Table 7 Statistic metrics obtained by W-ANFIS-A-DEPSO model to forecast the EC parameter for all combinations.

From: An improved adaptive neuro fuzzy inference system model using conjoined metaheuristic algorithms for electrical conductivity prediction

Model

Criteria

Combination

Combo 1

Combo 2

Combo 3

Combo 4

Wavelet-Demy Test

R

0.866

0.960

0.962

0.990

RMSE

221.322

99.818

96.881

51.193

MAE

173.394

78.444

76.877

41.870

RAE

0.625

0.283

0.277

0.151

MAPE

9.053

4.016

4.053

2.143

E

0.609

0.920

0.925

0.979

IA

0.911

0.979

0.981

0.995

PI

1.000

0.613

0.608

0.480

Wavelet-Bior Test

R

0.857

0.959

0.955

0.988

RMSE

192.071

101.203

106.158

54.064

MAE

157.716

81.614

84.647

43.549

RAE

0.568

0.294

0.305

0.157

MAPE

7.919

4.222

4.395

2.222

E

0.705

0.918

0.910

0.977

IA

0.914

0.978

0.977

0.994

PI

1.000

0.67032

0.684

0.518

Wavelet-Demy Train

R

0.947

0.979

0.978

0.992

RMSE

213.432

134.953

140.161

83.955

MAE

164.758

102.836

104.114

65.822

RAE

0.304

0.190

0.192

0.121

MAPE

9.018

5.611

5.482

3.607

E

0.897

0.959

0.956

0.984

IA

0.972

0.989

0.989

0.996

PI

1.000

0.770

0.774

0.633

Wavelet-Bior Train

R

0.947

0.979

0.978

0.994

RMSE

213.683

134.877

138.033

75.835

MAE

155.866

104.022

107.249

59.092

RAE

0.288

0.192

0.198

0.109

MAPE

8.512

5.592

5.719

3.245

E

0.897

0.959

0.957

0.987

IA

0.972

0.989

0.989

0.997

PI

1.000

0.787

0.797

0.619

  1. Significant values are in bold.
Back to article page