Conference paper Open Access

A Weighted Late Fusion Framework for Recognizing Human Activity from Wearable Sensors

Athina Tsanousa; Georgios Meditskos; Stefanos Vrochidis; Ioannis Kompatsiaris


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3507004</identifier>
  <creators>
    <creator>
      <creatorName>Athina Tsanousa</creatorName>
      <affiliation>Information Technologies Institute, CERTH, Thessaloniki, Hellas</affiliation>
    </creator>
    <creator>
      <creatorName>Georgios Meditskos</creatorName>
      <affiliation>Information Technologies Institute, CERTH, Thessaloniki, Hellas</affiliation>
    </creator>
    <creator>
      <creatorName>Stefanos Vrochidis</creatorName>
      <affiliation>Information Technologies Institute, CERTH, Thessaloniki, Hellas</affiliation>
    </creator>
    <creator>
      <creatorName>Ioannis Kompatsiaris</creatorName>
      <affiliation>Information Technologies Institute, CERTH, Thessaloniki, Hellas</affiliation>
    </creator>
  </creators>
  <titles>
    <title>A Weighted Late Fusion Framework for Recognizing Human Activity from Wearable Sensors</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <dates>
    <date dateType="Issued">2019-07-15</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3507004</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3507003</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Following the technological advancement and the&lt;br&gt;
constantly emerging assisted living applications, sensor-based activity&lt;br&gt;
recognition research receives great attention. Until recently,&lt;br&gt;
the majority of relevant research involved extracting knowledge&lt;br&gt;
out of single modalities, however, when individual sensors performances&lt;br&gt;
are not satisfactory, combining information from multiple&lt;br&gt;
sensors can be of use and improve the activity recognition rate.&lt;br&gt;
Early and late fusion classifier strategies are usually employed&lt;br&gt;
to successfully merge multiple sensors. This paper proposes a&lt;br&gt;
novel framework for combining accelerometers and gyroscopes&lt;br&gt;
at decision level, in order to recognize human activity. More&lt;br&gt;
specifically, we propose a weighted late fusion framework that&lt;br&gt;
utilizes the detection rate of a classifier. Furthermore, we propose&lt;br&gt;
the modification of an already existing class-based weighted late&lt;br&gt;
fusion framework. Experimental results on a publicly available&lt;br&gt;
and widely used dataset demonstrated that the combination of&lt;br&gt;
accelerometer and gyroscope under the proposed frameworks&lt;br&gt;
improves the classification performance.&lt;/p&gt;</description>
  </descriptions>
</resource>
34
292
views
downloads
All versions This version
Views 3434
Downloads 292292
Data volume 61.6 MB61.6 MB
Unique views 3333
Unique downloads 284284

Share

Cite as