IEEE Geoscience and Remote Sensing Magazine - March 2017 - 25

TABLE 6. SCENARIO 2: THE CLASSIFICATION ACCURACIES (%)
OBTAINED BY DIFFERENT CLASSIFICATION APPROACHES
ON THE HOUSTON HYPERSPECTRAL DATA.

5
4.5
Standard Deviation

4

CLASS SVM

RF

BP

ELM

KELM

1D CNN MLR

3.5

1

82.24

82.62

81.86

97.25

95.37

82.91

82.62

3

2

82.99

83.46

85.63

98.39

98.75

83.65

83.55

2.5

3

99.80

97.62

99.90

100.00 100.00

99.8

99.80

2

4

92.33

92.14

90.11

96.09

99.49

90.06

92.23

1.5

5

98.30

96.78

98.08

96.80

97.84

97.82

98.39

1

6

99.30

99.30

86.43

99.03

100.00

99.3

95.10

0.5

7

79.10

74.72

79.64

53.26

73.63

85.63

78.73

0

8

50.62

32.95

51.80

66.04

76.18

41.41

53.46

9

79.13

68.65

77.26

76.81

73.88

79.41

79.79

10

57.92

43.15

57.46

71.39

76.08

53.38

58.10

11

81.31

70.49

85.76

82.25

67.28

70.49

82.44

12

76.08

55.04

81.76

72.21

59.74

72.72

76.36

1.2

13

69.82

60.00

74.42

42.65

41.74

63.86

68.42

1

14

100.00 99.19

99.31

89.81

90.41

99.6

98.78

15

96.83

97.46

98.08

94.15

94.34

98.52

97.88

OA

80.18

72.99

80.98

79.55

80.64

78.21

80.60

AA

83.05

76.9

83.17

82.4

82.98

81.23

83.04

Kappa

0.7866

0.7097 0.7934 0.7783 0.7901

0.7846

0.7908

1

5
10
15
20
Training Samples (%)
(a)

25

Standard Deviation

1.4

0.8
0.6
0.4
0.2
0

◗ SVM versus RF: Although both classifiers have the same
1

RF
ELM

5
10
15
Training Samples (%)
(b)
SVM
KELM

BP
1-D CNN

20

MLR

FIGURE 12. Scenario 1: stability. The standard deviation value

over ten runs using different percentages of training samples from
(a) Indian Pines and (b) Pavia University obtained by different
classification approaches.
Figure 11 shows the OA of different approaches (i.e.,
the average value over ten runs) on different percentages
of training samples on Indian Pines and Pavia University.
To evaluate the stability of different classifiers on the change
of training samples, the standard deviation value over ten
runs for each percentage is estimated and shown in Figure 12.
For the Houston hyperspectral data, since the training
and test sets were already separated, we performed the classifiers on the standard set of training and test samples. The
classification accuracies (i.e., OA, AA, Kappa, and class specific accuracies) are reported in Table 6. The classification
maps of this data set are shown in Figure 13.
RESULTS AND DISCUSSION
The main observations obtained from our experimental results are listed systematically as follows:
march 2017

ieee Geoscience and remote sensing magazine

number of hyperparameters to tune (i.e., the RBF SVM has
c and C, and RFs have the number of trees and the depth
of the tree), RFs' parameters are easier to set. In practice,
the more trees we have, the higher the classification accuracy of RFs that can be obtained. RFs are trained faster
than a kernel SVM. A suggested number of trees can be
varied from 100 to 500 for the classification of hyperspectral data. However, with respect to our experiments, the
SVM established higher classification accuracies than RFs.
◗ SVM versus BP: The SVM classifier presents a series of advantages over the BP classifier. The SVM exhibits less computational complexity, even when the kernel trick is used,
and usually provides better results when a small number
of training samples is available. However, if the BP configuration is properly tuned, both classifiers can provide
comparable classification accuracies. Last but not least, the
BP is much more complex from a computational point of
view. Actually, in this work we use the scaled conjugate gradient BP algorithm, which presents a practical complexity
of O ((n ((dLK) + L + K)) 2) (the square of the number of
weights of the network), where n is the number of training
patterns, d the number of spectral bands, L the number of
hidden nodes, and K the number of classes [64].
◗ SVM versus ELM: From an optimization point of view,
the ELM presents the same optimization cost function
as the least squares SVM [148] but much less computational complexity. In general terms, ELM training is tens
or hundreds of times faster than a traditional SVM.
25



Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - March 2017

IEEE Geoscience and Remote Sensing Magazine - March 2017 - Cover1
IEEE Geoscience and Remote Sensing Magazine - March 2017 - Cover2
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 1
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 2
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 3
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 4
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 5
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 6
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 7
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 8
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 9
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 10
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 11
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 12
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 13
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 14
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 15
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 16
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 17
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 18
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 19
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 20
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 21
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 22
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 23
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 24
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 25
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 26
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 27
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 28
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 29
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 30
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 31
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 32
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 33
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 34
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 35
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 36
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 37
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 38
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 39
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 40
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 41
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 42
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 43
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 44
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 45
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 46
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 47
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 48
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 49
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 50
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 51
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 52
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 53
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 54
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 55
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 56
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 57
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 58
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 59
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 60
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 61
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 62
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 63
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 64
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 65
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 66
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 67
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 68
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 69
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 70
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 71
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 72
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 73
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 74
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 75
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 76
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 77
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 78
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 79
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 80
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 81
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 82
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 83
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 84
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 85
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 86
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 87
IEEE Geoscience and Remote Sensing Magazine - March 2017 - 88
IEEE Geoscience and Remote Sensing Magazine - March 2017 - Cover3
IEEE Geoscience and Remote Sensing Magazine - March 2017 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2023
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2023
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2023
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2023
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2022
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2022
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2022
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2022
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2021
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2021
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2021
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2021
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2020
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2020
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2020
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2020
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2019
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2019
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2019
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2019
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2018
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2018
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2018
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2018
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2017
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2017
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2017
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2017
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2016
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2016
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2016
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2016
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2015
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2015
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2015
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2015
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2014
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2014
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2014
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2014
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2013
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2013
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2013
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2013
https://www.nxtbookmedia.com