Table 3.

Classification results of machine-learning models with data fusion combining optimal wavelengths and texture features. ^a

Classifier	Parameter	Calibration set accuracy (%)					Prediction set accuracy (%)
		Healthy	2 DPI	4 DPI	6 DPI	Overall	Healthy	2 DPI	4 DPI	6 DPI	Overall
PLS-DA	2	93.33	100.00	45.00	65.00	81.67	90.00	90.00	80.00	50.00	81.67
RF	62	100.00	100.00	100.00	100.00	100.00	93.33	90.00	90.00	100.00	93.33
SVM	(1.00, 1.00)	100.00	80.00	80.00	100.00	93.33	93.33	80.00	70.00	100.00	88.33
LS-SVM	(33.52, 9.88)	100.00	100.00	100.00	100.00	100.00	100.00	90.00	90.00	100.00	96.67
ELM	60	100.00	100.00	100.00	100.00	100.00	96.67	90.00	70.00	90.00	90.00
BPNN	6	98.33	100.00	95.00	100.00	98.33	96.67	90.00	90.00	100.00	95.00

^aParameters and abbreviations as in Table 1.