Skip to main content

Table 2 Modeling results based on image features

From: Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method

Storage time (h)

Evaluation index

Classification model

RF

SVM (c = 6.0629, g = 0.0.0544)

XGBoost (eta = 1, max_depth = 1)

2

Number of misjudgments

2

2

2

Accuracy (%)

90.00

90.00

90.00

8

Number of misjudgments

0

0

0

Accuracy (%)

100.00

100.00

100.00

24

Number of misjudgments

5

8

3

Accuracy (%)

75.00

60.00

65.00

48

Number of misjudgments

4

5

5

Accuracy (%)

80.00

75.00

55.00

Total number of misjudgments

11

15

10

 

Overall accuracy (%)

86.25

81.25

87.50

 
  1. c” is the penalty coefficient, “g” is the radius of the kernel function, optimize “c” and “g” by Gridsearch
  2. “eta” is the learning rate, “max_depth” is the maximum depth of each tree