Table 2.

Comparison of the classification accuracy of the K-nearest neighbor (KNN), soft independent modeling of class analogy (SIMCA), partial least squares-discriminant analysis (PLS-DA), and support vector machine-discriminant analysis (SVM-DA) models.

Classification Models	Optimal Parameters	Classification Accuracy
		Calibration Set (%)	Prediction Set (%)
KNN	K = 3	92	94
SIMCA	PCs = 6, 4, 4, 5, 5	93	96
PLS-DA	PCs = 8	95	98
SVM-DA	C = 100, γ = 0.00316, PCs = 6	100	100