A Weakly Supervised Method for Mud Detection in Ores Based on Deep Active Learning
Automatically detecting mud in bauxite ores is important and valuable, with which we can improve productivity and reduce pollution. However, distinguishing mud and ores in a real scene is challenging for their similarity in shape, color, and texture. Moreover, training a deep learning model needs a...
Gespeichert in:
Veröffentlicht in: | Mathematical problems in engineering 2020, Vol.2020 (2020), p.1-10 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 10 |
---|---|
container_issue | 2020 |
container_start_page | 1 |
container_title | Mathematical problems in engineering |
container_volume | 2020 |
creator | Cai, Zuowei Luan, Xidao Li, Fangmin Huang, Zhijian |
description | Automatically detecting mud in bauxite ores is important and valuable, with which we can improve productivity and reduce pollution. However, distinguishing mud and ores in a real scene is challenging for their similarity in shape, color, and texture. Moreover, training a deep learning model needs a large amount of exactly labeled samples, which is expensive and time consuming. Aiming at the challenging problem, this paper proposed a novel weakly supervised method based on deep active learning (AL), named YOLO-AL. The method uses the YOLO-v3 model as the basic detector, which is initialized with the pretrained weights on the MS COCO dataset. Then, an AL framework-embedded YOLO-v3 model is constructed. In the AL process, it iteratively fine-tunes the last few layers of the YOLO-v3 model with the most valuable samples, which is selected by a Less Confident (LC) strategy. Experimental results show that the proposed method can effectively detect mud in ores. More importantly, the proposed method can obviously reduce the labeled samples without decreasing the detection accuracy. |
doi_str_mv | 10.1155/2020/3510313 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2410091367</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2410091367</sourcerecordid><originalsourceid>FETCH-LOGICAL-c360t-82c88d0bee59e1bd3243cdd3244d6b83ecfeeaa73b5189214413f713ccd588563</originalsourceid><addsrcrecordid>eNqF0M9LwzAUB_AgCs7pzbMEPGpdXn603XFu_oKNgT_QW0mTV9c525q2k_33plTw6OmF5MPLe19CToFdASg14oyzkVDABIg9MgAVikCBjPb9mXEZABdvh-SorteMcVAQD8jjhL6i_tjs6FNbodvmNVq6wGZVWpqVji5aS2fYoGnysqB5QZcOa3qtO-YvZogVnfjHLdI5alfkxfsxOcj0psaT3zokL7c3z9P7YL68e5hO5oERIWuCmJs4tixFVGOE1AouhbFdkTZMY4EmQ9Q6EqkfdMxBShBZBMIYq-LYrzYk533fypVfLdZNsi5bV_gvEy6BsTGIMPLqslfGlXXtMEsql39qt0uAJV1qSZda8pua5xc9X-WF1d_5f_qs1-gNZvpPw1hKxcUPlaZ0Fw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2410091367</pqid></control><display><type>article</type><title>A Weakly Supervised Method for Mud Detection in Ores Based on Deep Active Learning</title><source>Wiley Online Library Open Access</source><source>EZB-FREE-00999 freely available EZB journals</source><source>Alma/SFX Local Collection</source><creator>Cai, Zuowei ; Luan, Xidao ; Li, Fangmin ; Huang, Zhijian</creator><contributor>Han, Chunjia ; Chunjia Han</contributor><creatorcontrib>Cai, Zuowei ; Luan, Xidao ; Li, Fangmin ; Huang, Zhijian ; Han, Chunjia ; Chunjia Han</creatorcontrib><description>Automatically detecting mud in bauxite ores is important and valuable, with which we can improve productivity and reduce pollution. However, distinguishing mud and ores in a real scene is challenging for their similarity in shape, color, and texture. Moreover, training a deep learning model needs a large amount of exactly labeled samples, which is expensive and time consuming. Aiming at the challenging problem, this paper proposed a novel weakly supervised method based on deep active learning (AL), named YOLO-AL. The method uses the YOLO-v3 model as the basic detector, which is initialized with the pretrained weights on the MS COCO dataset. Then, an AL framework-embedded YOLO-v3 model is constructed. In the AL process, it iteratively fine-tunes the last few layers of the YOLO-v3 model with the most valuable samples, which is selected by a Less Confident (LC) strategy. Experimental results show that the proposed method can effectively detect mud in ores. More importantly, the proposed method can obviously reduce the labeled samples without decreasing the detection accuracy.</description><identifier>ISSN: 1024-123X</identifier><identifier>EISSN: 1563-5147</identifier><identifier>DOI: 10.1155/2020/3510313</identifier><language>eng</language><publisher>Cairo, Egypt: Hindawi Publishing Corporation</publisher><subject>Active learning ; Bauxite ; Bayer process ; Confidence ; Datasets ; Labeling ; Machine learning ; Minerals ; Mines ; Mud ; Neural networks ; Remote sensing ; Sensors ; Teaching methods</subject><ispartof>Mathematical problems in engineering, 2020, Vol.2020 (2020), p.1-10</ispartof><rights>Copyright © 2020 Zhijian Huang et al.</rights><rights>Copyright © 2020 Zhijian Huang et al. This is an open access article distributed under the Creative Commons Attribution License (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. http://creativecommons.org/licenses/by/4.0</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c360t-82c88d0bee59e1bd3243cdd3244d6b83ecfeeaa73b5189214413f713ccd588563</citedby><cites>FETCH-LOGICAL-c360t-82c88d0bee59e1bd3243cdd3244d6b83ecfeeaa73b5189214413f713ccd588563</cites><orcidid>0000-0002-8612-1756 ; 0000-0003-4470-7107 ; 0000-0002-5476-1767 ; 0000-0002-7948-425X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,4024,27923,27924,27925</link.rule.ids></links><search><contributor>Han, Chunjia</contributor><contributor>Chunjia Han</contributor><creatorcontrib>Cai, Zuowei</creatorcontrib><creatorcontrib>Luan, Xidao</creatorcontrib><creatorcontrib>Li, Fangmin</creatorcontrib><creatorcontrib>Huang, Zhijian</creatorcontrib><title>A Weakly Supervised Method for Mud Detection in Ores Based on Deep Active Learning</title><title>Mathematical problems in engineering</title><description>Automatically detecting mud in bauxite ores is important and valuable, with which we can improve productivity and reduce pollution. However, distinguishing mud and ores in a real scene is challenging for their similarity in shape, color, and texture. Moreover, training a deep learning model needs a large amount of exactly labeled samples, which is expensive and time consuming. Aiming at the challenging problem, this paper proposed a novel weakly supervised method based on deep active learning (AL), named YOLO-AL. The method uses the YOLO-v3 model as the basic detector, which is initialized with the pretrained weights on the MS COCO dataset. Then, an AL framework-embedded YOLO-v3 model is constructed. In the AL process, it iteratively fine-tunes the last few layers of the YOLO-v3 model with the most valuable samples, which is selected by a Less Confident (LC) strategy. Experimental results show that the proposed method can effectively detect mud in ores. More importantly, the proposed method can obviously reduce the labeled samples without decreasing the detection accuracy.</description><subject>Active learning</subject><subject>Bauxite</subject><subject>Bayer process</subject><subject>Confidence</subject><subject>Datasets</subject><subject>Labeling</subject><subject>Machine learning</subject><subject>Minerals</subject><subject>Mines</subject><subject>Mud</subject><subject>Neural networks</subject><subject>Remote sensing</subject><subject>Sensors</subject><subject>Teaching methods</subject><issn>1024-123X</issn><issn>1563-5147</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>RHX</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNqF0M9LwzAUB_AgCs7pzbMEPGpdXn603XFu_oKNgT_QW0mTV9c525q2k_33plTw6OmF5MPLe19CToFdASg14oyzkVDABIg9MgAVikCBjPb9mXEZABdvh-SorteMcVAQD8jjhL6i_tjs6FNbodvmNVq6wGZVWpqVji5aS2fYoGnysqB5QZcOa3qtO-YvZogVnfjHLdI5alfkxfsxOcj0psaT3zokL7c3z9P7YL68e5hO5oERIWuCmJs4tixFVGOE1AouhbFdkTZMY4EmQ9Q6EqkfdMxBShBZBMIYq-LYrzYk533fypVfLdZNsi5bV_gvEy6BsTGIMPLqslfGlXXtMEsql39qt0uAJV1qSZda8pua5xc9X-WF1d_5f_qs1-gNZvpPw1hKxcUPlaZ0Fw</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>Cai, Zuowei</creator><creator>Luan, Xidao</creator><creator>Li, Fangmin</creator><creator>Huang, Zhijian</creator><general>Hindawi Publishing Corporation</general><general>Hindawi</general><general>Hindawi Limited</general><scope>ADJCN</scope><scope>AHFXO</scope><scope>RHU</scope><scope>RHW</scope><scope>RHX</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7TB</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>CWDGH</scope><scope>DWQXO</scope><scope>FR3</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>KR7</scope><scope>L6V</scope><scope>M7S</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><orcidid>https://orcid.org/0000-0002-8612-1756</orcidid><orcidid>https://orcid.org/0000-0003-4470-7107</orcidid><orcidid>https://orcid.org/0000-0002-5476-1767</orcidid><orcidid>https://orcid.org/0000-0002-7948-425X</orcidid></search><sort><creationdate>2020</creationdate><title>A Weakly Supervised Method for Mud Detection in Ores Based on Deep Active Learning</title><author>Cai, Zuowei ; Luan, Xidao ; Li, Fangmin ; Huang, Zhijian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c360t-82c88d0bee59e1bd3243cdd3244d6b83ecfeeaa73b5189214413f713ccd588563</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Active learning</topic><topic>Bauxite</topic><topic>Bayer process</topic><topic>Confidence</topic><topic>Datasets</topic><topic>Labeling</topic><topic>Machine learning</topic><topic>Minerals</topic><topic>Mines</topic><topic>Mud</topic><topic>Neural networks</topic><topic>Remote sensing</topic><topic>Sensors</topic><topic>Teaching methods</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cai, Zuowei</creatorcontrib><creatorcontrib>Luan, Xidao</creatorcontrib><creatorcontrib>Li, Fangmin</creatorcontrib><creatorcontrib>Huang, Zhijian</creatorcontrib><collection>الدوريات العلمية والإحصائية - e-Marefa Academic and Statistical Periodicals</collection><collection>معرفة - المحتوى العربي الأكاديمي المتكامل - e-Marefa Academic Complete</collection><collection>Hindawi Publishing Complete</collection><collection>Hindawi Publishing Subscription Journals</collection><collection>Hindawi Publishing Open Access Journals</collection><collection>CrossRef</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>Middle East & Africa Database</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Civil Engineering Abstracts</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><jtitle>Mathematical problems in engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cai, Zuowei</au><au>Luan, Xidao</au><au>Li, Fangmin</au><au>Huang, Zhijian</au><au>Han, Chunjia</au><au>Chunjia Han</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Weakly Supervised Method for Mud Detection in Ores Based on Deep Active Learning</atitle><jtitle>Mathematical problems in engineering</jtitle><date>2020</date><risdate>2020</risdate><volume>2020</volume><issue>2020</issue><spage>1</spage><epage>10</epage><pages>1-10</pages><issn>1024-123X</issn><eissn>1563-5147</eissn><abstract>Automatically detecting mud in bauxite ores is important and valuable, with which we can improve productivity and reduce pollution. However, distinguishing mud and ores in a real scene is challenging for their similarity in shape, color, and texture. Moreover, training a deep learning model needs a large amount of exactly labeled samples, which is expensive and time consuming. Aiming at the challenging problem, this paper proposed a novel weakly supervised method based on deep active learning (AL), named YOLO-AL. The method uses the YOLO-v3 model as the basic detector, which is initialized with the pretrained weights on the MS COCO dataset. Then, an AL framework-embedded YOLO-v3 model is constructed. In the AL process, it iteratively fine-tunes the last few layers of the YOLO-v3 model with the most valuable samples, which is selected by a Less Confident (LC) strategy. Experimental results show that the proposed method can effectively detect mud in ores. More importantly, the proposed method can obviously reduce the labeled samples without decreasing the detection accuracy.</abstract><cop>Cairo, Egypt</cop><pub>Hindawi Publishing Corporation</pub><doi>10.1155/2020/3510313</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0002-8612-1756</orcidid><orcidid>https://orcid.org/0000-0003-4470-7107</orcidid><orcidid>https://orcid.org/0000-0002-5476-1767</orcidid><orcidid>https://orcid.org/0000-0002-7948-425X</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1024-123X |
ispartof | Mathematical problems in engineering, 2020, Vol.2020 (2020), p.1-10 |
issn | 1024-123X 1563-5147 |
language | eng |
recordid | cdi_proquest_journals_2410091367 |
source | Wiley Online Library Open Access; EZB-FREE-00999 freely available EZB journals; Alma/SFX Local Collection |
subjects | Active learning Bauxite Bayer process Confidence Datasets Labeling Machine learning Minerals Mines Mud Neural networks Remote sensing Sensors Teaching methods |
title | A Weakly Supervised Method for Mud Detection in Ores Based on Deep Active Learning |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T06%3A44%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Weakly%20Supervised%20Method%20for%20Mud%20Detection%20in%20Ores%20Based%20on%20Deep%20Active%20Learning&rft.jtitle=Mathematical%20problems%20in%20engineering&rft.au=Cai,%20Zuowei&rft.date=2020&rft.volume=2020&rft.issue=2020&rft.spage=1&rft.epage=10&rft.pages=1-10&rft.issn=1024-123X&rft.eissn=1563-5147&rft_id=info:doi/10.1155/2020/3510313&rft_dat=%3Cproquest_cross%3E2410091367%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2410091367&rft_id=info:pmid/&rfr_iscdi=true |