Determination of manganese content in cottonseed meal using near-infrared spectrometry and multivariate calibration

Table 3 The performance of four kinds of regression models

Models	Varialbes	Calibration			Validation			RPD	RMSECV
Models	Varialbes	Num	R ² _c	RMSEC	Num	R ² _v	RMSEP	RPD	RMSECV
PLS	700	216	0.894 7	2.598 3	72	0.926 9	2.438 7	3.574 6	3.171 9
LSSVM	700	216	0.984 9	1.001 7	72	0.944 1	2.108 4	4.134 7	2.491 0
MCUVE-LSSVM	233	216	0.976 3	1.242 0	72	0.948 6	2.010 8	4.335 4	2.309 1
MCUVE-SPA-LSSVM	49	216	0.972 9	1.330 8	72	0.949 3	1.994 6	4.370 5	2.101 3

Num Number of samples used to perform the calibration and validation, R²_c Coefficient of determination in calibration, R²_v Coefficient of determination in calibration, RMSEC The root mean square error of calibration, RMSEP The root mean square error of prediction, RPD The residual predictive deviation, RMSECV The root mean square error of cross-valid

ISSN: 2523-3254