Polychotomous kernel Fisher discriminant via top–down induction of binary tree
In spite of the popularity of Fisher discriminant analysis in the realm of feature extraction and pattern classification, it is beyond the capability of Fisher discriminant analysis to extract nonlinear structures from the data. That is where the kernel Fisher discriminant algorithm sets in the scen...
Gespeichert in:
Veröffentlicht in: | Computers & mathematics with applications (1987) 2010-08, Vol.60 (3), p.511-519 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 519 |
---|---|
container_issue | 3 |
container_start_page | 511 |
container_title | Computers & mathematics with applications (1987) |
container_volume | 60 |
creator | Lu, Zhao Liang, Lily Rui Song, Gangbing Wang, Shufang |
description | In spite of the popularity of Fisher discriminant analysis in the realm of feature extraction and pattern classification, it is beyond the capability of Fisher discriminant analysis to extract nonlinear structures from the data. That is where the kernel Fisher discriminant algorithm sets in the scenario of supervised learning. In this article, a new trail is blazed in developing innovative and effective algorithm for polychotomous kernel Fisher discriminant with the capability in estimating the posterior probabilities, which is exceedingly necessary and significant in solving complex nonlinear pattern recognition problems arising from the real world. Different from the conventional ‘divide-and-combine’ approaches to polychotomous classification problems, such as pairwise and one-versus-others, the method proposed herein synthesizes the multi-category classifier via the induction of top-to-down binary tree by means of kernelized group clustering algorithm. The deficiencies inherited in the conventional multi-category kernel Fisher discriminant are surmounted and the simulation on a benchmark image dataset demonstrates the superiority of the proposed approach. |
doi_str_mv | 10.1016/j.camwa.2010.04.048 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1671238806</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0898122110003305</els_id><sourcerecordid>1671238806</sourcerecordid><originalsourceid>FETCH-LOGICAL-c266t-1071e5e6f13e5448ada9bf840172de31ba289ec275b6167ebd5e93b34969f2233</originalsourceid><addsrcrecordid>eNp9kM1KAzEUhYMoWKtP4CZLN1PzM5PJLFxIsSoU7ELXIZO5Q1NnkppMW7rzHXxDn8TUuhYOXLic73LPQeiakgklVNyuJkb3Oz1hJG1IniRP0IjKkmelEPIUjYisZEYZo-foIsYVISTnjIzQYuG7vVn6wfd-E_E7BAcdntm4hIAbG02wvXXaDXhrNR78-vvzq_E7h61rNmaw3mHf4jpZwh4PAeASnbW6i3D1N8fobfbwOn3K5i-Pz9P7eWaYEENGSUmhANFSDkWeS93oqm5lTmjJGuC01kxWYFhZ1IKKEuqmgIrXPK9E1TLG-RjdHO-ug__YQBxUn76FrtMOUhKVIMq4lEQkKz9aTfAxBmjVOqVKDytK1KE_tVK__alDf4rkSTJRd0cKUoqthaCiseAMNDaAGVTj7b_8D8AJe54</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1671238806</pqid></control><display><type>article</type><title>Polychotomous kernel Fisher discriminant via top–down induction of binary tree</title><source>Access via ScienceDirect (Elsevier)</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Lu, Zhao ; Liang, Lily Rui ; Song, Gangbing ; Wang, Shufang</creator><creatorcontrib>Lu, Zhao ; Liang, Lily Rui ; Song, Gangbing ; Wang, Shufang</creatorcontrib><description>In spite of the popularity of Fisher discriminant analysis in the realm of feature extraction and pattern classification, it is beyond the capability of Fisher discriminant analysis to extract nonlinear structures from the data. That is where the kernel Fisher discriminant algorithm sets in the scenario of supervised learning. In this article, a new trail is blazed in developing innovative and effective algorithm for polychotomous kernel Fisher discriminant with the capability in estimating the posterior probabilities, which is exceedingly necessary and significant in solving complex nonlinear pattern recognition problems arising from the real world. Different from the conventional ‘divide-and-combine’ approaches to polychotomous classification problems, such as pairwise and one-versus-others, the method proposed herein synthesizes the multi-category classifier via the induction of top-to-down binary tree by means of kernelized group clustering algorithm. The deficiencies inherited in the conventional multi-category kernel Fisher discriminant are surmounted and the simulation on a benchmark image dataset demonstrates the superiority of the proposed approach.</description><identifier>ISSN: 0898-1221</identifier><identifier>EISSN: 1873-7668</identifier><identifier>DOI: 10.1016/j.camwa.2010.04.048</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Algorithms ; Binary tree ; Classification ; Computer simulation ; Discriminant analysis ; Kernel Fisher discriminant ; Kernel-induced distance ; Kernelized group clustering ; Kernels ; Mathematical models ; Nonlinearity ; Posterior probability ; Trees</subject><ispartof>Computers & mathematics with applications (1987), 2010-08, Vol.60 (3), p.511-519</ispartof><rights>2010 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c266t-1071e5e6f13e5448ada9bf840172de31ba289ec275b6167ebd5e93b34969f2233</citedby><cites>FETCH-LOGICAL-c266t-1071e5e6f13e5448ada9bf840172de31ba289ec275b6167ebd5e93b34969f2233</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.camwa.2010.04.048$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Lu, Zhao</creatorcontrib><creatorcontrib>Liang, Lily Rui</creatorcontrib><creatorcontrib>Song, Gangbing</creatorcontrib><creatorcontrib>Wang, Shufang</creatorcontrib><title>Polychotomous kernel Fisher discriminant via top–down induction of binary tree</title><title>Computers & mathematics with applications (1987)</title><description>In spite of the popularity of Fisher discriminant analysis in the realm of feature extraction and pattern classification, it is beyond the capability of Fisher discriminant analysis to extract nonlinear structures from the data. That is where the kernel Fisher discriminant algorithm sets in the scenario of supervised learning. In this article, a new trail is blazed in developing innovative and effective algorithm for polychotomous kernel Fisher discriminant with the capability in estimating the posterior probabilities, which is exceedingly necessary and significant in solving complex nonlinear pattern recognition problems arising from the real world. Different from the conventional ‘divide-and-combine’ approaches to polychotomous classification problems, such as pairwise and one-versus-others, the method proposed herein synthesizes the multi-category classifier via the induction of top-to-down binary tree by means of kernelized group clustering algorithm. The deficiencies inherited in the conventional multi-category kernel Fisher discriminant are surmounted and the simulation on a benchmark image dataset demonstrates the superiority of the proposed approach.</description><subject>Algorithms</subject><subject>Binary tree</subject><subject>Classification</subject><subject>Computer simulation</subject><subject>Discriminant analysis</subject><subject>Kernel Fisher discriminant</subject><subject>Kernel-induced distance</subject><subject>Kernelized group clustering</subject><subject>Kernels</subject><subject>Mathematical models</subject><subject>Nonlinearity</subject><subject>Posterior probability</subject><subject>Trees</subject><issn>0898-1221</issn><issn>1873-7668</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2010</creationdate><recordtype>article</recordtype><recordid>eNp9kM1KAzEUhYMoWKtP4CZLN1PzM5PJLFxIsSoU7ELXIZO5Q1NnkppMW7rzHXxDn8TUuhYOXLic73LPQeiakgklVNyuJkb3Oz1hJG1IniRP0IjKkmelEPIUjYisZEYZo-foIsYVISTnjIzQYuG7vVn6wfd-E_E7BAcdntm4hIAbG02wvXXaDXhrNR78-vvzq_E7h61rNmaw3mHf4jpZwh4PAeASnbW6i3D1N8fobfbwOn3K5i-Pz9P7eWaYEENGSUmhANFSDkWeS93oqm5lTmjJGuC01kxWYFhZ1IKKEuqmgIrXPK9E1TLG-RjdHO-ug__YQBxUn76FrtMOUhKVIMq4lEQkKz9aTfAxBmjVOqVKDytK1KE_tVK__alDf4rkSTJRd0cKUoqthaCiseAMNDaAGVTj7b_8D8AJe54</recordid><startdate>20100801</startdate><enddate>20100801</enddate><creator>Lu, Zhao</creator><creator>Liang, Lily Rui</creator><creator>Song, Gangbing</creator><creator>Wang, Shufang</creator><general>Elsevier Ltd</general><scope>6I.</scope><scope>AAFTH</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20100801</creationdate><title>Polychotomous kernel Fisher discriminant via top–down induction of binary tree</title><author>Lu, Zhao ; Liang, Lily Rui ; Song, Gangbing ; Wang, Shufang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c266t-1071e5e6f13e5448ada9bf840172de31ba289ec275b6167ebd5e93b34969f2233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Algorithms</topic><topic>Binary tree</topic><topic>Classification</topic><topic>Computer simulation</topic><topic>Discriminant analysis</topic><topic>Kernel Fisher discriminant</topic><topic>Kernel-induced distance</topic><topic>Kernelized group clustering</topic><topic>Kernels</topic><topic>Mathematical models</topic><topic>Nonlinearity</topic><topic>Posterior probability</topic><topic>Trees</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lu, Zhao</creatorcontrib><creatorcontrib>Liang, Lily Rui</creatorcontrib><creatorcontrib>Song, Gangbing</creatorcontrib><creatorcontrib>Wang, Shufang</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Computers & mathematics with applications (1987)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lu, Zhao</au><au>Liang, Lily Rui</au><au>Song, Gangbing</au><au>Wang, Shufang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Polychotomous kernel Fisher discriminant via top–down induction of binary tree</atitle><jtitle>Computers & mathematics with applications (1987)</jtitle><date>2010-08-01</date><risdate>2010</risdate><volume>60</volume><issue>3</issue><spage>511</spage><epage>519</epage><pages>511-519</pages><issn>0898-1221</issn><eissn>1873-7668</eissn><abstract>In spite of the popularity of Fisher discriminant analysis in the realm of feature extraction and pattern classification, it is beyond the capability of Fisher discriminant analysis to extract nonlinear structures from the data. That is where the kernel Fisher discriminant algorithm sets in the scenario of supervised learning. In this article, a new trail is blazed in developing innovative and effective algorithm for polychotomous kernel Fisher discriminant with the capability in estimating the posterior probabilities, which is exceedingly necessary and significant in solving complex nonlinear pattern recognition problems arising from the real world. Different from the conventional ‘divide-and-combine’ approaches to polychotomous classification problems, such as pairwise and one-versus-others, the method proposed herein synthesizes the multi-category classifier via the induction of top-to-down binary tree by means of kernelized group clustering algorithm. The deficiencies inherited in the conventional multi-category kernel Fisher discriminant are surmounted and the simulation on a benchmark image dataset demonstrates the superiority of the proposed approach.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.camwa.2010.04.048</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0898-1221 |
ispartof | Computers & mathematics with applications (1987), 2010-08, Vol.60 (3), p.511-519 |
issn | 0898-1221 1873-7668 |
language | eng |
recordid | cdi_proquest_miscellaneous_1671238806 |
source | Access via ScienceDirect (Elsevier); EZB-FREE-00999 freely available EZB journals |
subjects | Algorithms Binary tree Classification Computer simulation Discriminant analysis Kernel Fisher discriminant Kernel-induced distance Kernelized group clustering Kernels Mathematical models Nonlinearity Posterior probability Trees |
title | Polychotomous kernel Fisher discriminant via top–down induction of binary tree |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T03%3A59%3A09IST&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=Polychotomous%20kernel%20Fisher%20discriminant%20via%20top%E2%80%93down%20induction%20of%20binary%20tree&rft.jtitle=Computers%20&%20mathematics%20with%20applications%20(1987)&rft.au=Lu,%20Zhao&rft.date=2010-08-01&rft.volume=60&rft.issue=3&rft.spage=511&rft.epage=519&rft.pages=511-519&rft.issn=0898-1221&rft.eissn=1873-7668&rft_id=info:doi/10.1016/j.camwa.2010.04.048&rft_dat=%3Cproquest_cross%3E1671238806%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=1671238806&rft_id=info:pmid/&rft_els_id=S0898122110003305&rfr_iscdi=true |