Feature learning for activity recognition in ubiquitous computing

Thomas Plötz, Nils Y. Hammerla, Patrick Olivier

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    243 Citations (Scopus)

    Abstract

    Feature extraction for activity recognition in context-aware ubiquitous computing applications is usually a heuristic process, informed by underlying domain knowledge. Relying on such explicit knowledge is problematic when aiming to generalize across different application domains. We investigate the potential of recent machine learning methods for discovering universal features for context-aware applications of activity recognition. We also describe an alternative data representation based on the empirical cumulative distribution function of the raw data, which effectively abstracts from absolute values. Experiments on accelerometer data from four publicly available activity recognition datasets demonstrate the significant potential of our approach to address both contemporary activity recognition tasks and next generation problems such as skill assessment and the detection of novel activities.

    Original languageEnglish
    Title of host publicationIJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence
    Pages1729-1734
    Number of pages6
    DOIs
    Publication statusPublished - 1 Dec 2011
    EventInternational Joint Conference on Artificial Intelligence 2011 - Barcelona Catalonia, Spain
    Duration: 16 Jul 201122 Jul 2011
    Conference number: 22nd
    https://www.ijcai.org/proceedings/2011 (conference proceedings)

    Conference

    ConferenceInternational Joint Conference on Artificial Intelligence 2011
    Abbreviated titleIJCAI 2011
    CountrySpain
    CityBarcelona Catalonia
    Period16/07/1122/07/11
    Internet address

    Cite this