Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

FU Xiaoyang; P E R Dale; ZHANG Shuqing

doi:10.1007/s11769-008-0162-x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

FU Xiaoyang, P E R Dale, ZHANG Shuqing

文章导航 > Chinese Geographical Science > 2008 > 18(2): 162-170

FU Xiaoyang, P E R Dale, ZHANG Shuqing. Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification[J]. 中国地理科学, 2008, 18(2): 162-170. doi: 10.1007/s11769-008-0162-x

引用本文:

FU Xiaoyang, P E R Dale, ZHANG Shuqing. Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification[J]. Chinese Geographical Science, 2008, 18(2): 162-170. doi: 10.1007/s11769-008-0162-x

Citation:

FU Xiaoyang, P E R Dale, ZHANG Shuqing. Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification[J]. Chinese Geographical Science, 2008, 18(2): 162-170. doi: 10.1007/s11769-008-0162-x

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

doi: 10.1007/s11769-008-0162-x

1.
Institute of Computer and Science Technology, Jilin University, Zhuhai 519041, China;
2.
Griffith School of Environment, Griffith University Queensland 4111, Australia;
3.
Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China

详细信息

通讯作者:
FU Xiaoyang. E-mail: dvndavidfu@vip.163.com

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

1.
Institute of Computer and Science Technology, Jilin University, Zhuhai 519041, China;
2.
Griffith School of Environment, Griffith University Queensland 4111, Australia;
3.
Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China

摘要: Coastal wetlands are characterized by complex patterns both in their geomorphic and ecological features. Besides field observations, it is necessary to analyze the land cover of wetlands through the color infrared (CIR) aerial photography or remote sensing image. In this paper, we designed an evolving neural network classifier using variable string genetic algorithm (VGA) for the land cover classification of CIR aerial image. With the VGA, the classifier that we designed is able to evolve automatically the appropriate number of hidden nodes for modeling the neural network topology optimally and to find a near-optimal set of connection weights globally. Then, with backpropagation algo-rithm (BP), it can find the best connection weights. The VGA-BP classifier, which is derived from hybrid algorithms mentioned above, is demonstrated on CIR images classification effectively. Compared with standard classifiers, such as Bayes maximum-likelihood classifier, VGA classifier and BP-MLP (multi-layer perception) classifier, it has shown that the VGA-BP classifier can have better performance on highly resolution land cover classification.
- variable string genetic algorithm /
- neural network /
- pattern classification /
- CIR image
Abstract: Coastal wetlands are characterized by complex patterns both in their geomorphic and ecological features. Besides field observations, it is necessary to analyze the land cover of wetlands through the color infrared (CIR) aerial photography or remote sensing image. In this paper, we designed an evolving neural network classifier using variable string genetic algorithm (VGA) for the land cover classification of CIR aerial image. With the VGA, the classifier that we designed is able to evolve automatically the appropriate number of hidden nodes for modeling the neural network topology optimally and to find a near-optimal set of connection weights globally. Then, with backpropagation algo-rithm (BP), it can find the best connection weights. The VGA-BP classifier, which is derived from hybrid algorithms mentioned above, is demonstrated on CIR images classification effectively. Compared with standard classifiers, such as Bayes maximum-likelihood classifier, VGA classifier and BP-MLP (multi-layer perception) classifier, it has shown that the VGA-BP classifier can have better performance on highly resolution land cover classification.
- variable string genetic algorithm /
- neural network /
- pattern classification /
- CIR image

[1]	TONG Huali, SHI Peiji, LUO Jun, LIU Xiaoxiao. The Structure and Pattern of Urban Network in the Lanzhou-Xining Urban Agglomeration . Chinese Geographical Science, 2020, 30(1): 59-74. doi: 10.1007/s11769-019-1090-7
[2]	HUANG Yajie, LI Zhen, YE Huichun, ZHANG Shiwen, ZHUO Zhiqing, XING An, HUANG Yuanfang. Mapping Soil Electrical Conductivity Using Ordinary Kriging Combined with Back-propagation Network . Chinese Geographical Science, 2019, 20(2): 270-282. doi: 10.1007/s11769-019-1027-1
[3]	MAO Kebiao, ZUO Zhiyuan, SHEN Xinyi, XU Tongren, GAO Chunyu, LIU Guang. Retrieval of Land-surface Temperature from AMSR2 Data Using a Deep Dynamic Learning Neural Network . Chinese Geographical Science, 2018, 28(1): 1-11. doi: 10.1007/s11769-018-0930-1
[4]	GUO Jianke, WANG Shaobo, WANG Dandan, LIU Tianbao. Spatial Structural Pattern and Vulnerability of China-Japan-Korea Shipping Network . Chinese Geographical Science, 2017, 27(5): 697-708. doi: 10.1007/s11769-017-0903-9
[5]	QIAO Weifeng, GAO Junbo, LIU Yansui, QIN Yueheng, LU Cheng, JI Qingqing. Evaluation of Intensive Urban Land Use Based on an Artificial Neural Network Model:A Case Study of Nanjing City, China . Chinese Geographical Science, 2017, 27(5): 735-746. doi: 10.1007/s11769-017-0905-7
[6]	MAO Kebiao, MA Ying, XIA Lang, SHEN Xinyi, SUN Zhiwen, HE Tianjue, ZHOU Guanhua. A Neural Network Method for Monitoring Snowstorm：A Case Study in Southern China . Chinese Geographical Science, 2014, 0(5): 599-606. doi: 10.1007/s11769-014-0675-4
[7]	ZHEN Feng, WANG Xia, YIN Jun, ZHANG Min. An Empirical Study on Chinese City Network Pattern Based on Producer Services . Chinese Geographical Science, 2013, 23(3): 274-285. doi: 10.1007/s11769-013-0595-8
[8]	YANG Fei Zhu Yunqiang Zhang Jiahua YAO Zuofang. Estimating Fraction of Photosynthetically Active Radiation of Corn with Vegetation Indices and Neural Network from Hyperspectral Data . Chinese Geographical Science, 2012, 22(1): 63-74.
[9]	SHI Xiaoliang, LI Ying, DENG Rongxin. The Method Study of Spatial heterogeneity evaluation on the Landscape Pattern Of Farmland Shelterbelt Network . Chinese Geographical Science, 2011, 21(1): 48-56.
[10]	DU Peijun, YUAN Linshan, XIA Junshi, et al.. Fusion and Classification of Beijing-1 Small Satellite Remote Sensing Image for Land Cover Monitoring in Mining Area . Chinese Geographical Science, 2011, 21(6): 656-665.
[11]	NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area . Chinese Geographical Science, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
[12]	WANG Jing, TANG Jilong, LIU Jibin, REN Chunying, LIU Xiangnan, FENG Jiang. Alternative Fuzzy Cluster Segmentation of Remote Sensing Images Based on Adaptive Genetic Algorithm . Chinese Geographical Science, 2009, 19(1): 83-88. doi: 10.1007/s11769-009-0083-3
[13]	MO Minghao, WANG Xuelei, WU Houjian, CAI Shuming, Xiaoyang ZHANG, WANG Huiliang. Ecosystem Health Assessment of Honghu Lake Wetland of China Using Artificial Neural Network Approach . Chinese Geographical Science, 2009, 19(4): 349-356. doi: 10.1007/s11769-009-0349-9
[14]	CAO Yungang, YANG Xiuchun, ZHU Xiaohua. Retrieval Snow Depth by Artificial Neural Network Methodology from Integrated AMSR-E and In-situ Data——A Case Study in Qinghai-Tibet Plateau . Chinese Geographical Science, 2008, 18(4): 356-360. doi: 10.1007/s11769-008-356-2
[15]	LIU Yongxue, LI Manchun, MAO Liang, XU Feifei, HUANG Shuo. Review of Remotely Sensed Imagery Classification Patterns Based on Object-oriented Image Analysis . Chinese Geographical Science, 2006, 16(3): 282-288.
[16]	SHI Chun, Philip JAMES, GUO Zhong-yang. APPLICATION OF ARTIFICIAL NEURAL NETWORK IN COMPLEX SYSTEMS OF REGIONAL SUSTAINABLE DEVELOPMENT . Chinese Geographical Science, 2004, 14(1): 1-8.
[17]	CHEN Jie, GONG Zi-tong, CHEN Zhi-cheng, TAN Man-zhi. CLASSIFICATION OF CRYOSOLS:SIGNIFICANCE, ACHIEVEMENTS AND CHALLENGES . Chinese Geographical Science, 2003, 13(4): 352-358.
[18]	WANG Xie-kang, HUANG Er, CUI Peng. SIMULATION AND PREDICTION OF DEBRIS FLOW USING ARTIFICIAL NEURAL NETWORK . Chinese Geographical Science, 2003, 13(3): 262-266.
[19]	DU Jin-kang, FENG Xue-zhi, WANG Zhou-long, HUANG Yong-sheng, RAMADAN Elnazir. THE METHODS OF EXTRACTING WATER INFORMATION FROM SPOT IMAGE . Chinese Geographical Science, 2002, 12(1): 68-72.
[20]	赵剑平. THE CHINESE ECOLOGICAL RESEARCH NETWORK . Chinese Geographical Science, 1994, 4(1): 81-94.

点击查看大图

计量

文章访问数: 867
HTML全文浏览量: 9
PDF下载量: 1954
被引次数: 0

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

doi: 10.1007/s11769-008-0162-x

1. Institute of Computer and Science Technology, Jilin University, Zhuhai 519041, China;

2. Griffith School of Environment, Griffith University Queensland 4111, Australia;

3. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China

通讯作者: FU Xiaoyang. E-mail: dvndavidfu@vip.163.com

收稿日期: 2007-10-09
修回日期: 2008-03-30
刊出日期: 2008-06-20

关键词:

variable string genetic algorithm /

neural network /

pattern classification /

CIR image

摘要: Coastal wetlands are characterized by complex patterns both in their geomorphic and ecological features. Besides field observations, it is necessary to analyze the land cover of wetlands through the color infrared (CIR) aerial photography or remote sensing image. In this paper, we designed an evolving neural network classifier using variable string genetic algorithm (VGA) for the land cover classification of CIR aerial image. With the VGA, the classifier that we designed is able to evolve automatically the appropriate number of hidden nodes for modeling the neural network topology optimally and to find a near-optimal set of connection weights globally. Then, with backpropagation algo-rithm (BP), it can find the best connection weights. The VGA-BP classifier, which is derived from hybrid algorithms mentioned above, is demonstrated on CIR images classification effectively. Compared with standard classifiers, such as Bayes maximum-likelihood classifier, VGA classifier and BP-MLP (multi-layer perception) classifier, it has shown that the VGA-BP classifier can have better performance on highly resolution land cover classification.

English Abstract

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

1. Institute of Computer and Science Technology, Jilin University, Zhuhai 519041, China;

2. Griffith School of Environment, Griffith University Queensland 4111, Australia;

3. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China

Received Date: 2007-10-09
Rev Recd Date: 2008-03-30
Publish Date: 2008-06-20

Keywords:

Abstract: Coastal wetlands are characterized by complex patterns both in their geomorphic and ecological features. Besides field observations, it is necessary to analyze the land cover of wetlands through the color infrared (CIR) aerial photography or remote sensing image. In this paper, we designed an evolving neural network classifier using variable string genetic algorithm (VGA) for the land cover classification of CIR aerial image. With the VGA, the classifier that we designed is able to evolve automatically the appropriate number of hidden nodes for modeling the neural network topology optimally and to find a near-optimal set of connection weights globally. Then, with backpropagation algo-rithm (BP), it can find the best connection weights. The VGA-BP classifier, which is derived from hybrid algorithms mentioned above, is demonstrated on CIR images classification effectively. Compared with standard classifiers, such as Bayes maximum-likelihood classifier, VGA classifier and BP-MLP (multi-layer perception) classifier, it has shown that the VGA-BP classifier can have better performance on highly resolution land cover classification.

引用本文:

Citation:

全文HTML

下载: 全尺寸图片幻灯片

返回文章

用微信扫码二维码

分享至好友和朋友圈

留言板

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

doi: 10.1007/s11769-008-0162-x

通讯作者: FU Xiaoyang. E-mail: dvndavidfu@vip.163.com

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

计量

出版历程

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

doi: 10.1007/s11769-008-0162-x

1. Institute of Computer and Science Technology, Jilin University, Zhuhai 519041, China; 2. Griffith School of Environment, Griffith University Queensland 4111, Australia; 3. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China

通讯作者: FU Xiaoyang. E-mail: dvndavidfu@vip.163.com

English Abstract

Evolving Neural Network Using Variable String Genetic Algorithm for Color Infrared Aerial Image Classification

1. Institute of Computer and Science Technology, Jilin University, Zhuhai 519041, China; 2. Griffith School of Environment, Griffith University Queensland 4111, Australia; 3. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China

全文HTML

目录

通讯作者:
FU Xiaoyang. E-mail: dvndavidfu@vip.163.com

1. Institute of Computer and Science Technology, Jilin University, Zhuhai 519041, China;

2. Griffith School of Environment, Griffith University Queensland 4111, Australia;

3. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China

1. Institute of Computer and Science Technology, Jilin University, Zhuhai 519041, China;

2. Griffith School of Environment, Griffith University Queensland 4111, Australia;

3. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China