Estimating Human Predictability From Mobile Sensor Data

Bjørn Sand Jensen, Jakob Eg Larsen, Kristian Jensen, Jan Larsen, Lars Kai Hansen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    Abstract

    Quantification of human behavior is of prime interest in many applications ranging from behavioral science to practical applications like GSM resource planning and context-aware services. As proxies for humans, we apply multiple mobile phone sensors all conveying information about human behavior. Using a recent, information theoretic approach it is demonstrated that the trajectories of individual sensors are highly predictable given complete knowledge of the infinite past. We suggest using a new approach to time scale selection which demonstrates that participants have even higher predictability of non-trivial behavior on smaller timer scale than previously considered.
    Original languageEnglish
    Title of host publicationIEEE International Workshop on Machine Learning for Signal Processing
    PublisherIEEE
    Publication date2010
    ISBN (Print)978-1-4244-7875-0
    DOIs
    Publication statusPublished - 2010
    Event2010 IEEE International Workshop on Machine Learning for Signal Processing - Kittilä, Finland
    Duration: 29 Aug 20101 Sep 2010
    http://mlsp2010.conwiz.dk/

    Workshop

    Workshop2010 IEEE International Workshop on Machine Learning for Signal Processing
    CountryFinland
    CityKittilä
    Period29/08/201001/09/2010
    Internet address

    Fingerprint Dive into the research topics of 'Estimating Human Predictability From Mobile Sensor Data'. Together they form a unique fingerprint.

    Cite this