Aggregation of Subclassifications : Methods, Tools and Experiments

Doell, Christoph; Borgelt, Christian

Aggregation of Subclassifications : Methods, Tools and Experiments

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2019

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

2019 IEEE Symposium Series on Computational Intelligence (SSCI). Piscataway, NJ: IEEE, 2019, pp. 3124-3131. ISBN 978-1-72812-485-8. Available under: doi: 10.1109/SSCI44817.2019.9002806

Zusammenfassung

Aggregation methods have been studied extensively from a mathematical, theoretical point of view. In this work, however, we focus on a more practical aspect: subclassifications. Given class predictions for several sub-objects of a single instance, we systematically investigate the performance of different aggregation methods. To this end, we simulate data for various data distributions. Thus we ensure that we know the ground truth for the evaluation, which would be impossible for real world data. Our source code is publicly available and can be extended to explore other aggregation methods and other data distributions.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

classification, aggregation, sum, product, voting

Konferenz

2019 IEEE Symposium Series on Computational Intelligence (SSCI), 6. Dez. 2019 - 9. Dez. 2019, Xiamen, China

Zitieren

ISO 690

DOELL, Christoph, Christian BORGELT, 2019. Aggregation of Subclassifications : Methods, Tools and Experiments. 2019 IEEE Symposium Series on Computational Intelligence (SSCI). Xiamen, China, 6. Dez. 2019 - 9. Dez. 2019. In: 2019 IEEE Symposium Series on Computational Intelligence (SSCI). Piscataway, NJ: IEEE, 2019, pp. 3124-3131. ISBN 978-1-72812-485-8. Available under: doi: 10.1109/SSCI44817.2019.9002806

BibTex

@inproceedings{Doell2019Aggre-53223,
  year={2019},
  doi={10.1109/SSCI44817.2019.9002806},
  title={Aggregation of Subclassifications : Methods, Tools and Experiments},
  isbn={978-1-72812-485-8},
  publisher={IEEE},
  address={Piscataway, NJ},
  booktitle={2019 IEEE Symposium Series on Computational Intelligence (SSCI)},
  pages={3124--3131},
  author={Doell, Christoph and Borgelt, Christian}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/53223">
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-03-22T16:08:09Z</dc:date>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/53223"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:language>eng</dc:language>
    <dcterms:title>Aggregation of Subclassifications : Methods, Tools and Experiments</dcterms:title>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-03-22T16:08:09Z</dcterms:available>
    <dc:creator>Doell, Christoph</dc:creator>
    <dc:creator>Borgelt, Christian</dc:creator>
    <dcterms:issued>2019</dcterms:issued>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Borgelt, Christian</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:abstract xml:lang="eng">Aggregation methods have been studied extensively from a mathematical, theoretical point of view. In this work, however, we focus on a more practical aspect: subclassifications. Given class predictions for several sub-objects of a single instance, we systematically investigate the performance of different aggregation methods. To this end, we simulate data for various data distributions. Thus we ensure that we know the ground truth for the evaluation, which would be impossible for real world data. Our source code is publicly available and can be extended to explore other aggregation methods and other data distributions.</dcterms:abstract>
    <dc:contributor>Doell, Christoph</dc:contributor>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja