Towards visual debugging for multi-target time series classification

Schlegel, Udo; Cakmak, Eren; Arnout, Hiba; El-Assady, Mennatallah; Oelke, Daniela; Keim, Daniel A.

Towards visual debugging for multi-target time series classification

Dateien

Schlegel_2-111pfyzk81o0c5.pdfGröße: 1.17 MBDownloads: 187

Datum

2020

Autor:innen

Schlegel, Udo

Cakmak, Eren

Arnout, Hiba

El-Assady, Mennatallah

Oelke, Daniela

Keim, Daniel A.

EU-Projektnummer

830892

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

PATERNÒ, Fabio, ed., Nuria OLIVER, ed.. IUI '20 : Proceedings of the 25th International Conference on Intelligent User Interfaces. New York, NY: ACM, 2020, pp. 202-206. ISBN 978-1-4503-7118-6. Available under: doi: 10.1145/3377325.3377528

Zusammenfassung

Multi-target classification of multivariate time series data poses a challenge in many real-world applications (e.g., predictive maintenance). Machine learning methods, such as random forests and neural networks, support training these classifiers. However, the debugging and analysis of possible misclassifications remain challenging due to the often complex relations between targets, classes, and the multivariate time series data. We propose a model-agnostic visual debugging workflow for multi-target time series classification that enables the examination of relations between targets, partially correct predictions, potential confusions, and the classified time series data. The workflow, as well as the prototype, aims to foster an in-depth analysis of multi-target classification results to identify potential causes of mispredictions visually. We demonstrate the usefulness of the workflow in the field of predictive maintenance in a usage scenario to show how users can iteratively explore and identify critical classes, as well as, relationships between targets.

Fachgebiet (DDC)

004 Informatik

Konferenz

IUI '20: 25th International Conference on Intelligent User Interfaces, 17. März 2020 - 20. März 2020, Cagliari, Italy

Zitieren

ISO 690

SCHLEGEL, Udo, Eren CAKMAK, Hiba ARNOUT, Mennatallah EL-ASSADY, Daniela OELKE, Daniel A. KEIM, 2020. Towards visual debugging for multi-target time series classification. IUI '20: 25th International Conference on Intelligent User Interfaces. Cagliari, Italy, 17. März 2020 - 20. März 2020. In: PATERNÒ, Fabio, ed., Nuria OLIVER, ed.. IUI '20 : Proceedings of the 25th International Conference on Intelligent User Interfaces. New York, NY: ACM, 2020, pp. 202-206. ISBN 978-1-4503-7118-6. Available under: doi: 10.1145/3377325.3377528

BibTex

@inproceedings{Schlegel2020Towar-53085,
  year={2020},
  doi={10.1145/3377325.3377528},
  title={Towards visual debugging for multi-target time series classification},
  isbn={978-1-4503-7118-6},
  publisher={ACM},
  address={New York, NY},
  booktitle={IUI '20 : Proceedings of the 25th International Conference on Intelligent User Interfaces},
  pages={202--206},
  editor={Paternò, Fabio and Oliver, Nuria},
  author={Schlegel, Udo and Cakmak, Eren and Arnout, Hiba and El-Assady, Mennatallah and Oelke, Daniela and Keim, Daniel A.}
}

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/123456789/53085">
    <dc:contributor>Oelke, Daniela</dc:contributor>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/53085/1/Schlegel_2-111pfyzk81o0c5.pdf"/>
    <dcterms:title>Towards visual debugging for multi-target time series classification</dcterms:title>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dc:creator>El-Assady, Mennatallah</dc:creator>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/53085"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-03-05T10:24:21Z</dcterms:available>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>El-Assady, Mennatallah</dc:contributor>
    <dcterms:abstract xml:lang="eng">Multi-target classification of multivariate time series data poses a challenge in many real-world applications (e.g., predictive maintenance). Machine learning methods, such as random forests and neural networks, support training these classifiers. However, the debugging and analysis of possible misclassifications remain challenging due to the often complex relations between targets, classes, and the multivariate time series data. We propose a model-agnostic visual debugging workflow for multi-target time series classification that enables the examination of relations between targets, partially correct predictions, potential confusions, and the classified time series data. The workflow, as well as the prototype, aims to foster an in-depth analysis of multi-target classification results to identify potential causes of mispredictions visually. We demonstrate the usefulness of the workflow in the field of predictive maintenance in a usage scenario to show how users can iteratively explore and identify critical classes, as well as, relationships between targets.</dcterms:abstract>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Arnout, Hiba</dc:contributor>
    <dc:language>eng</dc:language>
    <dc:contributor>Cakmak, Eren</dc:contributor>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dc:creator>Schlegel, Udo</dc:creator>
    <dc:contributor>Schlegel, Udo</dc:contributor>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/53085/1/Schlegel_2-111pfyzk81o0c5.pdf"/>
    <dcterms:issued>2020</dcterms:issued>
    <dc:creator>Oelke, Daniela</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-03-05T10:24:21Z</dc:date>
    <dc:creator>Arnout, Hiba</dc:creator>
    <dc:creator>Cakmak, Eren</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja