Skip to main navigation Skip to search Skip to main content

Unobtrusive gait recognition using smartwatches

  • Neamah Al-Naffakh
  • , Nathan Clarke
  • , Fudong Li
  • , Paul Haskell-Dowland

    Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

    227 Downloads (Pure)

    Abstract

    Gait recognition is a technique that identifies or verifies people based upon their walking patterns. Smartwatches, which contain an accelerometer and gyroscope have recently been used to implement gait-based biometrics. However, this prior work relied upon data from single sessions for both training and testing, which is not realistic and can lead to overly optimistic performance results. This paper aims to remedy some of these problems by training and evaluating a smartwatch-based biometric system on data obtained from different days. Also, it proposes an advanced feature selection approach to identify optimal features for each user. Two experiments are presented under three different scenarios: Same-Day, Mixed-Day, and Cross-Day. Competitive results were achieved (best EERs of 0.13% and 3.12% by using the Same day data for accelerometer and gyroscope respectively and 0.69% and 7.97% for the same sensors under the Cross-Day evaluation. The results show that the technology is sufficiently capable and the signals captured sufficiently discriminative to be useful in performing gait recognition.

    Original languageEnglish
    Title of host publication2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages110-114
    ISBN (Electronic)978-3885796640
    ISBN (Print)978-1538603963
    DOIs
    Publication statusPublished - 2 Oct 2017
    Event2017 International Conference of the Biometrics Special Interest Group - Darmstadt, Germany
    Duration: 20 Sept 2017 → 22 Sept 2017

    Publication series

    NameIEEE BIOSIG Proceedings Series
    ISSN (Electronic)1617-5468

    Conference

    Conference2017 International Conference of the Biometrics Special Interest Group
    Abbreviated titleBIOSIG 2017
    Country/TerritoryGermany
    CityDarmstadt
    Period20/09/17 → 22/09/17

    Keywords

    • accelerometer
    • gait biometrics
    • mobile authentication
    • smartwatch authentication

    Fingerprint

    Dive into the research topics of 'Unobtrusive gait recognition using smartwatches'. Together they form a unique fingerprint.

    Cite this