Table 10.

Prediction results of PSO-LSSVM based on fluorescence spectral data.

Feature extraction method	Number of feature variables	${\mathit{\text{R}}}_c^2$	RMSEC	${\mathit{\text{R}}}_p^2$	RMSEP	RPD
Boss	31	0.8987	0.5659	0.6119	0.8922	1.47
CARS	25	0.8739	0.6312	0.7099	0.7713	1.98
IVSO	23	0.8523	0.6832	0.5851	0.9225	1.50
IVISSA	41	0.9582	0.3634	0.7473	0.7199	2.29
MASS	29	0.8677	0.6467	0.7650	0.6942	2.19
CARS-Boss	21	0.8547	0.6777	0.6372	0.8626	1.65
MASS-Boss	21	0.8050	0.7850	0.7206	0.7569	1.61
IVISSA-Boss	20	0.8359	0.7201	0.7691	0.6881	1.97

The bold values represent the best performer in each table.