Fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image.
Currently, remote sensing technologies were widely employed in the dynamic monitoring of the land. This paper presented an algorithm named fuzzy nonlinear proximal support vector machine (FNPSVM) by basing on ETM(+) remote sensing image. This algorithm is applied to extract various types of lands of...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2013-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC3720649?pdf=render |
id |
doaj-d0eb2d2a79f249b286f98a9359dcb80d |
---|---|
record_format |
Article |
spelling |
doaj-d0eb2d2a79f249b286f98a9359dcb80d2020-11-25T02:22:53ZengPublic Library of Science (PLoS)PLoS ONE1932-62032013-01-0187e6943410.1371/journal.pone.0069434Fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image.Xiaomei ZhongJianping LiHuacheng DouShijun DengGuofei WangYu JiangYongjie WangZebing ZhouLi WangFei YanCurrently, remote sensing technologies were widely employed in the dynamic monitoring of the land. This paper presented an algorithm named fuzzy nonlinear proximal support vector machine (FNPSVM) by basing on ETM(+) remote sensing image. This algorithm is applied to extract various types of lands of the city Da'an in northern China. Two multi-category strategies, namely "one-against-one" and "one-against-rest" for this algorithm were described in detail and then compared. A fuzzy membership function was presented to reduce the effects of noises or outliers on the data samples. The approaches of feature extraction, feature selection, and several key parameter settings were also given. Numerous experiments were carried out to evaluate its performances including various accuracies (overall accuracies and kappa coefficient), stability, training speed, and classification speed. The FNPSVM classifier was compared to the other three classifiers including the maximum likelihood classifier (MLC), back propagation neural network (BPN), and the proximal support vector machine (PSVM) under different training conditions. The impacts of the selection of training samples, testing samples and features on the four classifiers were also evaluated in these experiments.http://europepmc.org/articles/PMC3720649?pdf=render |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiaomei Zhong Jianping Li Huacheng Dou Shijun Deng Guofei Wang Yu Jiang Yongjie Wang Zebing Zhou Li Wang Fei Yan |
spellingShingle |
Xiaomei Zhong Jianping Li Huacheng Dou Shijun Deng Guofei Wang Yu Jiang Yongjie Wang Zebing Zhou Li Wang Fei Yan Fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image. PLoS ONE |
author_facet |
Xiaomei Zhong Jianping Li Huacheng Dou Shijun Deng Guofei Wang Yu Jiang Yongjie Wang Zebing Zhou Li Wang Fei Yan |
author_sort |
Xiaomei Zhong |
title |
Fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image. |
title_short |
Fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image. |
title_full |
Fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image. |
title_fullStr |
Fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image. |
title_full_unstemmed |
Fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image. |
title_sort |
fuzzy nonlinear proximal support vector machine for land extraction based on remote sensing image. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS ONE |
issn |
1932-6203 |
publishDate |
2013-01-01 |
description |
Currently, remote sensing technologies were widely employed in the dynamic monitoring of the land. This paper presented an algorithm named fuzzy nonlinear proximal support vector machine (FNPSVM) by basing on ETM(+) remote sensing image. This algorithm is applied to extract various types of lands of the city Da'an in northern China. Two multi-category strategies, namely "one-against-one" and "one-against-rest" for this algorithm were described in detail and then compared. A fuzzy membership function was presented to reduce the effects of noises or outliers on the data samples. The approaches of feature extraction, feature selection, and several key parameter settings were also given. Numerous experiments were carried out to evaluate its performances including various accuracies (overall accuracies and kappa coefficient), stability, training speed, and classification speed. The FNPSVM classifier was compared to the other three classifiers including the maximum likelihood classifier (MLC), back propagation neural network (BPN), and the proximal support vector machine (PSVM) under different training conditions. The impacts of the selection of training samples, testing samples and features on the four classifiers were also evaluated in these experiments. |
url |
http://europepmc.org/articles/PMC3720649?pdf=render |
work_keys_str_mv |
AT xiaomeizhong fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT jianpingli fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT huachengdou fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT shijundeng fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT guofeiwang fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT yujiang fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT yongjiewang fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT zebingzhou fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT liwang fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage AT feiyan fuzzynonlinearproximalsupportvectormachineforlandextractionbasedonremotesensingimage |
_version_ |
1724861241901449216 |