Loading…
Classifying real-world data with the DDα-procedure
The D D α -classifier, a nonparametric fast and very robust procedure, is described and applied to fifty classification problems regarding a broad spectrum of real-world data. The procedure first transforms the data from their original property space into a depth space, which is a low-dimensional un...
Saved in:
| Published in: | Advances in data analysis and classification 2015-09, Vol.9 (3), p.287-314 |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 314 |
| container_issue | 3 |
| container_start_page | 287 |
| container_title | Advances in data analysis and classification |
| container_volume | 9 |
| creator | Mozharovskyi, Pavlo Mosler, Karl Lange, Tatjana |
| description | The
D
D
α
-classifier, a nonparametric fast and very robust procedure, is described and applied to fifty classification problems regarding a broad spectrum of real-world data. The procedure first transforms the data from their original property space into a depth space, which is a low-dimensional unit cube, and then separates them by a projective invariant procedure, called
α
-procedure. To each data point the transformation assigns its depth values with respect to the given classes. Several alternative depth notions (spatial depth, Mahalanobis depth, projection depth, and Tukey depth, the latter two being approximated by univariate projections) are used in the procedure, and compared regarding their average error rates. With the Tukey depth, which fits the distributions’ shape best and is most robust, ‘outsiders’, that is data points having zero depth in all classes, appear. They need an additional treatment for classification. Evidence is also given about the dimension of the extended feature space needed for linear separation. The
D
D
α
-procedure is available as an R-package. |
| doi_str_mv | 10.1007/s11634-014-0180-8 |
| format | article |
| fullrecord | <record><control><sourceid>springer</sourceid><recordid>TN_cdi_springer_journals_10_1007_s11634_014_0180_8</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1007_s11634_014_0180_8</sourcerecordid><originalsourceid>FETCH-LOGICAL-s198t-f774785134bb00c362240a1c45f069401ae580567386ffee0b2431e4cca816053</originalsourceid><addsrcrecordid>eNo9j0tOwzAYhC0EEqVwAHa-gOH__e4SpbykSmxgbTmOTVNFTWWnqnqsXoQzkaiIxWhmNTMfIfcIDwhgHguiFpIBTrLA7AWZodWcKaHU5X-W5prclLIB0CBBzYioOl9Km47t9pvm6Dt26HPX0MYPnh7aYU2HdaTL5c-J7XIfYrPP8ZZcJd-VePfnc_L18vxZvbHVx-t79bRiBRd2YMkYaaxCIesaIAjNuQSPQaoEeiEBfVQWlDbC6pRihJpLgVGG4C1qUGJO-Lm37PJ4L2a36fd5O046BDdhuzO2G7HdhO2s-AXoQUnI</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Classifying real-world data with the DDα-procedure</title><source>Springer Nature</source><creator>Mozharovskyi, Pavlo ; Mosler, Karl ; Lange, Tatjana</creator><creatorcontrib>Mozharovskyi, Pavlo ; Mosler, Karl ; Lange, Tatjana</creatorcontrib><description>The
D
D
α
-classifier, a nonparametric fast and very robust procedure, is described and applied to fifty classification problems regarding a broad spectrum of real-world data. The procedure first transforms the data from their original property space into a depth space, which is a low-dimensional unit cube, and then separates them by a projective invariant procedure, called
α
-procedure. To each data point the transformation assigns its depth values with respect to the given classes. Several alternative depth notions (spatial depth, Mahalanobis depth, projection depth, and Tukey depth, the latter two being approximated by univariate projections) are used in the procedure, and compared regarding their average error rates. With the Tukey depth, which fits the distributions’ shape best and is most robust, ‘outsiders’, that is data points having zero depth in all classes, appear. They need an additional treatment for classification. Evidence is also given about the dimension of the extended feature space needed for linear separation. The
D
D
α
-procedure is available as an R-package.</description><identifier>ISSN: 1862-5347</identifier><identifier>EISSN: 1862-5355</identifier><identifier>DOI: 10.1007/s11634-014-0180-8</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Chemistry and Earth Sciences ; Computer Science ; Data Mining and Knowledge Discovery ; Economics ; Finance ; Health Sciences ; Humanities ; Insurance ; Law ; Management ; Mathematics and Statistics ; Medicine ; Physics ; Regular Article ; Statistical Theory and Methods ; Statistics ; Statistics for Business ; Statistics for Engineering ; Statistics for Life Sciences ; Statistics for Social Sciences</subject><ispartof>Advances in data analysis and classification, 2015-09, Vol.9 (3), p.287-314</ispartof><rights>Springer-Verlag Berlin Heidelberg 2014</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Mozharovskyi, Pavlo</creatorcontrib><creatorcontrib>Mosler, Karl</creatorcontrib><creatorcontrib>Lange, Tatjana</creatorcontrib><title>Classifying real-world data with the DDα-procedure</title><title>Advances in data analysis and classification</title><addtitle>Adv Data Anal Classif</addtitle><description>The
D
D
α
-classifier, a nonparametric fast and very robust procedure, is described and applied to fifty classification problems regarding a broad spectrum of real-world data. The procedure first transforms the data from their original property space into a depth space, which is a low-dimensional unit cube, and then separates them by a projective invariant procedure, called
α
-procedure. To each data point the transformation assigns its depth values with respect to the given classes. Several alternative depth notions (spatial depth, Mahalanobis depth, projection depth, and Tukey depth, the latter two being approximated by univariate projections) are used in the procedure, and compared regarding their average error rates. With the Tukey depth, which fits the distributions’ shape best and is most robust, ‘outsiders’, that is data points having zero depth in all classes, appear. They need an additional treatment for classification. Evidence is also given about the dimension of the extended feature space needed for linear separation. The
D
D
α
-procedure is available as an R-package.</description><subject>Chemistry and Earth Sciences</subject><subject>Computer Science</subject><subject>Data Mining and Knowledge Discovery</subject><subject>Economics</subject><subject>Finance</subject><subject>Health Sciences</subject><subject>Humanities</subject><subject>Insurance</subject><subject>Law</subject><subject>Management</subject><subject>Mathematics and Statistics</subject><subject>Medicine</subject><subject>Physics</subject><subject>Regular Article</subject><subject>Statistical Theory and Methods</subject><subject>Statistics</subject><subject>Statistics for Business</subject><subject>Statistics for Engineering</subject><subject>Statistics for Life Sciences</subject><subject>Statistics for Social Sciences</subject><issn>1862-5347</issn><issn>1862-5355</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><sourceid/><recordid>eNo9j0tOwzAYhC0EEqVwAHa-gOH__e4SpbykSmxgbTmOTVNFTWWnqnqsXoQzkaiIxWhmNTMfIfcIDwhgHguiFpIBTrLA7AWZodWcKaHU5X-W5prclLIB0CBBzYioOl9Km47t9pvm6Dt26HPX0MYPnh7aYU2HdaTL5c-J7XIfYrPP8ZZcJd-VePfnc_L18vxZvbHVx-t79bRiBRd2YMkYaaxCIesaIAjNuQSPQaoEeiEBfVQWlDbC6pRihJpLgVGG4C1qUGJO-Lm37PJ4L2a36fd5O046BDdhuzO2G7HdhO2s-AXoQUnI</recordid><startdate>20150902</startdate><enddate>20150902</enddate><creator>Mozharovskyi, Pavlo</creator><creator>Mosler, Karl</creator><creator>Lange, Tatjana</creator><general>Springer Berlin Heidelberg</general><scope/></search><sort><creationdate>20150902</creationdate><title>Classifying real-world data with the DDα-procedure</title><author>Mozharovskyi, Pavlo ; Mosler, Karl ; Lange, Tatjana</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-s198t-f774785134bb00c362240a1c45f069401ae580567386ffee0b2431e4cca816053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Chemistry and Earth Sciences</topic><topic>Computer Science</topic><topic>Data Mining and Knowledge Discovery</topic><topic>Economics</topic><topic>Finance</topic><topic>Health Sciences</topic><topic>Humanities</topic><topic>Insurance</topic><topic>Law</topic><topic>Management</topic><topic>Mathematics and Statistics</topic><topic>Medicine</topic><topic>Physics</topic><topic>Regular Article</topic><topic>Statistical Theory and Methods</topic><topic>Statistics</topic><topic>Statistics for Business</topic><topic>Statistics for Engineering</topic><topic>Statistics for Life Sciences</topic><topic>Statistics for Social Sciences</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mozharovskyi, Pavlo</creatorcontrib><creatorcontrib>Mosler, Karl</creatorcontrib><creatorcontrib>Lange, Tatjana</creatorcontrib><jtitle>Advances in data analysis and classification</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mozharovskyi, Pavlo</au><au>Mosler, Karl</au><au>Lange, Tatjana</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Classifying real-world data with the DDα-procedure</atitle><jtitle>Advances in data analysis and classification</jtitle><stitle>Adv Data Anal Classif</stitle><date>2015-09-02</date><risdate>2015</risdate><volume>9</volume><issue>3</issue><spage>287</spage><epage>314</epage><pages>287-314</pages><issn>1862-5347</issn><eissn>1862-5355</eissn><abstract>The
D
D
α
-classifier, a nonparametric fast and very robust procedure, is described and applied to fifty classification problems regarding a broad spectrum of real-world data. The procedure first transforms the data from their original property space into a depth space, which is a low-dimensional unit cube, and then separates them by a projective invariant procedure, called
α
-procedure. To each data point the transformation assigns its depth values with respect to the given classes. Several alternative depth notions (spatial depth, Mahalanobis depth, projection depth, and Tukey depth, the latter two being approximated by univariate projections) are used in the procedure, and compared regarding their average error rates. With the Tukey depth, which fits the distributions’ shape best and is most robust, ‘outsiders’, that is data points having zero depth in all classes, appear. They need an additional treatment for classification. Evidence is also given about the dimension of the extended feature space needed for linear separation. The
D
D
α
-procedure is available as an R-package.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s11634-014-0180-8</doi><tpages>28</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1862-5347 |
| ispartof | Advances in data analysis and classification, 2015-09, Vol.9 (3), p.287-314 |
| issn | 1862-5347 1862-5355 |
| language | eng |
| recordid | cdi_springer_journals_10_1007_s11634_014_0180_8 |
| source | Springer Nature |
| subjects | Chemistry and Earth Sciences Computer Science Data Mining and Knowledge Discovery Economics Finance Health Sciences Humanities Insurance Law Management Mathematics and Statistics Medicine Physics Regular Article Statistical Theory and Methods Statistics Statistics for Business Statistics for Engineering Statistics for Life Sciences Statistics for Social Sciences |
| title | Classifying real-world data with the DDα-procedure |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T03%3A32%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-springer&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Classifying%20real-world%20data%20with%20the%20DD%CE%B1-procedure&rft.jtitle=Advances%20in%20data%20analysis%20and%20classification&rft.au=Mozharovskyi,%20Pavlo&rft.date=2015-09-02&rft.volume=9&rft.issue=3&rft.spage=287&rft.epage=314&rft.pages=287-314&rft.issn=1862-5347&rft.eissn=1862-5355&rft_id=info:doi/10.1007/s11634-014-0180-8&rft_dat=%3Cspringer%3E10_1007_s11634_014_0180_8%3C/springer%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-s198t-f774785134bb00c362240a1c45f069401ae580567386ffee0b2431e4cca816053%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |