Identification of Tilletia foetida, Ustilago tritici, and Urocystis tritici Based on Near-Infrared Spectroscopy

Table 5

The optimal results except those with both the identification accuracy of the training set and the identification accuracy of the testing set equal to 100% when the SVM models for Data treatment method 1 were built with different modeling ratios in each modeling spectral region.

Spectral region (cm^−1)	Modeling ratio of training set to testing set	Optimal parameters		Identification accuracy of training set (%)	Identification accuracy of testing set (%)
		C
4000–12000	3 : 1	0.2500	6.9644	100	99.73
4000–6000	4 : 1	1.3195	64.0000	100	99.67
4000–10000	3 : 1	0.4353	6.9644	100	99.73
5000–6000	3 : 1	4.0000	36.7583	99.91	100
5000–6000	4 : 1	1.3195	337.7940	100	99.67
5000–10000	3 : 1	0.4353	12.1257	100	99.73
5000–10000	5 : 1	0.7579	111.4305	100	99.60
6000–8000	3 : 1	6.9644	64.0000	100	99.73
6000–8000	5 : 1	2.2974	588.1336	100	99.20
6000–9000	3 : 1	1.3195	21.1121	100	99.47
6000–9000	5 : 1	1.3195	337.7940	100	99.20
6000–10000	3 : 1	1.3195	12.1257	99.91	99.73
9000–10000	3 : 1	64.0000	111.4305	100	99.73
9000–10000	4 : 1	588.1336	4.0000	99.92	100
9000–10000	5 : 1	12.1257	337.7940	100	99.60