<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01192999</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-04-23T14:13:04+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A fast and flexible instance selection algorithm adapted to non-trivial database sizes</title>
            <author role="aut">
              <persName>
                <forename type="first">F.</forename>
                <surname>Ros</surname>
              </persName>
              <idno type="halauthorid">441212-0</idno>
              <affiliation ref="#struct-98357"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Rachid</forename>
                <surname>Harba</surname>
              </persName>
              <email type="md5">8df1ef8d8fec825b19be009e2c4066e8</email>
              <email type="domain">univ-orleans.fr</email>
              <idno type="idhal" notation="numeric">905353</idno>
              <idno type="halauthorid" notation="string">570519-905353</idno>
              <affiliation ref="#struct-98357"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">M.</forename>
                <surname>Pintore</surname>
              </persName>
              <idno type="halauthorid">155205-0</idno>
              <affiliation ref="#struct-429929"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">S.</forename>
                <surname>Guillaume</surname>
              </persName>
              <email type="md5">571218d2626c6240340d807c5768576c</email>
              <email type="domain">chu-montpellier.fr</email>
              <idno type="idhal" notation="numeric">1148420</idno>
              <idno type="halauthorid" notation="string">912831-1148420</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-6769-9982</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/DXC-4017-2022</idno>
              <idno type="IDREF">https://www.idref.fr/111748119</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/DXC-4017-2022</idno>
              <affiliation ref="#struct-16792"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Import Ws</forename>
                <surname>Irstea</surname>
              </persName>
              <email type="md5">db907169de0b78bb03b3d9d698fbf5a0</email>
              <email type="domain">irstea.fr.invalid</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2015-09-04 10:18:01</date>
              <date type="whenWritten">2015</date>
              <date type="whenModified">2025-06-12 16:30:03</date>
              <date type="whenReleased">2015-09-04 16:44:33</date>
              <date type="whenProduced">2015</date>
              <date type="whenEndEmbargoed">2015-09-04</date>
              <ref type="file" target="https://hal.science/hal-01192999v1/document">
                <date notBefore="2015-09-04"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01192999v1/file/mo2015-pub00044884.pdf" id="file-1192999-1276337">
                <date notBefore="2015-09-04"/>
              </ref>
              <ref type="externalLink" target="https://hal.archives-ouvertes.fr/hal-01192999/file/mo2015-pub00044884.pdf"/>
              <fs>
                <f name="inra_publicVise_local" notation="string" n="SC">
                  <string>Scientists</string>
                </f>
              </fs>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="125582">
                <persName>
                  <forename>Import Ws</forename>
                  <surname>Irstea</surname>
                </persName>
                <email type="md5">db907169de0b78bb03b3d9d698fbf5a0</email>
                <email type="domain">irstea.fr.invalid</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01192999</idno>
            <idno type="halUri">https://hal.science/hal-01192999</idno>
            <idno type="halBibtex">ros:hal-01192999</idno>
            <idno type="halRefHtml">&lt;i&gt;Intelligent Data Analysis&lt;/i&gt;, 2015, 19 (3), pp.631-658. &lt;a target="_blank" href="https://dx.doi.org/10.3233/IDA-150736"&gt;&amp;#x27E8;10.3233/IDA-150736&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Intelligent Data Analysis, 2015, 19 (3), pp.631-658. &amp;#x27E8;10.3233/IDA-150736&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1192999-1276337"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SDE">Sciences De l'Environnement</idno>
            <idno type="stamp" n="UNIV-ORLEANS">Université d'Orléans</idno>
            <idno type="stamp" n="ENSI-BOURGES">Ecole Nationale Supérieure d'Ingénieurs de Bourges</idno>
            <idno type="stamp" n="IRSTEA">IRSTEA - Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (&lt;b&gt;anciennement Cemagref&lt;/b&gt;)</idno>
            <idno type="stamp" n="MSL">Modelisation Systemes Langages</idno>
            <idno type="stamp" n="GIP-BE">GIP Bretagne Environnement</idno>
            <idno type="stamp" n="MSL-THESE">Modelisation Systemes Langages</idno>
            <idno type="stamp" n="AGROPOLIS">Agropolis</idno>
            <idno type="stamp" n="AGREENIUM">Archive ouverte en agrobiosciences</idno>
            <idno type="stamp" n="PRISME-CVL" corresp="UNIV-ORLEANS">Laboratoire Pluridisciplinaire de Recherche Ingénierie des Systèmes, Mécanique, Énergétique</idno>
            <idno type="stamp" n="ITAP">Unité Mixte de Recherche Information - Technologies - Analyse environnementale - Procédés agricoles</idno>
            <idno type="stamp" n="INSTITUT-AGRO-MONTPELLIER">Institut Agro Montpellier</idno>
            <idno type="stamp" n="INRAE">Institut National de Recherche en Agriculture, Alimentation et Environnement</idno>
            <idno type="stamp" n="INRAEOCCITANIEMONTPELLIER" corresp="INRAE">INRAE Occitanie Montpellier</idno>
            <idno type="stamp" n="MATHNUM">Département MathNum</idno>
            <idno type="stamp" n="INSTITUT-AGRO">Institut Agro</idno>
            <idno type="stamp" n="TEST-MATHNUM">Test MathNum</idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">[Departement_IRSTEA]Ecotechnologies [TR1_IRSTEA]INSPIRE</note>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A fast and flexible instance selection algorithm adapted to non-trivial database sizes</title>
                <author role="aut">
                  <persName>
                    <forename type="first">F.</forename>
                    <surname>Ros</surname>
                  </persName>
                  <idno type="halauthorid">441212-0</idno>
                  <affiliation ref="#struct-98357"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Rachid</forename>
                    <surname>Harba</surname>
                  </persName>
                  <email type="md5">8df1ef8d8fec825b19be009e2c4066e8</email>
                  <email type="domain">univ-orleans.fr</email>
                  <idno type="idhal" notation="numeric">905353</idno>
                  <idno type="halauthorid" notation="string">570519-905353</idno>
                  <affiliation ref="#struct-98357"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">M.</forename>
                    <surname>Pintore</surname>
                  </persName>
                  <idno type="halauthorid">155205-0</idno>
                  <affiliation ref="#struct-429929"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">S.</forename>
                    <surname>Guillaume</surname>
                  </persName>
                  <email type="md5">571218d2626c6240340d807c5768576c</email>
                  <email type="domain">chu-montpellier.fr</email>
                  <idno type="idhal" notation="numeric">1148420</idno>
                  <idno type="halauthorid" notation="string">912831-1148420</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-6769-9982</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/DXC-4017-2022</idno>
                  <idno type="IDREF">https://www.idref.fr/111748119</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/DXC-4017-2022</idno>
                  <affiliation ref="#struct-16792"/>
                </author>
              </analytic>
              <monogr>
                <idno type="localRef">PUB00044884</idno>
                <idno type="halJournalId" status="VALID">14249</idno>
                <idno type="issn">1088-467X</idno>
                <title level="j">Intelligent Data Analysis</title>
                <imprint>
                  <publisher>IOS Press</publisher>
                  <biblScope unit="volume">19</biblScope>
                  <biblScope unit="issue">3</biblScope>
                  <biblScope unit="pp">631-658</biblScope>
                  <date type="datePub">2015</date>
                </imprint>
              </monogr>
              <idno type="doi">10.3233/IDA-150736</idno>
              <idno type="irstea">PUB00044884</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">BASE DE DONNEES</term>
                <term xml:lang="en">ALGORITHME</term>
                <term xml:lang="en">CLASSIFICATION</term>
                <term xml:lang="en">INFORMATIQUE</term>
                <term xml:lang="fr">DATABASE SYSTEMS</term>
                <term xml:lang="fr">CLUSTERING ALGORITHM</term>
                <term xml:lang="fr">INSTANCE SELECTION</term>
                <term xml:lang="fr">K-NEAREST NEIGHBORS</term>
                <term xml:lang="fr">SUPERVISED CLASSIFICATION</term>
                <term xml:lang="fr">ALGORITHMS</term>
                <term xml:lang="fr">CLASSIFICATION (OF INFORMATION)</term>
                <term xml:lang="fr">NEAREST NEIGHBOR SEARCH</term>
                <term xml:lang="fr">DIGITAL STORAGE</term>
                <term xml:lang="fr">ITERATIVE METHODS</term>
                <term xml:lang="fr">CLUSTERING ALGORITHMS</term>
                <term xml:lang="fr">SYNTHETIC AND REAL DATA</term>
                <term xml:lang="fr">STORAGE REQUIREMENTS</term>
                <term xml:lang="fr">ITERATIVE PROCESS</term>
                <term xml:lang="fr">FILTERING PROCESS</term>
                <term xml:lang="fr">DIFFERENT MECHANISMS</term>
              </keywords>
              <classCode scheme="halDomain" n="sde">Environmental Sciences</classCode>
              <classCode scheme="vocinrae-old" n="ALGORITHME">ALGORITHME</classCode>
              <classCode scheme="vocinrae-old" n="CLASSIFICATION">CLASSIFICATION</classCode>
              <classCode scheme="vocinrae-old" n="BASE DE DONNEES">BASE DE DONNEES</classCode>
              <classCode scheme="vocinrae-old" n="INFORMATIQUE">INFORMATIQUE</classCode>
              <classCode scheme="vocinrae-old" n="ALGORITHM">ALGORITHM</classCode>
              <classCode scheme="vocinrae-old" n="CLASSIFICATION">CLASSIFICATION</classCode>
              <classCode scheme="vocinrae-old" n="DATA BASE">DATA BASE</classCode>
              <classCode scheme="vocinrae-old" n="COMPUTER SCIENCE">COMPUTER SCIENCE</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>In this paper, a new instance selection algorithm is proposed in the context of classification to manage non-trivial database sizes. The algorithm is hybrid and runs with only a few parameters that directly control the balance between the three objectives of classification, i.e. errors, storage requirements and runtime. It comprises different mechanisms involving neighborhood and stratification algorithms that specifically speed up the runtime without significantly degrading efficiency. Instead of applying an IS (Instance Selection) algorithm to the whole database, IS is applied to strata deriving from the regions, each region representing a set of patterns selected from the original training set. The application of IS is conditioned by the purity of each region (i.e. the extent to which different categories of patterns are mixed in the region) and the stratification strategy is adapted to the region components. For each region, the number of delivered instances is firstly limited via the use of an iterative process that takes into account the boundary complexity, and secondly optimized by removing the superfluous ones. The sets of instances determined from all the regions are put together to provide an intermediate instance set that undergoes a dedicated filtering process to deliver the final set. Experiments performed with various synthetic and real data sets demonstrate the advantages of the proposed approach.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-98357" status="OLD">
          <idno type="IdRef">166710369</idno>
          <idno type="RNSR">200815466F</idno>
          <orgName>Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique [2008-2013]</orgName>
          <orgName type="acronym">PRISME</orgName>
          <date type="start">2008-01-01</date>
          <desc>
            <address>
              <addrLine>8 rue Léonard de Vinci, 45072 Orléans Cédex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-orleans.fr/prisme</ref>
          </desc>
          <listRelation>
            <relation name="EA 4229" active="#struct-300297" type="direct"/>
            <relation name="EA 4229" active="#struct-302160" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-429929" status="INCOMING">
          <orgName>aucun</orgName>
          <desc>
            <address>
              <addrLine>Saint Jean de la Ruelle</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-429928" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-16792" status="OLD">
          <idno type="RNSR">200118630A</idno>
          <orgName>Information – Technologies – Analyse Environnementale – Procédés Agricoles</orgName>
          <orgName type="acronym">UMR ITAP</orgName>
          <date type="start">2012-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>361, rue J.F. Breton - BP 5095 - 34033 Montpellier Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://itap.irstea.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR1463" active="#struct-302049" type="direct"/>
            <relation active="#struct-474617" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300297" status="VALID">
          <idno type="IdRef">026402971</idno>
          <idno type="ISNI">0000 0001 2158 1666</idno>
          <idno type="ROR">https://ror.org/014zrew76</idno>
          <orgName>Université d'Orléans</orgName>
          <orgName type="acronym">UO</orgName>
          <desc>
            <address>
              <addrLine>Château de la Source - Avenue du Parc Floral - BP 6749 - 45067 Orléans cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-orleans.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302160" status="OLD">
          <idno type="IdRef">136225233</idno>
          <orgName>Ecole Nationale Supérieure d'Ingénieurs de Bourges</orgName>
          <orgName type="acronym">ENSI Bourges</orgName>
          <date type="start">1997</date>
          <date type="end">2013-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-429928" status="INCOMING">
          <orgName>PILA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302049" status="OLD">
          <idno type="ROR">https://ror.org/01wep6g48</idno>
          <orgName>Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture</orgName>
          <orgName type="acronym">IRSTEA</orgName>
          <date type="start">2012-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irstea.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-474617" status="OLD">
          <idno type="ROR">https://ror.org/03rnk6m14</idno>
          <orgName>Institut national d’études supérieures agronomiques de Montpellier</orgName>
          <orgName type="acronym">Montpellier SupAgro</orgName>
          <date type="start">2015-02-06</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>2, place Viala34060 Montpellier Cédex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.supagro.fr</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>