Conference paper Open Access

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

Athina Tsanousa; Georgios Meditskos; Stefanos Vrochidis; Ioannis Kompatsiaris


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <controlfield tag="005">20200120170439.0</controlfield>
  <controlfield tag="001">3507004</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, CERTH, Thessaloniki, Hellas</subfield>
    <subfield code="a">Georgios Meditskos</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, CERTH, Thessaloniki, Hellas</subfield>
    <subfield code="a">Stefanos Vrochidis</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, CERTH, Thessaloniki, Hellas</subfield>
    <subfield code="a">Ioannis Kompatsiaris</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">210858</subfield>
    <subfield code="z">md5:a72eded930c6a711abc5bfe1d9d0a84c</subfield>
    <subfield code="u">https://zenodo.org/record/3507004/files/A weighted late fusion framework_final.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-07-15</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:3507004</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, CERTH, Thessaloniki, Hellas</subfield>
    <subfield code="a">Athina Tsanousa</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">A Weighted Late Fusion Framework for Recognizing Human Activity from Wearable Sensors</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&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;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3507003</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3507004</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
32
184
views
downloads
All versions This version
Views 3232
Downloads 184184
Data volume 38.8 MB38.8 MB
Unique views 3131
Unique downloads 176176

Share

Cite as