Research Article

Moisture Content Quantization of Masson Pine Seedling Leaf Based on Stacked Autoencoder with Near-Infrared Spectroscopy

Table 1

Calibration and prediction results of the moisture content in masson pine seedling leaves using different regression models.

ModelCalibration datasetPrediction dataset
RMSECRMSEP

MLR0.92670.56190.39152.879
PLSR0.96580.40790.89810.6774
SVR0.98920.22850.90160.7052
ANN0.99740.11230.93220.5559
SAE-ANN0.99440.16440.94210.5228
SAE-SVR0.99460.16360.96210.4249