Research Article

A Novel Genetic Algorithm-Based Optimization Framework for the Improvement of Near-Infrared Quantitative Calibration Models

Table 3

The optimal model validating results corresponding to the 5 selected wavebands.

Waveband (nm)The optimal parameters for genetic evolutionRMSEV (wt.%)RV
Crossover (%)Mutation (%)Iteration times

1134–1180501.55004.7550.906
1252–1296400.84374.5460.897
1446–1520500.84694.3530.918
1980–2050400.84344.2150.926
2070–2104500.84844.6490.912

The iteration times represent when the optimal RMSEV was kept as a constant value for a cycle of 20 times iteration, or less than 20 in case the iteration had reached 500 times.