A review of addressing class noise problems of remote sensing classification

The development of image classification is one of the most important research topics in remote sensing. The predic-tion accuracy depends not only on the appropriate choice of the machine learning method but also on the quality of the training datasets. However, real-world data is not perfect and oft...

Full description

Saved in:
Bibliographic Details
Published in:Journal of systems engineering and electronics 2023-02, Vol.34 (1), p.36-46
Main Authors: Feng, Wei, Long, Yijun, Wang, Shuo, Quan, Yinghui
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c325t-170cbed006c24610c51bb5e95d4dd3e3298a6bfa258fdb526a795f70fb6a0ad43
cites cdi_FETCH-LOGICAL-c325t-170cbed006c24610c51bb5e95d4dd3e3298a6bfa258fdb526a795f70fb6a0ad43
container_end_page 46
container_issue 1
container_start_page 36
container_title Journal of systems engineering and electronics
container_volume 34
creator Feng, Wei
Long, Yijun
Wang, Shuo
Quan, Yinghui
description The development of image classification is one of the most important research topics in remote sensing. The predic-tion accuracy depends not only on the appropriate choice of the machine learning method but also on the quality of the training datasets. However, real-world data is not perfect and often suf-fers from noise. This paper gives an overview of noise filtering methods. Firstly, the types of noise and the consequences of class noise on machine learning are presented. Secondly, class noise handling methods at both the data level and the algorithm level are introduced. Then ensemble-based class noise handling methods including class noise removal, correction, and noise robust ensemble learners are presented. Finally, a summary of existing data-cleaning techniques is given.
doi_str_mv 10.23919/JSEE.2023.000034
format article
fullrecord <record><control><sourceid>wanfang_jour_cross</sourceid><recordid>TN_cdi_wanfang_journals_xtgcydzjs_e202301006</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><wanfj_id>xtgcydzjs_e202301006</wanfj_id><sourcerecordid>xtgcydzjs_e202301006</sourcerecordid><originalsourceid>FETCH-LOGICAL-c325t-170cbed006c24610c51bb5e95d4dd3e3298a6bfa258fdb526a795f70fb6a0ad43</originalsourceid><addsrcrecordid>eNpNkMtOwzAQRS0EElXpB7DzB5AytuOkWVZVeakSC2Bt-TGuXLVOZQdK-XoSigSzmVmcmdE9hFwzmHLRsOb26WW5nHLgYgp9ifKMjBhAWZRM8PN_8yWZ5LwZGKiBcxiR1Zwm_Ah4oK2n2rmEOYe4pnarc6axDRnpPrVmi7s8IAl3bYc0Y_zDgg9Wd6GNV-TC623GyW8fk7e75evioVg93z8u5qvCCi67gtVgDTqAyvKyYmAlM0ZiI13pnEDBm5mujNdczrwzkle6bqSvwZtKg3alGJOb092Djl7Htdq07yn2H9Vnt7ZH97XJCgcd0CevepydcJvanBN6tU9hp9NRMVA_AtUgUA0b6iRQfAM0GGQd</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A review of addressing class noise problems of remote sensing classification</title><source>IEEE Xplore All Journals</source><creator>Feng, Wei ; Long, Yijun ; Wang, Shuo ; Quan, Yinghui</creator><creatorcontrib>Feng, Wei ; Long, Yijun ; Wang, Shuo ; Quan, Yinghui</creatorcontrib><description>The development of image classification is one of the most important research topics in remote sensing. The predic-tion accuracy depends not only on the appropriate choice of the machine learning method but also on the quality of the training datasets. However, real-world data is not perfect and often suf-fers from noise. This paper gives an overview of noise filtering methods. Firstly, the types of noise and the consequences of class noise on machine learning are presented. Secondly, class noise handling methods at both the data level and the algorithm level are introduced. Then ensemble-based class noise handling methods including class noise removal, correction, and noise robust ensemble learners are presented. Finally, a summary of existing data-cleaning techniques is given.</description><identifier>ISSN: 1004-4132</identifier><identifier>EISSN: 1004-4132</identifier><identifier>DOI: 10.23919/JSEE.2023.000034</identifier><language>eng</language><publisher>Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an 710071, China</publisher><ispartof>Journal of systems engineering and electronics, 2023-02, Vol.34 (1), p.36-46</ispartof><rights>Copyright © Wanfang Data Co. Ltd. All Rights Reserved.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c325t-170cbed006c24610c51bb5e95d4dd3e3298a6bfa258fdb526a795f70fb6a0ad43</citedby><cites>FETCH-LOGICAL-c325t-170cbed006c24610c51bb5e95d4dd3e3298a6bfa258fdb526a795f70fb6a0ad43</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttp://www.wanfangdata.com.cn/images/PeriodicalImages/xtgcydzjs-e/xtgcydzjs-e.jpg</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Feng, Wei</creatorcontrib><creatorcontrib>Long, Yijun</creatorcontrib><creatorcontrib>Wang, Shuo</creatorcontrib><creatorcontrib>Quan, Yinghui</creatorcontrib><title>A review of addressing class noise problems of remote sensing classification</title><title>Journal of systems engineering and electronics</title><description>The development of image classification is one of the most important research topics in remote sensing. The predic-tion accuracy depends not only on the appropriate choice of the machine learning method but also on the quality of the training datasets. However, real-world data is not perfect and often suf-fers from noise. This paper gives an overview of noise filtering methods. Firstly, the types of noise and the consequences of class noise on machine learning are presented. Secondly, class noise handling methods at both the data level and the algorithm level are introduced. Then ensemble-based class noise handling methods including class noise removal, correction, and noise robust ensemble learners are presented. Finally, a summary of existing data-cleaning techniques is given.</description><issn>1004-4132</issn><issn>1004-4132</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNpNkMtOwzAQRS0EElXpB7DzB5AytuOkWVZVeakSC2Bt-TGuXLVOZQdK-XoSigSzmVmcmdE9hFwzmHLRsOb26WW5nHLgYgp9ifKMjBhAWZRM8PN_8yWZ5LwZGKiBcxiR1Zwm_Ah4oK2n2rmEOYe4pnarc6axDRnpPrVmi7s8IAl3bYc0Y_zDgg9Wd6GNV-TC623GyW8fk7e75evioVg93z8u5qvCCi67gtVgDTqAyvKyYmAlM0ZiI13pnEDBm5mujNdczrwzkle6bqSvwZtKg3alGJOb092Djl7Htdq07yn2H9Vnt7ZH97XJCgcd0CevepydcJvanBN6tU9hp9NRMVA_AtUgUA0b6iRQfAM0GGQd</recordid><startdate>20230201</startdate><enddate>20230201</enddate><creator>Feng, Wei</creator><creator>Long, Yijun</creator><creator>Wang, Shuo</creator><creator>Quan, Yinghui</creator><general>Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an 710071, China</general><general>Xi'an Key Laboratory of Advanced Remote Sensing, Xi'an 710071, China</general><general>School of Electronic Engineering, Xidian University, Xi'an 710071, China</general><scope>AAYXX</scope><scope>CITATION</scope><scope>2B.</scope><scope>4A8</scope><scope>92I</scope><scope>93N</scope><scope>PSX</scope><scope>TCJ</scope></search><sort><creationdate>20230201</creationdate><title>A review of addressing class noise problems of remote sensing classification</title><author>Feng, Wei ; Long, Yijun ; Wang, Shuo ; Quan, Yinghui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c325t-170cbed006c24610c51bb5e95d4dd3e3298a6bfa258fdb526a795f70fb6a0ad43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Feng, Wei</creatorcontrib><creatorcontrib>Long, Yijun</creatorcontrib><creatorcontrib>Wang, Shuo</creatorcontrib><creatorcontrib>Quan, Yinghui</creatorcontrib><collection>CrossRef</collection><collection>Wanfang Data Journals - Hong Kong</collection><collection>WANFANG Data Centre</collection><collection>Wanfang Data Journals</collection><collection>万方数据期刊 - 香港版</collection><collection>China Online Journals (COJ)</collection><collection>China Online Journals (COJ)</collection><jtitle>Journal of systems engineering and electronics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Feng, Wei</au><au>Long, Yijun</au><au>Wang, Shuo</au><au>Quan, Yinghui</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A review of addressing class noise problems of remote sensing classification</atitle><jtitle>Journal of systems engineering and electronics</jtitle><date>2023-02-01</date><risdate>2023</risdate><volume>34</volume><issue>1</issue><spage>36</spage><epage>46</epage><pages>36-46</pages><issn>1004-4132</issn><eissn>1004-4132</eissn><abstract>The development of image classification is one of the most important research topics in remote sensing. The predic-tion accuracy depends not only on the appropriate choice of the machine learning method but also on the quality of the training datasets. However, real-world data is not perfect and often suf-fers from noise. This paper gives an overview of noise filtering methods. Firstly, the types of noise and the consequences of class noise on machine learning are presented. Secondly, class noise handling methods at both the data level and the algorithm level are introduced. Then ensemble-based class noise handling methods including class noise removal, correction, and noise robust ensemble learners are presented. Finally, a summary of existing data-cleaning techniques is given.</abstract><pub>Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an 710071, China</pub><doi>10.23919/JSEE.2023.000034</doi><tpages>11</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1004-4132
ispartof Journal of systems engineering and electronics, 2023-02, Vol.34 (1), p.36-46
issn 1004-4132
1004-4132
language eng
recordid cdi_wanfang_journals_xtgcydzjs_e202301006
source IEEE Xplore All Journals
title A review of addressing class noise problems of remote sensing classification
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T22%3A01%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-wanfang_jour_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20review%20of%20addressing%20class%20noise%20problems%20of%20remote%20sensing%20classification&rft.jtitle=Journal%20of%20systems%20engineering%20and%20electronics&rft.au=Feng,%20Wei&rft.date=2023-02-01&rft.volume=34&rft.issue=1&rft.spage=36&rft.epage=46&rft.pages=36-46&rft.issn=1004-4132&rft.eissn=1004-4132&rft_id=info:doi/10.23919/JSEE.2023.000034&rft_dat=%3Cwanfang_jour_cross%3Extgcydzjs_e202301006%3C/wanfang_jour_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c325t-170cbed006c24610c51bb5e95d4dd3e3298a6bfa258fdb526a795f70fb6a0ad43%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_wanfj_id=xtgcydzjs_e202301006&rfr_iscdi=true