Table 9 Statistic metrics obtained by W-LSSVM 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

0.887

0.956

0.952

0.984

RMSE

166.303

104.268

108.997

64.727

MAE

133.497

77.533

82.778

51.466

RAE

0.481

0.279

0.298

0.185

MAPE

7.046

4.033

4.398

2.638

E

0.779

0.913

0.905

0.967

IA

0.941

0.978

0.975

0.992

PI

1.000

0.729

0.754

0.599

Wavelet-Bior Tesr

R

0.863

0.959

0.953

0.985

RMSE

181.865

100.140

107.135

62.553

MAE

137.126

75.682

81.766

50.104

RAE

0.494

0.273

0.295

0.181

MAPE

7.088

3.914

4.332

2.564

E

0.736

0.920

0.908

0.969

IA

0.927

0.979

0.976

0.992

PI

1.000

0.693

0.723

0.572

Wavelet-Demy Train

R

0.938

0.980

0.980

0.993

RMSE

231.397

132.822

131.547

78.506

MAE

174.007

100.098

99.820

61.028

RAE

0.321

0.185

0.184

0.113

MAPE

9.489

5.303

5.246

3.303

E

0.879

0.960

0.961

0.986

IA

0.966

0.990

0.990

0.996

PI

1.000

0.733

0.731

0.599

Wavelet-Bior Train

R

0.931

0.977

0.979

0.993

RMSE

243.767

141.328

135.022

79.378

MAE

175.774

106.906

102.476

61.849

RAE

0.324

0.197

0.189

0.114

MAPE

9.398

5.666

5.385

3.361

E

0.866

0.955

0.959

0.986

IA

0.962

0.988

0.989

0.996

PI

1.000

0.747

0.731

0.596

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