A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random Forest

The purposes of the algorithm presented in this paper are to select features with the highest average separability by using the random forest method to distinguish categories that are easy to distinguish and to select the most divisible features from the most difficult categories using the weighted...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengmeng Sun, Chunyang Wang, Shuangting Wang, Zongze Zhao, Xiao Li
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Advances in Multimedia
Online Access:http://dx.doi.org/10.1155/2018/3521720
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850220640445923328
author Mengmeng Sun
Chunyang Wang
Shuangting Wang
Zongze Zhao
Xiao Li
author_facet Mengmeng Sun
Chunyang Wang
Shuangting Wang
Zongze Zhao
Xiao Li
author_sort Mengmeng Sun
collection DOAJ
description The purposes of the algorithm presented in this paper are to select features with the highest average separability by using the random forest method to distinguish categories that are easy to distinguish and to select the most divisible features from the most difficult categories using the weighted entropy algorithm. The framework is composed of five parts: (1) random samples selection with (2) probabilistic output initial random forest classification processing based on the number of votes; (3) semisupervised classification, which is an improvement of the supervision classification of random forest based on the weighted entropy algorithm; (4) precision evaluation; and (5) a comparison with the traditional minimum distance classification and the support vector machine (SVM) classification. In order to verify the universality of the proposed algorithm, two different data sources are tested, which are AVIRIS and Hyperion data. The results show that the overall classification accuracy of AVIRIS data is up to 87.36%, the kappa coefficient is up to 0.8591, and the classification time is 22.72s. Hyperion data is up to 99.17%, the kappa coefficient is up to 0.9904, and the classification time is 8.16s. Classification accuracy is obviously improved and efficiency is greatly improved, compared with the minimum distance and the SVM classifier and the CART classifier.
format Article
id doaj-art-75a6d1c02c044265a4b695f995b0fe8a
institution OA Journals
issn 1687-5680
1687-5699
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Advances in Multimedia
spelling doaj-art-75a6d1c02c044265a4b695f995b0fe8a2025-08-20T02:07:01ZengWileyAdvances in Multimedia1687-56801687-56992018-01-01201810.1155/2018/35217203521720A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random ForestMengmeng Sun0Chunyang Wang1Shuangting Wang2Zongze Zhao3Xiao Li4School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaThe purposes of the algorithm presented in this paper are to select features with the highest average separability by using the random forest method to distinguish categories that are easy to distinguish and to select the most divisible features from the most difficult categories using the weighted entropy algorithm. The framework is composed of five parts: (1) random samples selection with (2) probabilistic output initial random forest classification processing based on the number of votes; (3) semisupervised classification, which is an improvement of the supervision classification of random forest based on the weighted entropy algorithm; (4) precision evaluation; and (5) a comparison with the traditional minimum distance classification and the support vector machine (SVM) classification. In order to verify the universality of the proposed algorithm, two different data sources are tested, which are AVIRIS and Hyperion data. The results show that the overall classification accuracy of AVIRIS data is up to 87.36%, the kappa coefficient is up to 0.8591, and the classification time is 22.72s. Hyperion data is up to 99.17%, the kappa coefficient is up to 0.9904, and the classification time is 8.16s. Classification accuracy is obviously improved and efficiency is greatly improved, compared with the minimum distance and the SVM classifier and the CART classifier.http://dx.doi.org/10.1155/2018/3521720
spellingShingle Mengmeng Sun
Chunyang Wang
Shuangting Wang
Zongze Zhao
Xiao Li
A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random Forest
Advances in Multimedia
title A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random Forest
title_full A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random Forest
title_fullStr A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random Forest
title_full_unstemmed A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random Forest
title_short A New Semisupervised-Entropy Framework of Hyperspectral Image Classification Based on Random Forest
title_sort new semisupervised entropy framework of hyperspectral image classification based on random forest
url http://dx.doi.org/10.1155/2018/3521720
work_keys_str_mv AT mengmengsun anewsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT chunyangwang anewsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT shuangtingwang anewsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT zongzezhao anewsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT xiaoli anewsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT mengmengsun newsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT chunyangwang newsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT shuangtingwang newsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT zongzezhao newsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest
AT xiaoli newsemisupervisedentropyframeworkofhyperspectralimageclassificationbasedonrandomforest