Phase registration improves classification and clustering of cycles based on self-organizing maps

Quintana-Duque, Juan-Carlos; Saupe, Dietmar

Phase registration improves classification and clustering of cycles based on self-organizing maps

Dateien

Quintana-Duque_2-1wmkwmq3x69e00.pdfGröße: 318.49 KBDownloads: 165

Datum

2015

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

URBAN, Bodo, ed. and others. WOAR '15 : Proceedings of the 2nd international Workshop on Sensor-based Activity Recognition and Interaction. New York: ACM, 2015, 5. ISBN 978-1-4503-3454-9. Available under: doi: 10.1145/2790044.2790053

Zusammenfassung

Self-Organizing Maps (SOMs), also known as Self-Organizing Feature Maps, have been used to reduce the complexity of joint kinematic and kinetic data in order to cluster, classify and visualize cyclic motion data. In this paper we describe the results after training SOMs with preprocessed data based on phase registration by dynamic time warping. For validation, we recorded acceleration data of human locomotion varying the treadmill slope, activity (i.e., walking, jogging, running), and whether or not 1.5 kg weights were attached to the ankles. The topological quality of the SOMs after training improved when the phase registration was applied. Furthermore, test (i.e., combination of treadmill slope and type of gait) and subject classification improved, in particular for walking data, when the phase registration was applied for each individual activity. Activity classification improved when the phase registration was calculated from all cycles of our experiments together.

Fachgebiet (DDC)

004 Informatik

Konferenz

WOAR '15, 2nd international Workshop on Sensor-based Activity Recognition and Interaction, 25. Juni 2015 - 26. Juni 2015, Rostock

Zitieren

ISO 690

QUINTANA-DUQUE, Juan-Carlos, Dietmar SAUPE, 2015. Phase registration improves classification and clustering of cycles based on self-organizing maps. WOAR '15, 2nd international Workshop on Sensor-based Activity Recognition and Interaction. Rostock, 25. Juni 2015 - 26. Juni 2015. In: URBAN, Bodo, ed. and others. WOAR '15 : Proceedings of the 2nd international Workshop on Sensor-based Activity Recognition and Interaction. New York: ACM, 2015, 5. ISBN 978-1-4503-3454-9. Available under: doi: 10.1145/2790044.2790053

BibTex

@inproceedings{QuintanaDuque2015Phase-31854,
  year={2015},
  doi={10.1145/2790044.2790053},
  title={Phase registration improves classification and clustering of cycles based on self-organizing maps},
  isbn={978-1-4503-3454-9},
  publisher={ACM},
  address={New York},
  booktitle={WOAR '15 : Proceedings of the 2nd international Workshop on Sensor-based Activity Recognition and Interaction},
  editor={Urban, Bodo},
  author={Quintana-Duque, Juan-Carlos and Saupe, Dietmar},
  note={Article Number: 5}
}

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/123456789/31854">
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2015-09-29T10:07:20Z</dc:date>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:abstract xml:lang="eng">Self-Organizing Maps (SOMs), also known as Self-Organizing Feature Maps, have been used to reduce the complexity of joint kinematic and kinetic data in order to cluster, classify and visualize cyclic motion data. In this paper we describe the results after training SOMs with preprocessed data based on phase registration by dynamic time warping. For validation, we recorded acceleration data of human locomotion varying the treadmill slope, activity (i.e., walking, jogging, running), and whether or not 1.5 kg weights were attached to the ankles. The topological quality of the SOMs after training improved when the phase registration was applied. Furthermore, test (i.e., combination of treadmill slope and type of gait) and subject classification improved, in particular for walking data, when the phase registration was applied for each individual activity. Activity classification improved when the phase registration was calculated from all cycles of our experiments together.</dcterms:abstract>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/31854"/>
    <dc:rights>terms-of-use</dc:rights>
    <dc:contributor>Quintana-Duque, Juan-Carlos</dc:contributor>
    <dcterms:title>Phase registration improves classification and clustering of cycles based on self-organizing maps</dcterms:title>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/31854/1/Quintana-Duque_2-1wmkwmq3x69e00.pdf"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:issued>2015</dcterms:issued>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/31854/1/Quintana-Duque_2-1wmkwmq3x69e00.pdf"/>
    <dc:creator>Saupe, Dietmar</dc:creator>
    <dc:language>eng</dc:language>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2015-09-29T10:07:20Z</dcterms:available>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Saupe, Dietmar</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Quintana-Duque, Juan-Carlos</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja