<?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-05125123</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="2026-05-15T19:58:52+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Anomaly Filtering for Pedestrian Dead Reckoning Using Segment-Based Autoencoders</title>
            <author role="aut">
              <persName>
                <forename type="first">Mohamad Issam</forename>
                <surname>Sayyaf</surname>
              </persName>
              <idno type="halauthorid">3598951-0</idno>
              <affiliation ref="#struct-580992"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ni</forename>
                <surname>Zhu</surname>
              </persName>
              <email type="md5">315b4175cbd6c7d3339ab0c3a2c607eb</email>
              <email type="domain">univ-eiffel.fr</email>
              <idno type="idhal" notation="string">ni-zhu</idno>
              <idno type="idhal" notation="numeric">737115</idno>
              <idno type="halauthorid" notation="string">35726-737115</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4033-3558</idno>
              <affiliation ref="#struct-580992"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Valerie</forename>
                <surname>Renaudin</surname>
              </persName>
              <email type="md5">d6c184d86231c26a3f6cc64a8d8983cb</email>
              <email type="domain">univ-eiffel.fr</email>
              <idno type="idhal" notation="string">valerie-renaudin</idno>
              <idno type="idhal" notation="numeric">736540</idno>
              <idno type="halauthorid" notation="string">1257265-736540</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4535-5406</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=MPzKaFcAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/193205130</idno>
              <affiliation ref="#struct-580992"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>FREDERIC</forename>
                <surname>LE BOURHIS</surname>
              </persName>
              <email type="md5">8588919c09ced68646cd6a2520991e99</email>
              <email type="domain">univ-eiffel.fr</email>
            </editor>
            <funder ref="#projanr-51349"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-06-23 09:34:15</date>
              <date type="whenWritten">2025-04-28</date>
              <date type="whenModified">2026-02-07 05:31:27</date>
              <date type="whenReleased">2025-06-23 09:34:15</date>
              <date type="whenProduced">2025-04-28</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="500540">
                <persName>
                  <forename>FREDERIC</forename>
                  <surname>LE BOURHIS</surname>
                </persName>
                <email type="md5">8588919c09ced68646cd6a2520991e99</email>
                <email type="domain">univ-eiffel.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05125123</idno>
            <idno type="halUri">https://hal.science/hal-05125123</idno>
            <idno type="halBibtex">sayyaf:hal-05125123</idno>
            <idno type="halRefHtml">&lt;i&gt;2025 IEEE/ION Position, Location and Navigation Symposium (PLANS)&lt;/i&gt;, Institute of Electrical and Electronics Engineers, Apr 2025, Salt Lake City, United States. pp.53-62, &lt;a target="_blank" href="https://dx.doi.org/10.1109/PLANS61210.2025.11028276"&gt;&amp;#x27E8;10.1109/PLANS61210.2025.11028276&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">2025 IEEE/ION Position, Location and Navigation Symposium (PLANS), Institute of Electrical and Electronics Engineers, Apr 2025, Salt Lake City, United States. pp.53-62, &amp;#x27E8;10.1109/PLANS61210.2025.11028276&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="IFSTTAR">Ifsttar</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="UNIV-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="U-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="AME">Aménagement, Mobilités et Environnement</idno>
            <idno type="stamp" n="LUDOSCIENCE">LUDOSCIENCE</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="en">Anomaly Filtering for Pedestrian Dead Reckoning Using Segment-Based Autoencoders</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Mohamad Issam</forename>
                    <surname>Sayyaf</surname>
                  </persName>
                  <idno type="halauthorid">3598951-0</idno>
                  <affiliation ref="#struct-580992"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ni</forename>
                    <surname>Zhu</surname>
                  </persName>
                  <email type="md5">315b4175cbd6c7d3339ab0c3a2c607eb</email>
                  <email type="domain">univ-eiffel.fr</email>
                  <idno type="idhal" notation="string">ni-zhu</idno>
                  <idno type="idhal" notation="numeric">737115</idno>
                  <idno type="halauthorid" notation="string">35726-737115</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4033-3558</idno>
                  <affiliation ref="#struct-580992"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Valerie</forename>
                    <surname>Renaudin</surname>
                  </persName>
                  <email type="md5">d6c184d86231c26a3f6cc64a8d8983cb</email>
                  <email type="domain">univ-eiffel.fr</email>
                  <idno type="idhal" notation="string">valerie-renaudin</idno>
                  <idno type="idhal" notation="numeric">736540</idno>
                  <idno type="halauthorid" notation="string">1257265-736540</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4535-5406</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=MPzKaFcAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/193205130</idno>
                  <affiliation ref="#struct-580992"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">[Proceedings of] 2025 IEEE/ION Position, Location and Navigation Symposium (PLANS)</title>
                <meeting>
                  <title>2025 IEEE/ION Position, Location and Navigation Symposium (PLANS)</title>
                  <date type="start">2025-04-28</date>
                  <date type="end">2025-05-01</date>
                  <settlement>Salt Lake City</settlement>
                  <country key="US">United States</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>Institute of Electrical and Electronics Engineers</name>
                </respStmt>
                <editor>Institute of Electrical and Electronics Engineers</editor>
                <imprint>
                  <publisher>IEEE</publisher>
                  <biblScope unit="pp">53-62</biblScope>
                  <date type="datePub">2025-04-28</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/PLANS61210.2025.11028276</idno>
              <ref type="publisher">https://ieeexplore.ieee.org/xpl/conhome/1000571/all-proceedings</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Pedestrian Dead Reckoning</term>
                <term xml:lang="en">Step detection</term>
                <term xml:lang="en">Autoencoder</term>
                <term xml:lang="en">Anomaly Detection</term>
                <term xml:lang="en">Inertial Sensor</term>
                <term xml:lang="en">Deep Learning</term>
              </keywords>
              <classCode scheme="halDomain" n="spi">Engineering Sciences [physics]</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>Accurate step detection is a cornerstone of Pedestrian Dead Reckoning (PDR), enabling applications such as indoor navigation, fitness monitoring and immersive gaming. However, step detection models often generate false detections during non-walking motions, such as hand gestures or sudden shaking. This paper introduces Robust SmartStep, a hybrid approach combining a reliable step detection algorithm SmartStep with a semi-supervised anomaly filtering framework based on a deep autoencoder. The method starts with the pre-processing of acceleration signals, including the generation of a time-frequency spectrogram and local normalization to enhance gait-specific features. An autoencoder trained on normal gait data identifies anomalous segments based on their higher reconstruction error, allowing the anomaly filter to effectively reject false steps. The experimental results of 14 km in different scenarios (pocket carrying, phone swinging, SMS, tests with visually impaired and sighted people) show that Robust SmartStep reduces over-detection errors by 20% compared to SmartStep and by 15% compared to the Android step counter and improves PDR accuracy. In addition, Robust SmartStep achieves PDR positioning performance that approaches the performance of highly personalized models tailored to the individual and one specific carrying mode of the device without the need for re-training. The method's lightweight design, coupled with open-source availability of datasets, code and an Android application facilitate integration into existing navigation systems. https://gitlab.univ-eiffel.fr/issam/robust-smartstep.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-580992" status="VALID">
          <orgName>Géolocalisation</orgName>
          <orgName type="acronym">AME-GEOLOC</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Allée des Ponts et Chaussées, CS 500444344 Bouguenais Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ifsttar.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-580722" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-580722" status="VALID">
          <idno type="ROR">https://ror.org/03x42jk29</idno>
          <orgName>Université Gustave Eiffel</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Cité Descartes, 5 Boulevard Descartes • Champs-sur-Marne, 77454 Marne-la-Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-gustave-eiffel.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-51349" status="VALID">
          <idno type="anr">ANR-20-LCV1-0002</idno>
          <orgName>INMOB</orgName>
          <desc>cartographie du handicap par mesure INertielle pour faciliter la MOBilité</desc>
          <date type="start">2020</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>