Identification of Pinus species related to historic architecture in Korea using NIR chemometric approaches

Journal of Wood Science

Official Journal of the Japan Wood Research Society

Table 5 Statistical summary of discriminant models for species classification based on wood block and tablet samples

Groups	Spectra pretreatment	Factors	Calibration set		Prediction set		Correct prediction (%)
Groups	Spectra pretreatment	Factors	R ²_c	RMSEC	R ²_p	RMSEP	Correct prediction (%)
A	Original	7	0.77	0.48	0.78	0.46	99.0
A	Second derivative	5	0.80	0.44	0.80	0.44	100
B	Original	7	0.78	0.46	0.81	0.44	99.5
B	Second derivative	6	0.85	0.39	0.86	0.38	100
C	Original	7	0.82	0.42	0.79	0.45	97.4
C	Second derivative	5	0.83	0.42	0.81	0.44	100
D	Original	6	0.80	0.44	0.79	0.46	98.5
D	Second derivative	5	0.82	0.42	0.85	0.38	99.0
E	Original	8	0.77	0.48	0.80	0.43	99.0
E	Second derivative	4	0.80	0.45	0.80	0.43	99.5

R ²_c coefficient of determination for calibration, R ²_p coefficient of determination for prediction, RMSEC root mean square error of calibration, RMSEP root mean square error of prediction