Research Article
Developing a Robust Model Based on the Gaussian Process Regression Approach to Predict Biodiesel Properties
Table 2
The comparison between four kernel functions for IV property from the point of view of statistical quantities.
| Model | Phase | R2 | MRE (%) | MSE | RMSE | STD |
| GPR (Exponential) | Train | 1.000 | 0.23024 | 0.15939 | 0.39923 | 0.29438 | Test | 0.984 | 0.96971 | 3.15731 | 1.77688 | 1.35545 | Total | 0.998 | 0.27729 | 0.79448 | 1.77688 | 0.83169 |
| GPR (Matern) | Train | 0.999 | 0.44408 | 0.44046 | 0.66367 | 0.39484 | Test | 0.993 | 0.83689 | 3.02336 | 1.73878 | 1.45060 | Total | 0.997 | 0.46640 | 0.98545 | 1.73878 | 0.81850 |
| GPR (Squared Exponential) | Train | 0.997 | 0.55285 | 1.18464 | 1.08841 | 0.85742 | Test | 0.998 | 0.69364 | 0.93277 | 0.96580 | 0.56754 | Total | 0.997 | 0.62869 | 1.22526 | 0.96580 | 0.81806 |
| GPR (Rational Quadratic) | Train | 0.996 | 0.60686 | 1.30529 | 1.14249 | 0.87268 | Test | 0.996 | 0.74534 | 1.93710 | 1.39180 | 1.14923 | Total | 0.996 | 0.64906 | 1.56170 | 1.39180 | 0.99212 |
|
|