Table 4 Statistical Validation of the Proposed Model in Aquaponic Fish Ponds Among Baseline Research Works.

From: IoT-based prediction model for aquaponic fish pond water quality using multiscale feature fusion with convolutional autoencoder and GRU networks

Metrics

EOO29

WSA30

GSO31

MOA25

RF-MOA

Accuracy

88.87094

89.97054

90.09511

92.24428

94.14154

Recall

88.86881

89.954

90.09349

92.25087

94.14575

Specificity

88.87447

89.99795

90.09779

92.23336

94.13456

Precision

92.97754

93.71348

93.78137

95.16624

96.37744

FPR

11.12553

10.00205

9.902208

7.766643

5.865445

FNR

11.13119

10.046

9.906508

7.749129

5.854249

NPV

82.80895

84.38669

84.58449

87.7763

90.65509

FDR

7.022455

6.286516

6.218629

4.833762

3.622556

F1-Score

90.87676

91.79526

91.90045

93.68588

95.24853

MCC

0.767587

0.790206

0.792733

0.837098

0.876542