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

Table 3

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 DPLS 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	The number of principal components	Identification accuracy of training set (%)	Identification accuracy of testing set (%)
4000–5000	3 : 1	9	99.91	99.73
4000–5000	4 : 1	9	100	99.67
4000–5000	5 : 1	10	99.92	100
6000–7000	3 : 1	10	99.46	98.66
6000–7000	4 : 1	9	99.33	99.33
6000–7000	5 : 1	9	99.44	98.80
8000–9000	3 : 1	8	98.21	98.13
8000–9000	4 : 1	9	98.40	98.33
8000–9000	5 : 1	9	98.39	97.99
8000–10000	3 : 1	10	99.91	99.47
8000–10000	4 : 1	8	99.92	99.33
8000–10000	5 : 1	9	99.84	99.60
9000–10000	3 : 1	9	98.03	97.33
9000–10000	4 : 1	7	97.98	97.66
9000–10000	5 : 1	9	97.99	97.59