Conference paper Open Access

Multiple-Instance Learning for In-The-Wild Parkinsonian Tremor Detection

Alexandros Papadopoulos; Konstantinos Kyritsis; Sevasti Bostanjopoulou; Lisa Klingelhoefer; Ray K. Chaudhuri; Anastasios Delopoulos


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.3676525</identifier>
  <creators>
    <creator>
      <creatorName>Alexandros Papadopoulos</creatorName>
      <affiliation>Multimedia Understanding Group, Information Processing Laboratory, Dept. of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Greece</affiliation>
    </creator>
    <creator>
      <creatorName>Konstantinos Kyritsis</creatorName>
      <affiliation>Multimedia Understanding Group, Information Processing Laboratory, Dept. of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Greece</affiliation>
    </creator>
    <creator>
      <creatorName>Sevasti Bostanjopoulou</creatorName>
      <affiliation>Department of Neurology, Hippokration Hospital, Thessaloniki, Greece</affiliation>
    </creator>
    <creator>
      <creatorName>Lisa Klingelhoefer</creatorName>
      <affiliation>Department of Neurology, Technical University of Dresden, Dresden, Germany</affiliation>
    </creator>
    <creator>
      <creatorName>Ray K. Chaudhuri</creatorName>
      <affiliation>International Parkinson Excellence Research Centre, King's College Hospital NHS Foundation Trust, London, UK</affiliation>
    </creator>
    <creator>
      <creatorName>Anastasios Delopoulos</creatorName>
      <affiliation>Multimedia Understanding Group, Information Processing Laboratory, Dept. of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Greece</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Multiple-Instance Learning for In-The-Wild Parkinsonian Tremor Detection</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <dates>
    <date dateType="Issued">2019-07-31</date>
  </dates>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3676525</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3676524</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;Parkinson&amp;rsquo;s Disease (PD) is a neurodegenerative&amp;nbsp;disorder that manifests through slowly progressing symptoms,&amp;nbsp;such as tremor, voice degradation and bradykinesia. Automated&amp;nbsp;detection of such symptoms has recently received much attention&amp;nbsp;by the research community, owing to the clinical benefits associated with the early diagnosis of the disease. Unfortunately,&amp;nbsp;most of the approaches proposed so far, operate under a strictly&amp;nbsp;laboratory setting, thus limiting their potential applicability in&amp;nbsp;real world conditions. In this work, we present a method for automatically detecting tremorous episodes related to PD, based on acceleration signals. We propose to address the problem&amp;nbsp;at hand, as a case of Multiple-Instance Learning, wherein a&amp;nbsp;subject is represented as an unordered bag of signal segments&amp;nbsp;and a single, expert-provided, ground-truth. We employ a&amp;nbsp;deep learning approach that combines feature learning and a&amp;nbsp;learnable pooling stage and is trainable end-to-end. Results on&amp;nbsp;a newly introduced dataset of accelerometer signals collected&amp;nbsp;in-the-wild confirm the validity of the proposed approach.&amp;nbsp;&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/690494/">690494</awardNumber>
      <awardTitle>Intelligent Parkinson eaRly detectiOn Guiding NOvel Supportive InterventionS</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
56
108
views
downloads
All versions This version
Views 5656
Downloads 108108
Data volume 46.1 MB46.1 MB
Unique views 5151
Unique downloads 103103

Share

Cite as