Table 3 Prediction accuracy of the PLSR and PCR models for EC based on moving-average data smoothing technique (MA) spectral smoothing.

Method		Calibration		Cross-validation		Independent Prediction		Number of predictors or factors
Method		R²	RMSE	R²	RMSE	R²	RMSE	Number of predictors or factors
PLSR	1 + A	0.8745	0.2320	0.7492	0.4453	0.6088	0.4650	10
PCR	1 + A	0.7620	0.3195	0.5646	0.4701	0.5601	0.4931	19
PLSR	1 + A + B	0.8973	0.2098	0.5861	0.4354	0.5863	0.4782	10
PCR	1 + A + B	0.7081	0.3538	0.4133	0.5198	0.6087	0.4650	19
PLSR	1 + C	0.5150	0.4561	0.1769	0.6109	−0.0240	0.7522	3
PCR	1 + C	0.2856	0.5535	0.1478	0.6192	0.0299	0.7648	6
PLSR	1 + D	0.9013	0.2057	0.6119	0.4223	0.5792	0.4822	9
PCR	1 + D	0.7503	0.3273	0.5121	0.4726	0.5818	0.4807	20
PLSR	1 + E	0.9060	0.2008	0.5755	0.4435	0.5528	0.4971	9
PCR	1 + E	0.7257	0.3430	0.5140	0.4741	0.4376	0.5575	17
PLSR	1 + F	0.8900	0.2172	0.5782	0.4413	0.5095	0.5207	8
PCR	1 + F	0.7357	0.3367	0.5326	0.4649	0.4547	0.5490	16

“Independent Prediction”stands for the accuracy of models by independent validation set (36 selected samples). “Number of predictors or factors” denotes the number of spectral principal components extracted. The number 1 represents the MA methods. 1 + A represents MA + log(1/X); 1 + A + B represents MA + log(1/X) + baseline correction; 1 + C represents MA + first derivative; 1 + D represents MA + area normalization; 1 + E represents MA + SNV; and 1 + F represents MA + MSC.

Quick links

Search