Table 9 Class-wise Score of PC dataset using D-Path-AE.

From: Enhancing feature learning of hyperspectral imaging using shallow autoencoder by adding parallel paths encoding

Number

Name

SVM

KNN

DT

1

water

100.00

100.00

100.00

2

trees

94.23

94.81

94.35

3

asphalt

87.21

88.01

87.73

4

self blocking bricks

67.11

85.72

79.11

5

bituem

92.11

97.01

96.22

6

tiles

95.21

96.29

95.22

7

shadows

91.11

93.17

92.19

8

meadows

100.00

100.00

99.01

9

bare soil

100.00

100.00

100.00

Kappa

 

96.46

97.62

97.04

OA

 

97.48

98.31

97.90

AA

 

91.95

95.32

93.52