An Assessment of Artificial Neural Networks, Support Vector Machines and Decision Trees for Land Cover Classification Using Sentinel-2A Data

Abstract

Remotely sensed images serve as a valuable source of present and archival information since they provide the geographical distribution of natural and cultural features both spatially and temporally, as well as objects on the earth's surface. Three machine learning classifiers, namely artificial neural networks (ANN), support vector machines (SVM), and decision tree (DT) algorithms, were applied in order to classify the Sentinel-2A data over the city of Soran. The differences in classification accuracies were evaluated by the confusion matrix. The supervised ANNs obtained the most accurate classification accuracy as compared with support SVM and DTs algorithms. Furthermore, the overall accuracy assessment of ANN was 90%, with SVM at 65%, while DTs were 60%. It can be concluded that ANNs can provide the best classification machine learning technique for land cover classification.

Full text

Applied Ecology and Environmental Sciences, 2020, Vol. 8, No. 6, 459-464
Available online at http://pubs.sciepub.com/aees/8/6/18
Published by Science and Education Publishing
DOI:10.12691/aees-8-6-18
An Assessment of Artificial Neural Networks, Support
Vector Machines and Decision Trees for Land Cover
Classification Using Sentinel-2A Data
Rahel Hamad1,2,*
1GIS and Remote Sensing Department, Scientific Research Centre (SRC), Delzyan Campus, Soran University, Soran 44008, Erbil, Iraq
2Department of Petroleum Geosciences, Faculty of Science, Delzyan Campus, Soran University, Soran 44008, Erbil, Iraq
*Corresponding author: rahel.hamad@soran.edu.iq
Received August 17, 2020; Revised September 19, 2020; Accepted September 29, 2020
Abstract Remotely sensed images serve as a valuable source of present and archival information since they
provide the geographical distribution of natural and cultural features both spatially and temporally, as well as objects
on the earth’s surface. Three machine learning classifiers, namely artificial neural networks (ANN), support vector
machines (SVM), and decision tree (DT) algorithms, were applied in order to classify the Sentinel-2A data over the
city of Soran. The differences in classification accuracies were evaluated by the confusion matrix. The supervised
ANNs obtained the most accurate classification accuracy as compared with support SVM and DTs algorithms.
Furthermore, the overall accuracy assessment of ANN was 90%, with SVM at 65%, while DTs were 60%. It can be
concluded that ANNs can provide the best classification machine learning technique for land cover classification.
Keywords: Soran, remote sensing, GIS, overfitting, hyperplane
Cite This Article: Rahel Hamad, “An Assessment of Artificial Neural Networks, Support Vector Machines
and Decision Trees for Land Cover Classification Using Sentinel-2A Data.” Applied Ecology and Environmental
Sciences, vol. 8, no. 6 (2020): 459-464. doi: 10.12691/aees-8-6-18.
1. Introduction
For last five decades Landsat imagery has presented a
unique resource for various researchers and scientists
through their studies in many and disparate areas such as
forestry, education, agriculture, etc. [1]. In addition, the
recent Sentinel-2A multispectral satellite sensor was
successfully launched by the European Space Agency
(ESA) on 23 June 2015. It provides images for various
purposes, and whose characteristics can meet the vast
majority of analysis requirements [2].
The successful remotely sensed classification is an
essential source for many application processes [3],
because many environmental, social and economic
applications are based on the results of classification [4].
Moreover, to obtain a successful classification, a suitable
classification system is required [5]. Therefore, the
submission of research objectives, questions, and
problems are necessary from the end user before
employing the classification [3]. On the other hand, there
are many factors must be taken into account when
choosing a classification method for use, such as the
spatial resolution of the remotely sensed data, different
sources of data, a classification system, and availability of
appropriate classification software [4]. In general, the
purpose of image classification is to predict any entered
image categories using its features [6].
Different classification techniques have been studied by
many researchers regarding the accuracy of their maps.
Image processing and classification approaches, may
affect the success of the classification, as the classification
of remote-sensing is a complex process and requires
consideration of a number of factors [4]. Various types of
algorithms are used to provide a suitable accuracy of
classification [3]. Classifying remotely sensed data is one
of the basic steps to extracting information [6], via any of
various classification techniques [4]. Many advanced
classification approaches, in the last two decades, have
been applied for image classification such as artificial
neural networks (ANNs) [7,8], support vector machines
(SVMs) [9,10], decision trees (DTs) [11,12], spectral
angle classifiers [13,14], and rule-base evidential
reasoning for building expert and decision-making
systems [15,16]. These aforementioned methods are non-
parametric classifiers, which do not employ statistical
parameters to calculate class separation.
The ideal map is one that has been well validated and
achieved, and which should consider a range of factors
such as methods for collecting reference points,
classification scheme, sample method collection, sample
size and sample unit, and the accuracy assessment
calculation [17,18]. Furthermore, other important accuracy
assessment elements can be derived from the confusion
matrix such as producer's accuracy, user’s accuracy, and
overall kappa statistics. However, obtaining the accuracy
assessment is more difficult than classification [19].

460 Applied Ecology and Environmental Sciences
The performance of different machine learning classifiers,
as evaluated through many comparative studies have been
investigated [1,20,21,22,23,24]. For instance, Szantoi,
Escobedo [20] implemented ANN and DTs on heterogeneous
wetland communities, and found that ANN significantly
outperformed the DT classifier. Chen [21] found that
Neural Networks were the most efficient algorithm and
outperformed SVM and DTs. Huang, Davis [1] assessed
SVM for land cover classification, and compared ANN
and DTs. They found that SVM can produce a more
accurate classification. Khatami, Mountrakis [22] found
that SVM considerably outperformed neural networks and
decision trees in a direct comparison. Otukei and Blaschke
[23] compared DTs, SVM, and MLC for assessing land
cover change, and found DTs to be more effective than
SVM or MLC. Mohamed [24] revealed that the classification
accuracy of the DT algorithm was better than the ANN
algorithm in his comparative research. Otukei and
Blaschke [23] showed decision trees to give better results
than MLC and SVM techniques for land cover change
assessment. Song and Ying [25] successfully showed the
decision tree method to be a powerful statistical tool for
classification, prediction, and interpretation that has
several potential applications in medical research. Friedl
and Brodley [26] found improved accuracy in complex
LULC classifications using a decision tree algorithm.
The objectives of this work are to (i) compare the
classification accuracy of three different algorithms and
(ii) to propose the most suitable algorithm for LU/LC over
the city of Soran using Sentinel- 2A data for 2019.
2. Materials and Methods
2.1. Study Site and Data
Soran was selected as a study area from the previous
work by [27]. The free and open source Sentinel-2A Level
image was downloaded from the Copernicus website
(https://scihub.copernicus.eu/) with a total of thirteen
spectral bands, as acquired on August 20, 2019. The
Sentinel-2A data is widely used in land cover
classification. For this work, four bands - visible (blue,
green, red) and near-infrared with a special resolution of
10 m - were used for the classification, as per Figure 1.
2.2. Algorithm Selection
2.2.1. Artificial Neural Networks Classification
The use of artificial neural networks in remote sensing
studies dates back to the early 1990s [28]. An artificial
neural network (ANN) is a mathematical model [29] that
takes the human brain as a model for problem solving [30].
An ANN is also referred to as a simulated neural network
(SNN) or, more commonly, just a neural network (NN).
An ANN is an interconnected group of artificial neurons
that uses a mathematical model to manipulate information
based on a mathematical link approach. Furthermore, an
ANN is an adaptive system that changes its structure
based on external or internal information that flows across
the network [31].
Figure 1. Location map of Soran district in the Kurdistan Region of Iraq, after [27], showing the ANN result map of this specific work

Applied Ecology and Environmental Sciences 461
A single ANN architecture typically consist of an
input, one or more hidden, and an output layer [32].
Kanellopoulos and Wilkinson [33] identified that the
classification accuracy with an ANN is often greater than
traditional statistical classifiers. Each layer in an ANN is
made up of many neurons where each neuron signifies a
variable in the input layer [30], therefore the stimulations
work in the same way as biological neural networks in the
human brain process information [29]. There will be one
output node for each class in the classification system,
through the image classification process. The general
shape of an ANN is shown in Figure 2.
Figure 2. An example of a neural network with four inputs and one
hidden layer with three hidden neurons, after [34]
A neural network is generated for a specific application,
such as pattern recognition or data classification, through
a learning process. ANN is considered the best method in
a problem solving approach for traditionally problematic
techniques for which algorithmic solution is too complex
to be found, or for which such a solution does not exist
[31]. Also, neural networks can perform image
categorization reasonably quickly, although the training
process itself can be extremely time consuming [35].
2.2.2. Support Vector Machines
Boser, Guyon, and Vapnik first presented support vector
machines (SVMs) formally in 1992 [36]. The SVM
method is a set of non-parametric supervised learning
method used for classification techniques [37], and tries to
generalize and provide reasonable predictions for new
datasets by creating a hyperplane that separates the dataset
into classes. Polynomial, radial basis functions, and
sigmoid kernels are the most commonly used kernels for
image processing [38]. SVM based on statistical learning
determines the border for distinguishing data belonging to
two classes from each other in an optimal manner [1] if
the data to be classified are separated linearly or non-
linearly [37]. Thus, it can be used for linearly and non-
linearly separable data.
The key concept of this discriminant machine learning
technique [39] is to find an optimal hyperplane or the
largest amount of margin among many hyperplanes
between two categories as possible [36], as per Figure 3.
Thus, it seeks the ideal hyperplane to find the maximum
margin in order separate the classes [40], which is why
SVM is known as a large margin classifier [39].
SVM was developed from powerful implementation
theory, whereas ANNs were experimentally moved from
application to theory. SVM does not control the
complexity of the model, as ANN does; instead, it
determines the complexity model automatically by setting
the number of support vectors [39]. It has been found that
SVM generally outperforms neural networks, which is
novel pattern recognition method [1,9].
Finally, support vector machines have been selected as
a group of relatively novel statistical learning algorithms
in classifying homogeneous and heterogeneous land cover
types, with the associated vigour being confirmed by
many various researchers [40].
Figure 3. The optimal separating hyperplane between two separable
samples showing a large margin classifier, after [41]
2.2.3. Decision Tree Classification
Decision Trees (DTs), or Decision Tree Classifiers
(DTCs), are a supervised machine learning method and
are one of many classifiers from statistical-based
algorithms [42] which have been successfully applied in a
variety of fields for digital image classification [43]. A
DTC is a non-parametric classifier [44], which is an
effective and popular technique for classification [45].
Decision tree classification problems can be solved
through identifying to which set an object belongs [46].
The tree in the DT approach constitutes a root node at the
top, a few hidden nodes (internal nodes) which split the
objects into different categories, and a large number
of terminal nodes (known leaves which contain most
homogeneous classes), which is the output [45,47].
Generally speaking, a decision tree asks a question and
then classifies [48] through defining the best associated
tree structure and decision boundaries [23].
3. Results
In this work, three machine learning classifiers were
compared for LULC classification, namely artificial
neural networks, support vector machines, and decision
trees.
3.1. Classification Accuracy Assessment
The confusion matrix results of all three algorithms
are reported in Table 1 - Table 3 with overall accuracy,
producer’s accuracy, user’s accuracy, and Kappa
coefficient for the classified maps for 2019 using Sentinel-
2A imaging [35]. The overall classification accuracies for
ANN, SVM, and DTs are 90%, 65% and 60%, and their
Kappa coefficients are 0.86, 0.57, and 0.53, respectively.

462 Applied Ecology and Environmental Sciences
Table 1. Confusion matrix results for the ANN algorithm for the
land use/land cover map
Sentinel-2A
Class 1 2 3 4 Total
User’s
accuracy (%)
1-Build-up area 69 1 2 3 75 92
2-Cultivated land 4 65 2 4 75 87
3-Riparian zone 1 2 71 1 75 95
4-Barren land 3 3 2 67 75 89
Total 77 71 77 75 300
Producer’s accuracy 90 91 92 87
Overall accuracy 90%
Kappa 0.86
Table 2. Confusion matrix results for the SVM algorithm for the
land use/land cover map
Sentinel-2A
Class 1 2 3 4 Total
User’s
accuracy (%)
1-Build-up area 42 12 14 7 75 56
2-Cultivated land
9
51
7
8
75
68
3-Riparian zone 4 2 66 3 75 88
4-Barren land 9 15 13 38 75 50
Total 64 80 100 56 300
Producer’s accuracy 65 63 66 68
Overall accuracy 65%
Kappa
0.57
Table 3. Confusion matrix results for the DT algorithm for the land
use/land cover map
Sentinel-2A
Class 1 2 3 4 Total
User’s
accuracy (%)
1-Build-up area 67 3 2 3 75 89
2-Cultivated land 14 41 12 8 75 46
3-Riparian zone 18 15 29 13 75 39
4-Barren land 8 12 11 44 75 59
Total 107 71 54 68 300
Producer’s accuracy 63 58 54 65
Overall accuracy 60%
Kappa 0.53
3.2. Landscape Structure and Dynamics
The classified areas were measured in the percentage,
as per Figure 4. Barren land was the predominant class
followed by built-up areas, cultivated land and riparian
zones, which covered 51.93%, 29.28%, 15.56% and 3.21%,
respectively, according to the ANN algorithm. In the
instance of the SVM algorithm, the built-up occupied was
50.25% followed by barren land at 42.6%, cultivated land
at 22.06% and riparian zone at 3.07%. By comparison, the
decision tree classifier produced another set of results.
Furthermore, the maximum percentage was occupied by
barren land at 39.42%, whereas the minimum class was
computerized for cultivated land by 2.87%. However, the
built-up area and riparian zones had almost the same
percentage coverages at 29.05% and 28.63%, respectively.
Figure 4. The percentage land use/land cover for the city of Soran city as
determined by each of the three algorithms considered
Figure 5. Standard natural colour composites and land cover
classifications via ANN, SVMs, and DTs of the acquired Sentinel-2A
imagery
The land use/land cover maps are shown in Figure 5 for
the three algorithms used, including the natural colour
composites. The red colour represents built-up area, orange
indicates barren land, and the light green colour indicates
cultivated land, while dark green represents riparian zone.
4. Discussion
4.1. Artificial Neural Networks
The results of the current work verified that the highest
classification accuracy was obtained by ANN using the
Sentinel-2 data. Most pixels which belong to classes were
correctly classified. Thus, this indicates promising results
through the application of the ANN to the whole dataset.
On the other hand, it achieved only poor results for pixels
in classes characterized by lower classification rates, as
29.28
3.21
51.93
15.56
50.25
3.07
42.6
22.06
29.05 28.63
39.42
2.87
0
10
20
30
40
50
60
Urban area
Riparian
zone
Barren land
Cultivated
land
ANN %
SVM %
DTs %

Applied Ecology and Environmental Sciences 463
revealed by both SVM and DTs. The demand for the use
of ANN in many real-world applications is increasing with
time [49] as a result of, their utility in solving problems
that do not have algorithmic solutions is due to their
powerful methodology [31].
4.2. Support Vector Machine
In spite of the fact that SVM has been successfully used
for data classification in many studies, but it did not prove
particularly effective in the current work. In general, the
main reasons for SVM producing sub-optimal results was
due to the weakness of the soft margin optimization
problem and the imbalanced support vector ratio [50].
For instance, in the current work, the number of training
cases for built-up area are significantly outnumbered by
barren land and slightly so by cultivated land, as per
Figure 4. More generally, the training data sets for barren
land and cultivated land fell into the built-up area classes,
thus the class boundary for built-up area learned by the
SVMs are sharply skewed towards barren land and
cultivated land. In other words, the dataset is imbalanced
with regard to built-up area with barren land and cultivated
land. This imbalanced dataset, as used to develop the
separating hyperplane for the SVM model, was identified
by [51]. Thus, the correct distances and correct orientation
of the hyperplane in learned SVMs do not perform at their
best, which could be due to the hyperplane separation may
not being exactly between two categories. Besides, this
could also indicate a purely linear SVM classifier that led
to the extremely poor performance observed, or in other
words there is no clear separation data lining as identified
by [39]. In general, it is difficult to explain SVM and
different related learning algorithms [52].
4.3. Decision Tree Classifier
In the current work, the decision tree algorithm did not
yield promising results though it has been successfully
used in various other fields [23,44,53]. Kumar and Kumar
[54] focused on two main disadvantages of DTs, which
are overfitting and not being fit for continuous variables.
Overfitting, which is a common problem with decision
trees, was due to noise in the current study, and can be
observed as misclassification of riparian zone, cultivated
land, and barren land in the decision tree classifier. Besides,
overfitting due to lack of samples could also be another
reason for overfitting. Furthermore, the decision trees lost
information between three aforementioned classes by
categorization variables, or in other words the entropy which
is a measure of the uncertainty between classes and that
produced low accuracy output from the test data. However
more generally, decision trees are prone to overfitting because
they are very data concentrated stated Choy and Flom [55].
Furthermore, the tree in the decision trees is highly
dependent on the training data used, therefore any slight
change in the data can cause large variation in the
estimated tree, which subsequently creates a completely
different tree. Another reason could be due to the physical
boundaries between zones. Soran has a homogeneous
landscape and all classes can be easily distinguished and
separated by the naked eye, thus DTs did not perform well
with the physical boundaries between zones. Finally, a
lack of, or no interactions between variables also prevent
DTs from working particularly well [56].
5. Conclusions
The analyses showed differences in the classification
accuracies obtained with different algorithms. Artificial
neural networks produced considerably better results than
the support vector machine and decision trees algorithms,
in the current work. In general, SVM and DTs were not as
effective at representing the classification over the city of
Soran. Hence, ANN is a robust method for classification
and detection of change, and could potentially overcome
the mixed pixel problem in the image. Relatively speaking,
an accurate LULC product can be achieved using ANNs
on the recently acquired Sentinel-2 sensor imagery. Thus,
using Sentinel-2 data may result in better resolution, and
certainly more accurate LULC produces.
Acknowledgments
Many thanks to the Scientific Research Centre (SRC) at
Soran University and to Dr. K. Kolo (SRC) for valuable
comments on the manuscript.
Conflict of Interests
Author has declared that no competing interests exist.
References
[1] Huang, C., L. Davis, and J. Townshend, An assessment of support
vector machines for land cover classification. International
Journal of remote sensing, 2002. 23(4): p. 725-749.
[2] Li, J. and D.P. Roy, A global analysis of Sentinel-2A, Sentinel-2B
and Landsat-8 data revisit intervals and implications for
terrestrial monitoring. Remote Sensing, 2017. 9(9): p. 902.
[3] Lu, D., S. Hetrick, and E. Moran, Impervious surface mapping
with Quickbird imagery. International journal of remote sensing,
2011. 32(9): p. 2519-2533.
[4] Lu, D. and Q. Weng, A survey of image classification methods and
techniques for improving classification performance. International
journal of Remote sensing, 2007. 28(5): p. 823-870.
[5] Anderson, J.R., A land use and land cover classification system
for use with remote sensor data. Vol. 964. 1976: US Government
Printing Office.
[6] Thai, L., T. Hai, and N.T. Thuy, Image classification using
support vector machine and artificial neural network.
International Journal of Information Technology and Computer
Science (IJITCS), 2012. 4(5): p. 32-38.
[7] Foody, G., Supervised image classification by MLP and RBF
neural networks with and without an exhaustively defined set of
classes. International Journal of Remote Sensing, 2004. 25(15):
p. 3091-3104.
[8] Verbeke, L., F. Vancoillie, and R. De Wulf, Reusing back-
propagation artificial neural networks for land cover
classification in tropical savannahs. International Journal of
Remote Sensing, 2004. 25(14): p. 2747-2771.
[9] Foody, G.M. and A. Mathur, Toward intelligent training of
supervised image classifications: directing training data
acquisition for SVM classification. Remote Sensing of
Environment, 2004. 93(1-2): p. 107-117.
[10] Mitra, P., B.U. Shankar, and S.K. Pal, Segmentation of
multispectral remote sensing images using active support vector
machines. Pattern recognition letters, 2004. 25(9): p. 1067-1074.

464 Applied Ecology and Environmental Sciences
[11] Lawrence, R., et al., Classification of remotely sensed imagery
using stochastic gradient boosting as a refinement of classification
tree analysis. Remote sensing of environment, 2004. 90(3):
p. 331-336.
[12] DeFries, R. and J.C.-W. Chan, Multiple criteria for evaluating
machine learning algorithms for land cover classification from
satellite data. Remote Sensing of Environment, 2000. 74(3): p.
503-515.
[13] Sohn, Y., E. Morán, and F. Gurri, Deforestation in North-Central
Yucatan (1985-1995)- Mapping secondary succession of forest
and agricultural land use in Sotuta using the cosine of the angle
concept. Photogrammetric engineering and remote sensing, 1999.
65: p. 947-958.
[14] Sohn, Y. and N.S. Rebello, Supervised and unsupervised spectral
angle classifiers. Photogrammetric engineering and remote
sensing, 2002. 68(12): p. 1271-1282.
[15] Dymova, L., P. Sevastianov, and P. Bartosiewicz, A new approach
to the rule-base evidential reasoning: Stock trading expert system
application. Expert Systems with Applications, 2010. 37(8):
p. 5564-5576.
[16] Yang, J.-B., et al., Belief rule-base inference methodology using
the evidential reasoning approach-RIMER. IEEE Transactions on
systems, Man, and Cybernetics-part A: Systems and Humans,
2006. 36(2): p. 266-285.
[17] Franklin, S. and M. Wulder, Remote sensing methods in medium
spatial resolution satellite data land cover classification of large
areas. Progress in Physical Geography, 2002. 26(2): p. 173-205.
[18] Congalton, R.G. and L. Plourde, Quality assurance and accuracy
assessment of information derived from remotely sensed data.
Manual of geospatial science and technology, 2002: p. 349-361.
[19] Foody, G.M., Status of land cover classification accuracy assessment.
Remote sensing of environment, 2002. 80(1): p. 185-201.
[20] Szantoi, Z., et al., Classifying spatially heterogeneous wetland
communities using machine learning algorithms and spectral and
textural features. Environmental monitoring and assessment, 2015.
187(5): p. 262.
[21] Chen, J., A comparison of four data mining models: bayes, neural
network. SVM and decision trees in identifying syndromes in
coronary heart disease, 2007. 4491: p. 2007.
[22] Khatami, R., G. Mountrakis, and S.V. Stehman, A meta-analysis
of remote sensing research on supervised pixel-based land-cover
image classification processes: General guidelines for practitioners
and future research. Remote Sensing of Environment, 2016. 177:
p. 89-100.
[23] Otukei, J.R. and T. Blaschke, Land cover change assessment using
decision trees, support vector machines and maximum likelihood
classification algorithms. International Journal of Applied Earth
Observation and Geoinformation, 2010. 12: p. S27-S31.
[24] Mohamed, A.E., Comparative study of four supervised machine
learning techniques for classification. International Journal of
Applied, 2017. 7(2).
[25] Song, Y.-Y. and L. Ying, Decision tree methods: applications for
classification and prediction. Shanghai archives of psychiatry,
2015. 27(2): p. 130.
[26] Friedl, M.A. and C.E. Brodley, Decision tree classification of land
cover from remotely sensed data. Remote sensing of environment,
1997. 61(3): p. 399-409.
[27] Hamad, R., A remote sensing and GIS-based analysis of urban
sprawl in Soran District, Iraqi Kurdistan. SN Applied Sciences,
2020. 2(1): p. 24.
[28] Atkinson, P.M. and A.R. Tatnall, Introduction neural networks in
remote sensing. International Journal of remote sensing, 1997.
18(4): p. 699-709.
[29] Liu, C., et al., Comparison of neural networks and statistical
methods in classification of ecological habitats using FIA data.
Forest Science, 2003. 49(4): p. 619-631.
[30] Kesikoglu, M.H., et al., Performance of ANN, SVM and MLH
techniques for land use/cover change detection at Sultan Marshes
wetland, Turkey. Water Science and Technology, 2019. 80(3): p.
466-477.
[31] Bhatta, B., Remote sensing and GIS. 2008: Oxford University
Press, USA.
[32] Civco, D.L., Artificial neural networks for land-cover
classification and mapping. International journal of geographical
information science, 1993. 7(2): p. 173-186.
[33] Kanellopoulos, I. and G.G. Wilkinson, Strategies and best
practice for neural network image classification. International
Journal of Remote Sensing, 1997. 18(4): p. 711-725.
[34] Todorov, T.I., R.R. Stewart, and D.P. Hampson, Porosity
prediction using attributes from 3C–3D seismic data. 1998,
CREWES research report, 10, Chapt-52.
[35] Lillesand, T., R.W. Kiefer, and J. Chipman, Remote sensing and
image interpretation. 2014: John Wiley & Sons.
[36] Wang, Q., Y. Tian, and D. Liu, Adaptive FH-SVM for Imbalanced
Classification. IEEE Access, 2019. 7: p. 130410-130422.
[37] Rudrapal, D. and M. Subhedar, Land cover classification using
support vector machine. International Journal of Engineering
Research & Technology (IJERT), 2015. 4(09).
[38] Kranjčić, N., et al., Support Vector Machine Accuracy Assessment
for Extracting Green Urban Areas in Towns. Remote Sensing,
2019. 11(6): p. 655.
[39] Awad, M. and R. Khanna, Support vector machines for classification,
in Efficient Learning Machines. 2015, Springer. p. 39-66.
[40] Shi, D. and X. Yang, Support vector machines for land cover
mapping from remote sensor imagery, in Monitoring and
Modeling of Global Changes: A Geomatics Perspective. 2015,
Springer. p. 265-279.
[41] Guo, G., S.Z. Li, and K.L. Chan, Support vector machines for face
recognition. Image and Vision computing, 2001. 19(9-10): p. 631-
638.
[42] Xie, Z., et al., Classification of land cover, forest, and tree species
classes with ZiYuan-3 multispectral and stereo data. Remote
Sensing, 2019. 11(2): p. 164.
[43] Osei-Bryson, K.-M., Post-pruning in decision tree induction using
multiple performance measures. Computers & operations research,
2007. 34(11): p. 3331-3345.
[44] Sahoo, S. and P. Raj, EVALUATION OF DIFFERENT
TECHNIQUES TO DETECT LAND USE/LAND COVER OVER
AN AREA. Journal of Spatial Hydrology, 2019. 14(2).
[45] Sharma, R., A. Ghosh, and P. Joshi, Decision tree approach
for classification of remotely sensed satellite data using open
source support. Journal of Earth System Science, 2013. 122(5):
p. 1237-1247.
[46] Michalski, R.S., J.G. Carbonell, and T.M. Mitchell, Machine
Learning: An Artificial Intelligence Approach, vol. 1. Tioga, Palo
Alto, California, 1983.
[47] Pantazi, X.-E., D. Moshou, and D. Bochtis, Intelligent Data
Mining and Fusion Systems in Agriculture. 2019: Academic Press.
[48] Coleman, J. and J.S. Coleman, Introducing speech and language
processing. 2005: Cambridge university press.
[49] Korkobi, T., M. Djemel, and M. Chtourou, Stability analysis of
neural networks-based system identification. Modelling and
Simulation in Engineering, 2008. 2008.
[50] He, H. and Y. Ma, Imbalanced learning: foundations, algorithms,
and applications. 2013: John Wiley & Sons.
[51] Veropoulos, Campell C., and Cristanini N., “Controlling the
sensitivity of support vector machines,” in Proceeding of the
International Joint Conference on Artificial Intelligence
(Stockholm, Sweden). 1999: p. pp. 55-60.
[52] Kowsari, K., et al. Hdltex: Hierarchical deep learning for text
classification. in 2017 16th IEEE international conference on
machine learning and applications (ICMLA). 2017. IEEE.
[53] Punia, M., P.K. Joshi, and M. Porwal, Decision tree classification
of land use land cover for Delhi, India using IRS-P6 AWiFS data.
Expert systems with Applications, 2011. 38(5): p. 5577-5583.
[54] Kumar, G.D. and G.D. Kumar, Machine Learning Techniques for
Improved Business Analytics. 2018: IGI Global.
[55] Choy, M. and P. Flom. Building decision trees from decision
stumps. in SAS Global Forum. 2010.
[56] Ramezankhani, A., et al., Decision tree-based modelling for
identification of potential interactions between type 2 diabetes risk
factors: a decade follow-up in a Middle East prospective cohort
study. BMJ open, 2016. 6(12): p. e013336.
© The Author(s) 2020
. This article is an open access article distributed under the terms and conditions of the Creative Commons
Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).