Table 2.

Confusion matrix of SVC models using full spectra

Cultivar	Parameter^a		Training set					Validation set					Testing set
Cultivar	Parameter^a		CK	Q	S	Accuracy^b	Kappa^c	CK	Q	S	Total^b	Kappa^c	CK	Q	S	Accuracy^b	Kappa^c
XS 134	(10⁷,10^–2)	CK	25	0	0			6	0	0			5	0	1
		Q	0	23	3			0	6	0			0	7	0
		S	1	1	26			0	2	5			1	0	6
						93.67%	90.47%				89.47%	80.65%				90%	84.96%
ZJ 88	(10⁷, 10^–2)	CK	28	0	0			7	0	0			6	0	0
		Q	0	28	0			0	6	1			0	6	0
		S	0	0	26			0	0	6			0	0	7
						100%	100%				95%	92.51%				100%	100%

^aParameter means the model parameter of SVC, which is the combination of penalty coefficient C and RBF kernel parameter g, i.e. (C, g)

^bTotal means the total classification accuracy

^cKappa is used to evaluate the inter-rater reliability of the classification results

CK: treated with nutrient solution, Q: treated with 0.25 g/L quinclorac, S: pre-treated with 10 mg/L SA followed by 0.25 g/L quinclorac