<?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-04945686</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="2026-05-16T16:22:11+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">Cartographie du risque épidémiologique : le défi des données fortement déséquilibrées</title>
            <author role="crp">
              <persName>
                <forename type="first">Rodrigue</forename>
                <surname>Govan</surname>
              </persName>
              <email type="md5">736140f60a9cf0ff10c05b0a178472fe</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">rodrigue-govan</idno>
              <idno type="idhal" notation="numeric">1177931</idno>
              <idno type="halauthorid" notation="string">2371217-1177931</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4087-7056</idno>
              <affiliation ref="#struct-529607"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Romane</forename>
                <surname>Scherrer</surname>
              </persName>
              <idno type="halauthorid">2425095-0</idno>
              <affiliation ref="#struct-529607"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cyrille</forename>
                <surname>Goarant</surname>
              </persName>
              <email type="md5">f2989cea65c3e2a78778cd24f2ac4db0</email>
              <email type="domain">pasteur.nc</email>
              <idno type="idhal" notation="string">cyrille-goarant</idno>
              <idno type="idhal" notation="numeric">328</idno>
              <idno type="halauthorid" notation="string">9971-328</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0690-9464</idno>
              <idno type="IDREF">https://www.idref.fr/059708328</idno>
              <affiliation ref="#struct-404800"/>
              <affiliation ref="#struct-548654"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Arnaud</forename>
                <surname>Cannet</surname>
              </persName>
              <idno type="halauthorid">1066309-0</idno>
              <affiliation ref="#struct-1078031"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Philippe</forename>
                <surname>Fournier-Viger</surname>
              </persName>
              <idno type="halauthorid">251501-0</idno>
              <affiliation ref="#struct-242850"/>
            </author>
            <author role="crp">
              <persName>
                <forename type="first">Nazha</forename>
                <surname>Selmaoui-Folcher</surname>
              </persName>
              <idno type="halauthorid">17566-0</idno>
              <affiliation ref="#struct-529607"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Rodrigue</forename>
                <surname>Govan</surname>
              </persName>
              <email type="md5">736140f60a9cf0ff10c05b0a178472fe</email>
              <email type="domain">gmail.com</email>
            </editor>
            <funder ref="#projanr-53457"/>
            <funder>Ce travail a été financé dans le cadre du projet ANR SPIraL (ANR-19-CE35-0006-02). Nous remercions la Direction des Affaires Sanitaires et Sociales de Nouvelle-Calédonie pour la collecte, la consolidation et la mise à disposition des données relatives aux cas de leptospirose.</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-02-13 13:23:26</date>
              <date type="whenWritten">2025-01-29</date>
              <date type="whenModified">2026-04-01 08:55:42</date>
              <date type="whenReleased">2025-02-19 14:13:58</date>
              <date type="whenProduced">2025-01-27</date>
              <date type="whenEndEmbargoed">2025-02-13</date>
              <ref type="file" target="https://hal.science/hal-04945686v1/document">
                <date notBefore="2025-02-13"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04945686v1/file/proceedings7518.pdf" id="file-4945686-4290653">
                <date notBefore="2025-02-13"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1322956">
                <persName>
                  <forename>Rodrigue</forename>
                  <surname>Govan</surname>
                </persName>
                <email type="md5">736140f60a9cf0ff10c05b0a178472fe</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04945686</idno>
            <idno type="halUri">https://hal.science/hal-04945686</idno>
            <idno type="halBibtex">govan:hal-04945686</idno>
            <idno type="halRefHtml">&lt;i&gt;Extraction et Gestion des Connaissances, EGC'2025&lt;/i&gt;, Jan 2025, Strasbourg, France. pp.159-170</idno>
            <idno type="halRef">Extraction et Gestion des Connaissances, EGC'2025, Jan 2025, Strasbourg, France. pp.159-170</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4945686-4290653"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="RIIP">Pasteur Network</idno>
            <idno type="stamp" n="UNIV-NC">Université de Nouvelle Calédonie</idno>
            <idno type="stamp" n="SANTE_PUB_INSERM" corresp="INSERM">Santé Publique à l'Inserm</idno>
            <idno type="stamp" n="RIIP_NOUVELLECALEDONIE" corresp="RIIP">Institut Pasteur de Nouvelle-Calédonie</idno>
            <idno type="stamp" n="UNC">Université de la Nouvelle-Calédonie</idno>
            <idno type="stamp" n="ISEA-UNC" corresp="UNC">ISEA - Institut de sciences exactes et appliquées</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ANR-ONE-HEALTH">ANR-ONE-HEALTH</idno>
            <idno type="stamp" n="ANR-ONE-HEALTH-REF-ANR" corresp="ANR-ONE-HEALTH">ANR-ONE-HEALTH-REF-ANR</idno>
          </seriesStmt>
          <notesStmt>
            <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="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="fr">Cartographie du risque épidémiologique : le défi des données fortement déséquilibrées</title>
                <author role="crp">
                  <persName>
                    <forename type="first">Rodrigue</forename>
                    <surname>Govan</surname>
                  </persName>
                  <email type="md5">736140f60a9cf0ff10c05b0a178472fe</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">rodrigue-govan</idno>
                  <idno type="idhal" notation="numeric">1177931</idno>
                  <idno type="halauthorid" notation="string">2371217-1177931</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4087-7056</idno>
                  <affiliation ref="#struct-529607"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Romane</forename>
                    <surname>Scherrer</surname>
                  </persName>
                  <idno type="halauthorid">2425095-0</idno>
                  <affiliation ref="#struct-529607"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cyrille</forename>
                    <surname>Goarant</surname>
                  </persName>
                  <email type="md5">f2989cea65c3e2a78778cd24f2ac4db0</email>
                  <email type="domain">pasteur.nc</email>
                  <idno type="idhal" notation="string">cyrille-goarant</idno>
                  <idno type="idhal" notation="numeric">328</idno>
                  <idno type="halauthorid" notation="string">9971-328</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0690-9464</idno>
                  <idno type="IDREF">https://www.idref.fr/059708328</idno>
                  <affiliation ref="#struct-404800"/>
                  <affiliation ref="#struct-548654"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Arnaud</forename>
                    <surname>Cannet</surname>
                  </persName>
                  <idno type="halauthorid">1066309-0</idno>
                  <affiliation ref="#struct-1078031"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Philippe</forename>
                    <surname>Fournier-Viger</surname>
                  </persName>
                  <idno type="halauthorid">251501-0</idno>
                  <affiliation ref="#struct-242850"/>
                </author>
                <author role="crp">
                  <persName>
                    <forename type="first">Nazha</forename>
                    <surname>Selmaoui-Folcher</surname>
                  </persName>
                  <idno type="halauthorid">17566-0</idno>
                  <affiliation ref="#struct-529607"/>
                </author>
              </analytic>
              <monogr>
                <idno type="isbn">9791096289226</idno>
                <title level="m">Revue des Nouvelles Technologies de l'Information</title>
                <meeting>
                  <title>Extraction et Gestion des Connaissances, EGC'2025</title>
                  <date type="start">2025-01-27</date>
                  <date type="end">2025-01-31</date>
                  <settlement>Strasbourg</settlement>
                  <country key="FR">France</country>
                </meeting>
                <editor>Thomas Guyet</editor>
                <editor>Baptiste Lafabrègue</editor>
                <editor>Aurélie Leborgne</editor>
                <imprint>
                  <publisher>RNTI</publisher>
                  <biblScope unit="volume">RNTI-E-41</biblScope>
                  <biblScope unit="pp">159-170</biblScope>
                </imprint>
              </monogr>
              <ref type="publisher">https://editions-rnti.fr/?procid=100192</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="sdv.spee">Life Sciences [q-bio]/Santé publique et épidémiologie</classCode>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The advent of big data collection has contributed to the development of knowledge extraction methods, but it has also introduced new challenges. One of the main issues is dealing with highly imbalanceddatasets, particularlyin class labelsforcategorical classificationtasks. This article presents a comprehensive strategy developed to address the issue of imbalanced data in a spatio-temporal epidemiological study of leptospirosis. The approach was evaluated using real data for a binary classification task, predicting the presence of contamination risk with the bacteria associated with leptospirosis, where the majority class represents 95% of the labels. By applying under-sampling, training 200 machine learning models, and using weighted predictions, our strategy achieved a balanced accuracy of 76.19%, an AUC-ROC of 83.29%, and a recall of 83.93%.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>L'émergence de la collecte de données massives a contribué au développement de méthodes d'extraction de connaissances, mais elle a également apporté son lot de défis. Parmi ces défis, on retrouve le problème des données fortement déséquilibrées, notamment dans les classes à prédire d'une tâche de classification catégorielle. Cet article présente une stratégie complète développée afin de pallier la problématique de données déséquilibrées dans le cadre d'une étude épidémiologique spatio-temporelle de la leptospirose. L'approche est évaluée sur des données réelles pour une tâche de classification binaire de "présence de risque" de contamination de la bactérie associée à la leptospirose, où la classe majoritaire représente environ 95% des classes à prédire. Par le sous-échantillonnage, l'entraînement de 200 modèles d'apprentissage supervisé et une prédiction pondérée, notre stratégie a atteint une justesse équilibrée de 76,19%, un AUC de 83,29% et un rappel de 83,93%.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-529607" status="VALID">
          <orgName>Institut des Sciences Exactes et Appliquées [Nouméa]</orgName>
          <orgName type="acronym">ISEA</orgName>
          <date type="start">2017-04-02</date>
          <desc>
            <address>
              <addrLine>Université de la Nouvelle-Calédonie, Campus de Nouville, 98851 Nouméa</addrLine>
              <country key="NC"/>
            </address>
            <ref type="url">https://isea.unc.nc/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300328" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-404800" status="VALID">
          <idno type="RNSR">201324334Y</idno>
          <orgName>Unité de Recherche et d'Expertise Leptospirose - Leptospirosis Research and Expertise Unit [Nouméa, Nouvelle-Calédonie]</orgName>
          <orgName type="acronym">UREL</orgName>
          <date type="start">2013-01-01</date>
          <desc>
            <address>
              <country key="NC"/>
            </address>
            <ref type="url">http://www.institutpasteur.nc/category/recherche/urel/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-45419" type="direct"/>
            <relation active="#struct-301247" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-548654" status="VALID">
          <idno type="ISNI">0000 0000 9500 7395</idno>
          <idno type="ROR">https://ror.org/05ewdm369</idno>
          <idno type="Wikidata">Q871511</idno>
          <orgName>Pacific community [Nouméa, nouvelle Calédonie]</orgName>
          <orgName type="acronym">SPC</orgName>
          <desc>
            <address>
              <addrLine>95 Promenade Roger LaroqueBP D598848 NoumeaNew Caledonia,</addrLine>
              <country key="NC"/>
            </address>
            <ref type="url">https://spc.int/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1078031" status="VALID">
          <orgName>Direction des Affaires sanitaires et sociales de la Nouvelle-Calédonie [Nouméa]</orgName>
          <orgName type="acronym">DASS [Nouméa]</orgName>
          <desc>
            <address>
              <addrLine>7 avenue Paul Doumer BP M2 98849 Nouméa</addrLine>
              <country key="NC"/>
            </address>
            <ref type="url">https://dass.gouv.nc/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-242850" status="VALID">
          <idno type="IdRef">234129905</idno>
          <idno type="ISNI">0000000104729649</idno>
          <idno type="ROR">https://ror.org/01vy4gh70</idno>
          <idno type="Wikidata">Q1945756</idno>
          <orgName>Shenzhen University [Shenzhen] = 深圳大学</orgName>
          <orgName type="acronym">SZU</orgName>
          <date type="start">1983-01-01</date>
          <desc>
            <address>
              <addrLine>Nanhai Ave 3688,Shenzhen,Guangdong,P.R.China,518060</addrLine>
              <country key="CN"/>
            </address>
            <ref type="url">http://www.szu.edu.cn/2013/english/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300328" status="VALID">
          <idno type="IdRef">060121076</idno>
          <idno type="ROR">https://ror.org/02jrgcx64</idno>
          <orgName>Université de la Nouvelle-Calédonie</orgName>
          <orgName type="acronym">UNC</orgName>
          <date type="start">1999-01-01</date>
          <desc>
            <address>
              <addrLine>Université de la Nouvelle-Calédonie, Campus de Nouville, BP R4 98851 Nouméa Cedex</addrLine>
              <country key="NC"/>
            </address>
            <ref type="url">https://unc.nc/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-45419" status="VALID">
          <idno type="RNSR">195522890F</idno>
          <idno type="ROR">https://ror.org/04sqtjj61</idno>
          <orgName>Institut Pasteur de Nouvelle-Calédonie</orgName>
          <date type="start">1955-01-01</date>
          <desc>
            <address>
              <addrLine>B.P. 61 98845 Nouméa</addrLine>
              <country key="NC"/>
            </address>
            <ref type="url">http://www.institutpasteur.nc</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301247" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301247" status="VALID">
          <orgName>Pasteur Network (Réseau International des Instituts Pasteur)</orgName>
          <desc>
            <address>
              <addrLine>25, rue du Dr Roux 75724 Paris Cedex 15</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://pasteur-network.org/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-53457" status="VALID">
          <idno type="anr">ANR-19-CE35-0006</idno>
          <orgName>SPIraL</orgName>
          <desc>Sols, pluie et leptospirose</desc>
          <date type="start">2019</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>