Table 8 Grey Wolf optimization results on machine learning Models.

From: Comprehensive framework of machine learning and deep learning architectures with metaheuristic optimization for high-fidelity prediction of nanofluid specific heat capacity

Final Models

\(\:{\varvec{R}}^{2}\) Score

MSE

RMSE

MAE

EVS

MAPE

SMAPE

Max Error

Decision Tree

0.99746

1625.80801

40.32130

26.07216

0.99748

0.00700

0.69795

178.00000

Random Forest + LR

0.99739

1672.00258

40.89012

26.92892

0.99742

0.00709

0.70782

148.81463

kNN + LR

0.99845

990.88814

31.47837

19.85222

0.99845

0.00527

0.52737

114.21565

LightGBM

0.98978

6549.0062

80.92593

28.11171

0.98978

0.00843

0.81587

1068.38786

Gradient Boosting + LR

0.99902

626.21541

25.02429

15.06049

0.99902

0.00400

0.39935

159.74076

AdaBoost + LR

0.95092

31455.399

177.35670

143.39257

0.95112

0.03798

3.78873

535.84895

CatBoost

0.99920

509.40400

22.56998

13.59114

0.99920

0.00358

0.35762

101.05405

XGBoost

0.99893

682.15078

26.11801

15.35519

0.99894

0.00404

0.40454

124.02148

MLP + LR

0.99927

466.06792

21.58860

13.14148

0.99927

0.00355

0.35490

104.24291

Back to article page