RF Based Real Time Human Motion Sensing

William Taylor, Ahmad Taha, Kia Dashtipour, Syed Aziz Shah, Qammer H. Abbasi, Muhammad Ali Imran

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

    1 Citation (Scopus)

    Abstract

    Recent research has shown that the propagation of Radio Frequencies signals is affected by human movements taking place between the RF transmitter and receiver antennas. Artificial intelligence has been widely used to classify the patterns of signal propagation. With the help of a universal software radio peripheral device, a system was developed based on a real-time machine learning classification algorithm to ensure alerts of incidents are received in a timely manner. The machine learning model was built to distinguish between “No Activity” and “Movement” status of a single human subject. The model recorded a high classification accuracy of 97.8 % which enabled an accurate classification of new data in real-time.
    Original languageEnglish
    Title of host publication2021 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, APS/URSI 2021 - Proceedings
    PublisherIEEE
    Pages2044-2045
    Number of pages2
    ISBN (Electronic)978-1-7281-4670-6
    DOIs
    Publication statusPublished - 16 Feb 2022
    Event2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting - Singapore, Singapore
    Duration: 4 Dec 202110 Dec 2021
    https://2021apsursi.org/

    Publication series

    Name2021 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, APS/URSI 2021 - Proceedings

    Conference

    Conference2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting
    Abbreviated titleAPS/URSI
    Country/TerritorySingapore
    CitySingapore
    Period4/12/2110/12/21
    Internet address

    Bibliographical note

    Funding Information:
    V. ACKNOWLEDGEMENT William Taylor’s studentship is funded by CENSIS UK through Scottish funding council in collaboration with British Telecom. This work is supported in parts by EPSRC EP/T021020/1 and EP/T021063/1

    Publisher Copyright:
    © 2021 IEEE.

    Keywords

    • Human motion detection
    • Channel State Information
    • RF signals
    • Machine Learning
    • Real-time

    Fingerprint

    Dive into the research topics of 'RF Based Real Time Human Motion Sensing'. Together they form a unique fingerprint.

    Cite this