High accuracy rapid prediction and feasibility of on-site nondestructive estimation of Para rubber quality by spectroscopic methods

Journal of Wood Science

Official Journal of the Japan Wood Research Society

Table 3 Cross-validation results of PLS-R analysis for the prediction of TSC

Parameter	A*	B*	Validation method	Pre-treatment of spectra	Wavenumber (nm)	Factor	r ²	RMSECV	RPD
DRC	57	0	Cross-validation	1st derivative + straight line subtraction	773.4–937.1	1	0.9741	1.09	6.28
TSC	57	0	Cross-validation	2nd derivative	550.4–1001.4	2	0.9602	1.34	5.07
DRC	40	17	Test set validation	1st derivative + straight line subtraction	773.4–937.1	1	0.9713	1.29	5.92
TSC	40	17	Test set validation	2nd derivative	550.4–1001.4	2	0.9468	1.63	4.78

r ² coefficient of determination for cross-validation, RMSECV root mean square error of cross-validation, RPD ratios of performance to deviation, A* the number of calibration samples, B* the number of validation samples