. 2022 Sep 23;11(19):2976. doi: 10.3390/foods11192976

Table 3.

The performance of PLS models, with different characteristic wavenumber selection procedures for the prediction of polyphenols, free amino acids content, and the polyphenols-to-amino acids ratio.

Methods	Tea Polyphenols Content								Free Amino Acids Content								TP/AA
	Variables	Factors	Calibration Set			Prediction Set			Variables	Factors	Calibration Set			Prediction Set			Variables	Factors	Calibration Set			Prediction Set
	Variables	Factors	R_C	RMSEC	RMSECV	R_P	RMSEP	RPD	Variables	Factors	R_C	RMSEC	RMSECV	R_P	RMSEP	RPD	Variables	Factors	R_C	RMSEC	RMSECV	R_P	RMSEP	RPD
Full	2075	8	0.9303	8.05	13.4	0.8546	14.2	1.91	2075	6	0.7619	6.08	7.74	0.8490	6.79	1.62	2075	8	0.9356	0.31	0.553	0.8089	0.645	1.73
siPLS	312	9	0.9344	7.82	12.0	0.9407	9.04	3.00	312	9	0.9103	3.89	6.3	0.9110	4.96	2.21	831	9	0.9641	0.233	0.466	0.9377	0.385	2.90
biPLS	519	7	0.9125	8.79	13.5	0.9508	8.33	3.26	1454	9	0.9492	2.95	7.2	0.9199	5.31	2.07	1013	9	0.9420	0.295	0.645	0.9303	0.437	2.55

Abbreviations: RMSEC, root mean square error of calibration; RMSECV, root mean square error of cross validation; RMSEP, root mean square error of prediction; RPD, residual predictive deviation.