Conference paper Open Access

Unsupervised Anomaly Detection in Data Quality Control

Poon, Lex; Farshidi, Siamak; Li, Na; Zhao, Zhiming


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="URL">https://zenodo.org/record/5872438</identifier>
  <creators>
    <creator>
      <creatorName>Poon, Lex</creatorName>
      <givenName>Lex</givenName>
      <familyName>Poon</familyName>
      <affiliation>University of Amsterdam</affiliation>
    </creator>
    <creator>
      <creatorName>Farshidi, Siamak</creatorName>
      <givenName>Siamak</givenName>
      <familyName>Farshidi</familyName>
      <affiliation>University of Amsterdam</affiliation>
    </creator>
    <creator>
      <creatorName>Li, Na</creatorName>
      <givenName>Na</givenName>
      <familyName>Li</familyName>
      <affiliation>University of Amsterdam</affiliation>
    </creator>
    <creator>
      <creatorName>Zhao, Zhiming</creatorName>
      <givenName>Zhiming</givenName>
      <familyName>Zhao</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-6717-9418</nameIdentifier>
      <affiliation>University of Amsterdam</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Unsupervised Anomaly Detection in Data Quality Control</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>data quality</subject>
    <subject>unsupervised learning</subject>
    <subject>data quality control</subject>
    <subject>data quality assessment</subject>
    <subject>anomaly detection,</subject>
    <subject>automated data quality control</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2021-12-15</date>
  </dates>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/5872438</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1109/BigData52589.2021.9671672</relatedIdentifier>
  </relatedIdentifiers>
  <version>camera ready</version>
  <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;Data is one of the most valuable assets of an&lt;/p&gt;

&lt;p&gt;organization and has a tremendous impact on its long-term&lt;/p&gt;

&lt;p&gt;success and decision-making processes. Typically, organizational&lt;/p&gt;

&lt;p&gt;data error and outlier detection processes perform manually and&lt;/p&gt;

&lt;p&gt;reactively, making them time-consuming and prone to human errors.&lt;/p&gt;

&lt;p&gt;Additionally, rich data types, unlabeled data, and increased&lt;/p&gt;

&lt;p&gt;volume have made such data more complex. Accordingly, an&lt;/p&gt;

&lt;p&gt;automated anomaly detection approach is required to improve&lt;/p&gt;

&lt;p&gt;data management and quality control processes. This study&lt;/p&gt;

&lt;p&gt;introduces an unsupervised anomaly detection approach based&lt;/p&gt;

&lt;p&gt;on models comparison, consensus learning, and a combination of&lt;/p&gt;

&lt;p&gt;rules of thumb with iterative hyper-parameter tuning to increase&lt;/p&gt;

&lt;p&gt;data quality. Furthermore, a domain expert is considered a&lt;/p&gt;

&lt;p&gt;human in the loop to evaluate and check the data quality and to&lt;/p&gt;

&lt;p&gt;judge the output of the unsupervised model. An experiment has&lt;/p&gt;

&lt;p&gt;been conducted to assess the proposed approach in the context of&lt;/p&gt;

&lt;p&gt;a case study. The experiment results confirm that the proposed&lt;/p&gt;

&lt;p&gt;approach can improve the quality of&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - European Training Networks/860627/">860627</awardNumber>
      <awardTitle>CLoud ARtificial Intelligence For pathologY</awardTitle>
    </fundingReference>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/862409/">862409</awardNumber>
      <awardTitle>Blue-Cloud: Piloting innovative services for Marine Research &amp; the Blue Economy</awardTitle>
    </fundingReference>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/825134/">825134</awardNumber>
      <awardTitle>smART socIal media eCOsytstem in a blockchaiN Federated environment</awardTitle>
    </fundingReference>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/824068/">824068</awardNumber>
      <awardTitle>ENVironmental Research Infrastructures building Fair services Accessible for society, Innovation and Research</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
35
46
views
downloads
Views 35
Downloads 46
Data volume 133.4 MB
Unique views 28
Unique downloads 45

Share

Cite as