]97.4697.7597.6597.9297.99
GoogLeNet [53]97.7797.3397.5597.6997.94
ResNet152V2 [44]96.9697.8997.4297.7497.67
DenseNet201 [34]97.4497.5997.5197.8798.11
IRNV2 [3]98.0697.9898.0298.2798.36
Proposed98.9798.7598.5798.5898.56