Genetic evolution processing of data structures for image classification
This paper describes a method of structural pattern recognition based on a genetic evolution processing of data structures with neural networks representation. Conventionally, one of the most popular learning formulations of data structure processing is backpropagation through structures (BPTS) [C....
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on knowledge and data engineering 2005-02, Vol.17 (2), p.216-231 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 231 |
|---|---|
| container_issue | 2 |
| container_start_page | 216 |
| container_title | IEEE transactions on knowledge and data engineering |
| container_volume | 17 |
| creator | Cho, Siu-Yeung Chi, Zheru |
| description | This paper describes a method of structural pattern recognition based on a genetic evolution processing of data structures with neural networks representation. Conventionally, one of the most popular learning formulations of data structure processing is backpropagation through structures (BPTS) [C. Goller et al., (1996)]. The BPTS algorithm has been successfully applied to a number of learning tasks that involved structural patterns such as image, shape, and texture classifications. However, this BPTS typed algorithm suffers from the long-term dependency problem in learning very deep tree structures. In this paper, we propose the genetic evolution for this data structures processing. The idea of this algorithm is to tune the learning parameters by the genetic evolution with specified chromosome structures. Also, the fitness evaluation as well as the adaptive crossover and mutation for this structural genetic processing are investigated in this paper. An application to flowers image classification by a structural representation is provided for the validation of our method. The obtained results significantly support the capabilities of our proposed approach to classify and recognize flowers in terms of generalization and noise robustness. |
| doi_str_mv | 10.1109/TKDE.2005.28 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_912075852</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1377173</ieee_id><sourcerecordid>896176024</sourcerecordid><originalsourceid>FETCH-LOGICAL-c406t-323eddb4f8a8952a52ebed5b820fcc0625de0537b8912a540fca0a087620faf53</originalsourceid><addsrcrecordid>eNqFkc1LxDAQxYsoqKs3b16CoF7sOkmbJjmKXysueNFzSdOJdOm2mrSC_71TVhA86GnCzG8eb_KS5IjDnHMwl8-PN7dzASDnQm8le1xKnQpu-Da9IedpnuVqN9mPcQUAWmm-lyzuscOhcQw_-nYcmr5jb6F3GGPTvbLes9oOlsUhjG4YA0bm-8CatX1F5lpLlG-cndYOkh1v24iH33WWvNzdPl8v0uXT_cP11TJ1ORRDmokM67rKvbbaSGGlwAprWWkB3jkohKwRZKYqbThNc-pasGS2IMB6mc2S840u2XwfMQ7luokO29Z22I-x1KbgqgCRE3n2JymMUFwJ8z-oQSiSJfDkF7jqx9DRuSW5BSW1FARdbCAX-hgD-vIt0IeFz5JDOcVUTjGVU0ykTPjpt6aNzrY-2M418WenyKXhZpI93nANIv6MM0U3ZNkX02qaKw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>912075852</pqid></control><display><type>article</type><title>Genetic evolution processing of data structures for image classification</title><source>IEEE Electronic Library (IEL)</source><creator>Cho, Siu-Yeung ; Chi, Zheru</creator><creatorcontrib>Cho, Siu-Yeung ; Chi, Zheru</creatorcontrib><description>This paper describes a method of structural pattern recognition based on a genetic evolution processing of data structures with neural networks representation. Conventionally, one of the most popular learning formulations of data structure processing is backpropagation through structures (BPTS) [C. Goller et al., (1996)]. The BPTS algorithm has been successfully applied to a number of learning tasks that involved structural patterns such as image, shape, and texture classifications. However, this BPTS typed algorithm suffers from the long-term dependency problem in learning very deep tree structures. In this paper, we propose the genetic evolution for this data structures processing. The idea of this algorithm is to tune the learning parameters by the genetic evolution with specified chromosome structures. Also, the fitness evaluation as well as the adaptive crossover and mutation for this structural genetic processing are investigated in this paper. An application to flowers image classification by a structural representation is provided for the validation of our method. The obtained results significantly support the capabilities of our proposed approach to classify and recognize flowers in terms of generalization and noise robustness.</description><identifier>ISSN: 1041-4347</identifier><identifier>EISSN: 1558-2191</identifier><identifier>DOI: 10.1109/TKDE.2005.28</identifier><identifier>CODEN: ITKEEH</identifier><language>eng</language><publisher>New York, NY: IEEE</publisher><subject>Algorithms ; and neural networks ; Applied sciences ; Artificial intelligence ; Backpropagation algorithms ; Biological cells ; Computer science; control theory; systems ; Data structures ; Evolution ; Evolution & development ; Exact sciences and technology ; genetic algorithm ; Genetic mutations ; Genetics ; Image classification ; Index Terms- Adaptive processing of data structures ; Information systems. Data bases ; Learning ; Memory organisation. Data processing ; Neural networks ; Noise robustness ; Pattern recognition ; Pattern recognition. Digital image processing. Computational geometry ; Representations ; Shape ; Software ; Studies ; Texture ; Tree data structures</subject><ispartof>IEEE transactions on knowledge and data engineering, 2005-02, Vol.17 (2), p.216-231</ispartof><rights>2005 INIST-CNRS</rights><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2005</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c406t-323eddb4f8a8952a52ebed5b820fcc0625de0537b8912a540fca0a087620faf53</citedby><cites>FETCH-LOGICAL-c406t-323eddb4f8a8952a52ebed5b820fcc0625de0537b8912a540fca0a087620faf53</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1377173$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1377173$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=16459192$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Cho, Siu-Yeung</creatorcontrib><creatorcontrib>Chi, Zheru</creatorcontrib><title>Genetic evolution processing of data structures for image classification</title><title>IEEE transactions on knowledge and data engineering</title><addtitle>TKDE</addtitle><description>This paper describes a method of structural pattern recognition based on a genetic evolution processing of data structures with neural networks representation. Conventionally, one of the most popular learning formulations of data structure processing is backpropagation through structures (BPTS) [C. Goller et al., (1996)]. The BPTS algorithm has been successfully applied to a number of learning tasks that involved structural patterns such as image, shape, and texture classifications. However, this BPTS typed algorithm suffers from the long-term dependency problem in learning very deep tree structures. In this paper, we propose the genetic evolution for this data structures processing. The idea of this algorithm is to tune the learning parameters by the genetic evolution with specified chromosome structures. Also, the fitness evaluation as well as the adaptive crossover and mutation for this structural genetic processing are investigated in this paper. An application to flowers image classification by a structural representation is provided for the validation of our method. The obtained results significantly support the capabilities of our proposed approach to classify and recognize flowers in terms of generalization and noise robustness.</description><subject>Algorithms</subject><subject>and neural networks</subject><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Backpropagation algorithms</subject><subject>Biological cells</subject><subject>Computer science; control theory; systems</subject><subject>Data structures</subject><subject>Evolution</subject><subject>Evolution & development</subject><subject>Exact sciences and technology</subject><subject>genetic algorithm</subject><subject>Genetic mutations</subject><subject>Genetics</subject><subject>Image classification</subject><subject>Index Terms- Adaptive processing of data structures</subject><subject>Information systems. Data bases</subject><subject>Learning</subject><subject>Memory organisation. Data processing</subject><subject>Neural networks</subject><subject>Noise robustness</subject><subject>Pattern recognition</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Representations</subject><subject>Shape</subject><subject>Software</subject><subject>Studies</subject><subject>Texture</subject><subject>Tree data structures</subject><issn>1041-4347</issn><issn>1558-2191</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2005</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNqFkc1LxDAQxYsoqKs3b16CoF7sOkmbJjmKXysueNFzSdOJdOm2mrSC_71TVhA86GnCzG8eb_KS5IjDnHMwl8-PN7dzASDnQm8le1xKnQpu-Da9IedpnuVqN9mPcQUAWmm-lyzuscOhcQw_-nYcmr5jb6F3GGPTvbLes9oOlsUhjG4YA0bm-8CatX1F5lpLlG-cndYOkh1v24iH33WWvNzdPl8v0uXT_cP11TJ1ORRDmokM67rKvbbaSGGlwAprWWkB3jkohKwRZKYqbThNc-pasGS2IMB6mc2S840u2XwfMQ7luokO29Z22I-x1KbgqgCRE3n2JymMUFwJ8z-oQSiSJfDkF7jqx9DRuSW5BSW1FARdbCAX-hgD-vIt0IeFz5JDOcVUTjGVU0ykTPjpt6aNzrY-2M418WenyKXhZpI93nANIv6MM0U3ZNkX02qaKw</recordid><startdate>20050201</startdate><enddate>20050201</enddate><creator>Cho, Siu-Yeung</creator><creator>Chi, Zheru</creator><general>IEEE</general><general>IEEE Computer Society</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7TB</scope><scope>FR3</scope><scope>F28</scope></search><sort><creationdate>20050201</creationdate><title>Genetic evolution processing of data structures for image classification</title><author>Cho, Siu-Yeung ; Chi, Zheru</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c406t-323eddb4f8a8952a52ebed5b820fcc0625de0537b8912a540fca0a087620faf53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Algorithms</topic><topic>and neural networks</topic><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Backpropagation algorithms</topic><topic>Biological cells</topic><topic>Computer science; control theory; systems</topic><topic>Data structures</topic><topic>Evolution</topic><topic>Evolution & development</topic><topic>Exact sciences and technology</topic><topic>genetic algorithm</topic><topic>Genetic mutations</topic><topic>Genetics</topic><topic>Image classification</topic><topic>Index Terms- Adaptive processing of data structures</topic><topic>Information systems. Data bases</topic><topic>Learning</topic><topic>Memory organisation. Data processing</topic><topic>Neural networks</topic><topic>Noise robustness</topic><topic>Pattern recognition</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Representations</topic><topic>Shape</topic><topic>Software</topic><topic>Studies</topic><topic>Texture</topic><topic>Tree data structures</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cho, Siu-Yeung</creatorcontrib><creatorcontrib>Chi, Zheru</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Engineering Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><jtitle>IEEE transactions on knowledge and data engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Cho, Siu-Yeung</au><au>Chi, Zheru</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Genetic evolution processing of data structures for image classification</atitle><jtitle>IEEE transactions on knowledge and data engineering</jtitle><stitle>TKDE</stitle><date>2005-02-01</date><risdate>2005</risdate><volume>17</volume><issue>2</issue><spage>216</spage><epage>231</epage><pages>216-231</pages><issn>1041-4347</issn><eissn>1558-2191</eissn><coden>ITKEEH</coden><abstract>This paper describes a method of structural pattern recognition based on a genetic evolution processing of data structures with neural networks representation. Conventionally, one of the most popular learning formulations of data structure processing is backpropagation through structures (BPTS) [C. Goller et al., (1996)]. The BPTS algorithm has been successfully applied to a number of learning tasks that involved structural patterns such as image, shape, and texture classifications. However, this BPTS typed algorithm suffers from the long-term dependency problem in learning very deep tree structures. In this paper, we propose the genetic evolution for this data structures processing. The idea of this algorithm is to tune the learning parameters by the genetic evolution with specified chromosome structures. Also, the fitness evaluation as well as the adaptive crossover and mutation for this structural genetic processing are investigated in this paper. An application to flowers image classification by a structural representation is provided for the validation of our method. The obtained results significantly support the capabilities of our proposed approach to classify and recognize flowers in terms of generalization and noise robustness.</abstract><cop>New York, NY</cop><pub>IEEE</pub><doi>10.1109/TKDE.2005.28</doi><tpages>16</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1041-4347 |
| ispartof | IEEE transactions on knowledge and data engineering, 2005-02, Vol.17 (2), p.216-231 |
| issn | 1041-4347 1558-2191 |
| language | eng |
| recordid | cdi_proquest_journals_912075852 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms and neural networks Applied sciences Artificial intelligence Backpropagation algorithms Biological cells Computer science control theory systems Data structures Evolution Evolution & development Exact sciences and technology genetic algorithm Genetic mutations Genetics Image classification Index Terms- Adaptive processing of data structures Information systems. Data bases Learning Memory organisation. Data processing Neural networks Noise robustness Pattern recognition Pattern recognition. Digital image processing. Computational geometry Representations Shape Software Studies Texture Tree data structures |
| title | Genetic evolution processing of data structures for image classification |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T08%3A03%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Genetic%20evolution%20processing%20of%20data%20structures%20for%20image%20classification&rft.jtitle=IEEE%20transactions%20on%20knowledge%20and%20data%20engineering&rft.au=Cho,%20Siu-Yeung&rft.date=2005-02-01&rft.volume=17&rft.issue=2&rft.spage=216&rft.epage=231&rft.pages=216-231&rft.issn=1041-4347&rft.eissn=1558-2191&rft.coden=ITKEEH&rft_id=info:doi/10.1109/TKDE.2005.28&rft_dat=%3Cproquest_RIE%3E896176024%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=912075852&rft_id=info:pmid/&rft_ieee_id=1377173&rfr_iscdi=true |