Dynamic Real-Time Segmentation and Recognition of Activities Using a Multi-feature Windowing Approach

Vorschaubild nicht verfügbar
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2017
Autor:innen
Shahi, Ahmad
Woodford, Brendon J.
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
eISSN
item.preview.dc.identifier.isbn
Bibliografische Daten
Verlag
Schriftenreihe
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Link zur Lizenz
oops
EU-Projektnummer
Projekt
Open Access-Veröffentlichung
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
Trends and Applications in Knowledge Discovery and Data Mining : PAKDD 2017 Workshops, MLSDA, BDM, DM-BPM, Jeju, South Korea, May 23, 2017, revised selected papers / Kang, U et al. (Hrsg.). - Cham : Springer, 2017. - (Lecture notes in artificial intelligence ; 10526). - S. 26-38. - ISSN 0302-9743. - eISSN 1611-3349. - ISBN 978-3-319-67273-1
Zusammenfassung
Segmenting sensor events for activity recognition has many key challenges due to its unsupervised nature, the real-time requirements necessary for on-line event detection, and the possibility of having to recognise overlapping activities. A further challenge is to achieve robustness of classification due to sub-optimal choice of window size. In this paper, we present a novel real-time recognition framework to address these problems. The proposed framework is divided into two phases: off-line modeling and on-line recognition. In the off-line phase a representation called Activity Features (AFs) are built from statistical information about the activities from annotated sensory data and a Naïve Bayesian (NB) classifier is modeled accordingly. In the on-line phase, a dynamic multi-feature windowing approach using AFs and the learnt NB classifier is introduced to segment unlabeled sensor data as well as predicting the related activity. How this on-line segmentation occurs, even in the presence of overlapping activities, diverges from many other studies. Experimental results demonstrate that our framework can outperform the state-of-the-art windowing-based approaches for activity recognition involving datasets acquired from multiple residents in smart home test-beds.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Human activity recognition, On-line stream mining, Real-time, Machine learning, Classification
Konferenz
PAKDD 2017 Workshops, MLSDA, BDM, DM-BPM, 23. Mai 2017, Jeju, South Korea
Rezension
undefined / . - undefined, undefined. - (undefined; undefined)
Zitieren
ISO 690SHAHI, Ahmad, Brendon J. WOODFORD, Hanhe LIN, 2017. Dynamic Real-Time Segmentation and Recognition of Activities Using a Multi-feature Windowing Approach. PAKDD 2017 Workshops, MLSDA, BDM, DM-BPM. Jeju, South Korea, 23. Mai 2017. In: KANG, U, ed. and others. Trends and Applications in Knowledge Discovery and Data Mining : PAKDD 2017 Workshops, MLSDA, BDM, DM-BPM, Jeju, South Korea, May 23, 2017, revised selected papers. Cham:Springer, pp. 26-38. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-67273-1. Available under: doi: 10.1007/978-3-319-67274-8_3
BibTex
@inproceedings{Shahi2017-10-07Dynam-44099,
  year={2017},
  doi={10.1007/978-3-319-67274-8_3},
  title={Dynamic Real-Time Segmentation and Recognition of Activities Using a Multi-feature Windowing Approach},
  number={10526},
  isbn={978-3-319-67273-1},
  issn={0302-9743},
  publisher={Springer},
  address={Cham},
  series={Lecture notes in artificial intelligence},
  booktitle={Trends and Applications in Knowledge Discovery and Data Mining : PAKDD 2017 Workshops, MLSDA, BDM, DM-BPM, Jeju, South Korea, May 23, 2017, revised selected papers},
  pages={26--38},
  editor={Kang, U},
  author={Shahi, Ahmad and Woodford, Brendon J. and Lin, Hanhe}
}
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/123456789/44099">
    <dc:contributor>Woodford, Brendon J.</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/44099"/>
    <dc:creator>Lin, Hanhe</dc:creator>
    <dcterms:issued>2017-10-07</dcterms:issued>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:title>Dynamic Real-Time Segmentation and Recognition of Activities Using a Multi-feature Windowing Approach</dcterms:title>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-11-30T13:02:42Z</dcterms:available>
    <dc:creator>Shahi, Ahmad</dc:creator>
    <dcterms:abstract xml:lang="eng">Segmenting sensor events for activity recognition has many key challenges due to its unsupervised nature, the real-time requirements necessary for on-line event detection, and the possibility of having to recognise overlapping activities. A further challenge is to achieve robustness of classification due to sub-optimal choice of window size. In this paper, we present a novel real-time recognition framework to address these problems. The proposed framework is divided into two phases: off-line modeling and on-line recognition. In the off-line phase a representation called Activity Features (AFs) are built from statistical information about the activities from annotated sensory data and a Naïve Bayesian (NB) classifier is modeled accordingly. In the on-line phase, a dynamic multi-feature windowing approach using AFs and the learnt NB classifier is introduced to segment unlabeled sensor data as well as predicting the related activity. How this on-line segmentation occurs, even in the presence of overlapping activities, diverges from many other studies. Experimental results demonstrate that our framework can outperform the state-of-the-art windowing-based approaches for activity recognition involving datasets acquired from multiple residents in smart home test-beds.</dcterms:abstract>
    <dc:contributor>Shahi, Ahmad</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-11-30T13:02:42Z</dc:date>
    <dc:creator>Woodford, Brendon J.</dc:creator>
    <dc:contributor>Lin, Hanhe</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:language>eng</dc:language>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet