Activity recognition in collaborative environments

Afsaneh Doryab, Julian Togelius

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We present an approach to learning to recognize concurrent activities based on multiple data streams. One example is recognition of concurrent activities in hospital operating rooms based on multiple wearable and embedded sensors. This problem differs from standard time series classification in that there is no natural single target dimension, as multiple activities are performed at the same time. Hence, most existing approaches fail. The key innovations that allow us to tackle this problem is (1) learning to recognize base activities from raw sensor data, (2) creating artificial joint activities from base activities using frequent pattern mining and (3) handling temporal dependency using virtual evidence boosting.

    Original languageEnglish (US)
    Title of host publication2012 International Joint Conference on Neural Networks, IJCNN 2012
    DOIs
    StatePublished - 2012
    Event2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 - Brisbane, QLD, Australia
    Duration: Jun 10 2012Jun 15 2012

    Other

    Other2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
    CountryAustralia
    CityBrisbane, QLD
    Period6/10/126/15/12

    Fingerprint

    Operating rooms
    Sensors
    Time series
    Innovation

    ASJC Scopus subject areas

    • Software
    • Artificial Intelligence

    Cite this

    Doryab, A., & Togelius, J. (2012). Activity recognition in collaborative environments. In 2012 International Joint Conference on Neural Networks, IJCNN 2012 [6252608] https://doi.org/10.1109/IJCNN.2012.6252608

    Activity recognition in collaborative environments. / Doryab, Afsaneh; Togelius, Julian.

    2012 International Joint Conference on Neural Networks, IJCNN 2012. 2012. 6252608.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Doryab, A & Togelius, J 2012, Activity recognition in collaborative environments. in 2012 International Joint Conference on Neural Networks, IJCNN 2012., 6252608, 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, QLD, Australia, 6/10/12. https://doi.org/10.1109/IJCNN.2012.6252608
    Doryab A, Togelius J. Activity recognition in collaborative environments. In 2012 International Joint Conference on Neural Networks, IJCNN 2012. 2012. 6252608 https://doi.org/10.1109/IJCNN.2012.6252608
    Doryab, Afsaneh ; Togelius, Julian. / Activity recognition in collaborative environments. 2012 International Joint Conference on Neural Networks, IJCNN 2012. 2012.
    @inproceedings{67c9f6860fc842ca8ca6dad66c31de7b,
    title = "Activity recognition in collaborative environments",
    abstract = "We present an approach to learning to recognize concurrent activities based on multiple data streams. One example is recognition of concurrent activities in hospital operating rooms based on multiple wearable and embedded sensors. This problem differs from standard time series classification in that there is no natural single target dimension, as multiple activities are performed at the same time. Hence, most existing approaches fail. The key innovations that allow us to tackle this problem is (1) learning to recognize base activities from raw sensor data, (2) creating artificial joint activities from base activities using frequent pattern mining and (3) handling temporal dependency using virtual evidence boosting.",
    author = "Afsaneh Doryab and Julian Togelius",
    year = "2012",
    doi = "10.1109/IJCNN.2012.6252608",
    language = "English (US)",
    isbn = "9781467314909",
    booktitle = "2012 International Joint Conference on Neural Networks, IJCNN 2012",

    }

    TY - GEN

    T1 - Activity recognition in collaborative environments

    AU - Doryab, Afsaneh

    AU - Togelius, Julian

    PY - 2012

    Y1 - 2012

    N2 - We present an approach to learning to recognize concurrent activities based on multiple data streams. One example is recognition of concurrent activities in hospital operating rooms based on multiple wearable and embedded sensors. This problem differs from standard time series classification in that there is no natural single target dimension, as multiple activities are performed at the same time. Hence, most existing approaches fail. The key innovations that allow us to tackle this problem is (1) learning to recognize base activities from raw sensor data, (2) creating artificial joint activities from base activities using frequent pattern mining and (3) handling temporal dependency using virtual evidence boosting.

    AB - We present an approach to learning to recognize concurrent activities based on multiple data streams. One example is recognition of concurrent activities in hospital operating rooms based on multiple wearable and embedded sensors. This problem differs from standard time series classification in that there is no natural single target dimension, as multiple activities are performed at the same time. Hence, most existing approaches fail. The key innovations that allow us to tackle this problem is (1) learning to recognize base activities from raw sensor data, (2) creating artificial joint activities from base activities using frequent pattern mining and (3) handling temporal dependency using virtual evidence boosting.

    UR - http://www.scopus.com/inward/record.url?scp=84865104562&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84865104562&partnerID=8YFLogxK

    U2 - 10.1109/IJCNN.2012.6252608

    DO - 10.1109/IJCNN.2012.6252608

    M3 - Conference contribution

    SN - 9781467314909

    BT - 2012 International Joint Conference on Neural Networks, IJCNN 2012

    ER -