Conference paper Open Access

Unsupervised Anomaly Detection in Data Quality Control

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

DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://zenodo.org/record/5872438">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/5872438</dct:identifier>
    <foaf:page rdf:resource="https://zenodo.org/record/5872438"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Poon, Lex</foaf:name>
        <foaf:givenName>Lex</foaf:givenName>
        <foaf:familyName>Poon</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Amsterdam</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Farshidi, Siamak</foaf:name>
        <foaf:givenName>Siamak</foaf:givenName>
        <foaf:familyName>Farshidi</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Amsterdam</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Li, Na</foaf:name>
        <foaf:givenName>Na</foaf:givenName>
        <foaf:familyName>Li</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Amsterdam</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-6717-9418">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-6717-9418</dct:identifier>
        <foaf:name>Zhao, Zhiming</foaf:name>
        <foaf:givenName>Zhiming</foaf:givenName>
        <foaf:familyName>Zhao</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Amsterdam</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Unsupervised Anomaly Detection in Data Quality Control</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2021</dct:issued>
    <dcat:keyword>data quality</dcat:keyword>
    <dcat:keyword>unsupervised learning</dcat:keyword>
    <dcat:keyword>data quality control</dcat:keyword>
    <dcat:keyword>data quality assessment</dcat:keyword>
    <dcat:keyword>anomaly detection,</dcat:keyword>
    <dcat:keyword>automated data quality control</dcat:keyword>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - European Training Networks/860627/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/862409/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/825134/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/824068/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-12-15</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/5872438"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/5872438</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <owl:sameAs rdf:resource="https://doi.org/10.1109/BigData52589.2021.9671672"/>
    <owl:versionInfo>camera ready</owl:versionInfo>
    <dct:description>&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;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.1109/BigData52589.2021.9671672"/>
        <dcat:byteSize>2899991</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5872438/files/2021.workshop.bigdata.midp21.camera.pdf"/>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - European Training Networks/860627/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">860627</dct:identifier>
    <dct:title>CLoud ARtificial Intelligence For pathologY</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/862409/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">862409</dct:identifier>
    <dct:title>Blue-Cloud: Piloting innovative services for Marine Research &amp; the Blue Economy</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/825134/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">825134</dct:identifier>
    <dct:title>smART socIal media eCOsytstem in a blockchaiN Federated environment</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/824068/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">824068</dct:identifier>
    <dct:title>ENVironmental Research Infrastructures building Fair services Accessible for society, Innovation and Research</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
</rdf:RDF>
37
47
views
downloads
Views 37
Downloads 47
Data volume 136.3 MB
Unique views 30
Unique downloads 46
More info on how stats are collected.
Indexed in
Publication date:
December 15, 2021
DOI:
10.1109/BigData52589.2021.9671672
Keyword(s):
data quality unsupervised learning data quality control data quality assessment anomaly detection, automated data quality control
Grants:
European Commission:
  • CLARIFY - CLoud ARtificial Intelligence For pathologY (860627)
  • Blue Cloud - Blue-Cloud: Piloting innovative services for Marine Research & the Blue Economy (862409)
  • ARTICONF - smART socIal media eCOsytstem in a blockchaiN Federated environment (825134)
  • ENVRI-FAIR - ENVironmental Research Infrastructures building Fair services Accessible for society, Innovation and Research (824068)
Meeting:
7th International Workshop on Methods to Improve Big Data Science Projects (MIDP-2021), in IEEE BigData 2021 (MIDP-2021), Virtual, 15-18 Dec 2021
License (for files):
Creative Commons Attribution 4.0 International

Share

Cite as

Export