Skip to main content

Table 10 Classification performance for baby spinach by applying tenfold validation using proposed algorithm with selected features

From: Machine learning driven non-invasive approach of water content estimation in living plant leaves using terahertz waves

Feature selection methods

Classifiers

Serial num. of features

Total no of features

Accuracy (%)

SFS

SVM

24

1–12, 14–25

97.9

KNN

23

1–14, 17–25

96.4

D-Tree

5

3, 5, 17, 20, 21

96.1

SBS

SVM

23

1–11, 13, 15–25

96.8

KNN

24

1–13, 15–25

94.5

D-Tree

5

7, 8, 9, 11, 15

93.2

Relief-F

SVM

17

2, 4–7, 10, 11, 15–21, 23–25

98.6

KNN

99.1

D-Tree

95.5