Skip to main content

Table 2 Confusion matrix of SVC models using full spectra

From: Evaluation of quinclorac toxicity and alleviation by salicylic acid in rice seedlings using ground-based visible/near-infrared hyperspectral imaging

Cultivar

Parametera

 

Training set

 

Validation set

 

Testing set

 
 

CK

Q

S

Accuracyb

Kappac

CK

Q

S

Totalb

Kappac

CK

Q

S

Accuracyb

Kappac

XS 134

(107,10–2)

CK

25

0

0

  

6

0

0

  

5

0

1

  

Q

0

23

3

  

0

6

0

  

0

7

0

  

S

1

1

26

  

0

2

5

  

1

0

6

  
    

93.67%

90.47%

   

89.47%

80.65%

   

90%

84.96%

ZJ 88

(107, 10–2)

CK

28

0

0

  

7

0

0

  

6

0

0

  

Q

0

28

0

  

0

6

1

  

0

6

0

  

S

0

0

26

  

0

0

6

  

0

0

7

  
    

100%

100%

   

95%

92.51%

   

100%

100%

  1. aParameter means the model parameter of SVC, which is the combination of penalty coefficient C and RBF kernel parameter g, i.e. (C, g)
  2. bTotal means the total classification accuracy
  3. cKappa is used to evaluate the inter-rater reliability of the classification results
  4. CK: treated with nutrient solution, Q: treated with 0.25 g/L quinclorac, S: pre-treated with 10 mg/L SA followed by 0.25 g/L quinclorac