Table 2.
Optimized parameters of GA selected as variable selection procedure to enhance the models' predictability
| Parameters | Optimum values | |
|---|---|---|
| MLK | LCZ | |
| Population size | 40 | 36 |
| Maximum generations | 65 | 52 |
| Mutation rate | 0.005 | 0.005 |
| % wavelength used at the initiation | 15 | 15 |
| The number of variables in a window (window width) | 2 | 2 |
| Percent of the population (% of convergence) | 80 | 80 |
| Cross-type | Double | Double |
| Maximum number of latent variables | 3 | 3 |
| Cross-validation | Random | Random |
| Number of subsets to divide data into for cross-validation | 5 | 5 |
| Number of iterations for cross-validation at each generation | 2 | 2 |