| Ref. | Model developed | Predicted parameter | Results |
| [26] | Ridge linear regression, ANN, SVM, and random forest | BGL, BP | Random forest technique outperformed ridge linear regression, ANN, and SVM. R2 = 0.91% (SBP), R2 = 0.89% (DBP), and R2 = 0.90% (BGL) | [28] | ANN (raw input), ANN (feature based), MAA, and ANFIS (feature based) | SBP, DBP | ANN (feature based) achieved the best performance compared to other models. For SBP predictions: MAE = 6.28, SDE = 8.58. For DBP predictions: MAE = 5.73, SDE = 7.33 | [29] | ANN | SBP, DBP | The experimental results confirmed the correctness of the ANN when compared with the linear regression model. Mean ± σ: SBP: 3.80 ± 3.46, DBP: 2.21 ± 2.09. Relative error: SBP: 3.48 ± 3.19. DBP: 3.90 ± 3.51 | [32] | SVM with RBF and polynomial kernel | SBP, DBP | SVM (RBF kernel) outperformed SVM (polynomial kernel). Coefficient of correlation (R) = 0.97 (SBP), 0.96 (DBP). RMSE = 6.94 (SBP), and 5.78 (DBP). Scatter index (SI) = 22.34 (SBP), 22.79 (DBP) | [36] | PCA-ANN, PCA-ANFIS, and PCA-LS-SVM | SBP, DBP | PCA-LS-SVM outperformed PCA-ANN and PCA-ANFIS.
For normotensive subjects: SBP: R2 = 95.42%, RMSE = 0.21, and MAPE = 5.88%. DBP: R2 = 94.22%, RMSE = 0.24, and MAPE = 4.05%. For hypertensive subjects: SBP: R2 = 98.76%, RMSE = 0.11, and MAPE = 0.88%. DBP: R2 = 98.78%, RMSE = 0.11, and MAPE = 0.84% | [37] | PCA-SWR, PCA-ANN, PCA-ANFIS, and PCA-LS-SVM | DBP | PCA-LS-SVM outperformed PCA-FSWR, PCA-ANN, and PCA-ANFIS. For normotensive subjects: R2 = 98.49%, RMSE = 0.1243, and MAPE = 3.01%. For hypertensive subjects: R2 = 95.95%, RMSE = 0.2013, and MAPE = 2.9% | [58] | ANN, ANFIS, and SVM | River flow in the semiarid mountain region | In comparing the results of the ANN, ANFIS, and SVM models, it was seen that the values of R, RMSE, mean absolute relative error (MARE), and Nash-Sutcliffe (NS) of the SVM model were higher than those of ANN and ANFIS for all combinations of input data | [59] | ANN, ANFIS | To predict depths-to-water table one month in advance, at three wells located at different distances from the river | Both models can be used with a high level of precision to the model water tables without a significant effect of the distance of the well from the river, as model precision expressed via RMSE was roughly the same in all three cases (0.14154–0.15248). R varied from 0.91973 to 0.9623 and coefficient of efficiency (COE) from 0.84588 to 0.92586 | [60] | ANN, ANFIS, and SVM | Longitudinal dispersion coefficient (LDC) | The SVM model was found to be superior (R2 = 90%) in predicting LDC due to low uncertainty as compared with those in the ANN (R2 = 82%) and ANFIS (R2 = 83%) models, while the ANFIS model performed better than the ANN model | [61] | Multilayer perceptron (MLP), ANN, fuzzy genetic (FG), LS-SVM, multivariate adaptive regression spline (MARS), ANFIS, multiple linear regression (MLR), and Stephens and Stewart models (SS) | Evaporation in different climates | The accuracies of the applied models were rank as: MLP, GRNN, LSSVM, FG, ANFIS-GP, MARS, and MLR | Present study | PCA-FSWR, PCA-ANN, PCA-ANFIS, and PCA-LS-SVM | BP reactivity to crossed legs | PCA-LS-SVM outperformed PCA-FSWR, PCA-ANN, and PCA-ANFIS. For normotensive subjects: SBP: R2 = 93.16%, RMSE = 0.27, and MAPE = 5.71%. For hypertensive subjects: SBP: R2 = 96.46%, RMSE = 0.19, and MAPE = 1.76%. DBP: R2 = 95.44%, RMSE = 0.21, and MAPE = 2.78% |
|
|