Localization using radial basis function networks and signal strength fingerprints in WLAN

Christos Laoudias, Paul Kemppi, G. Panayiotou Christos

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

    43 Citations (Scopus)

    Abstract

    Fingerprinting localization techniques provide reliable location estimates and enable the development of location aware applications especially for indoor environments, where satellite based positioning is infeasible. In our approach we utilize Received Signal Strength (RSS) fingerprints collected in known locations and employ a Radial Basis Function (RBF) neural network to approximate the function that maps fingerprints to location coordinates. We present a clustering scheme to reduce the size and computational complexity of the RBF architecture and demonstrate the applicability of this approach in a real-world WLAN setup. Experimental results indicate that the RBF based method is an efficient approach to the location determination problem that outperforms existing techniques in terms of the positioning error.
    Original languageEnglish
    Title of host publicationProceedings of GLOBECOM 2009
    Subtitle of host publication2009 IEEE Global Telecommunications Conference
    PublisherIEEE Institute of Electrical and Electronic Engineers
    Number of pages6
    ISBN (Print)978-1-4244-4148-8
    DOIs
    Publication statusPublished - 2009
    MoE publication typeA4 Article in a conference publication
    EventIEEE Global Telecommunications Conference, GLOBECOM 2009 - Honolulu, United States
    Duration: 30 Nov 20094 Dec 2009

    Conference

    ConferenceIEEE Global Telecommunications Conference, GLOBECOM 2009
    Abbreviated titleGLOBECOM 2009
    CountryUnited States
    CityHonolulu
    Period30/11/094/12/09

    Fingerprint

    Radial basis function networks
    Wireless local area networks (WLAN)
    Computational complexity
    Satellites
    Neural networks

    Keywords

    • fingerprinting
    • localization
    • Radial Basis Function Networks
    • received signal strength
    • WLAN

    Cite this

    Laoudias, C., Kemppi, P., & Panayiotou Christos, G. (2009). Localization using radial basis function networks and signal strength fingerprints in WLAN. In Proceedings of GLOBECOM 2009: 2009 IEEE Global Telecommunications Conference IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/GLOCOM.2009.5425278
    Laoudias, Christos ; Kemppi, Paul ; Panayiotou Christos, G. / Localization using radial basis function networks and signal strength fingerprints in WLAN. Proceedings of GLOBECOM 2009: 2009 IEEE Global Telecommunications Conference. IEEE Institute of Electrical and Electronic Engineers , 2009.
    @inproceedings{aa4ed781e54b4e4db49d1ed601985795,
    title = "Localization using radial basis function networks and signal strength fingerprints in WLAN",
    abstract = "Fingerprinting localization techniques provide reliable location estimates and enable the development of location aware applications especially for indoor environments, where satellite based positioning is infeasible. In our approach we utilize Received Signal Strength (RSS) fingerprints collected in known locations and employ a Radial Basis Function (RBF) neural network to approximate the function that maps fingerprints to location coordinates. We present a clustering scheme to reduce the size and computational complexity of the RBF architecture and demonstrate the applicability of this approach in a real-world WLAN setup. Experimental results indicate that the RBF based method is an efficient approach to the location determination problem that outperforms existing techniques in terms of the positioning error.",
    keywords = "fingerprinting, localization, Radial Basis Function Networks, received signal strength, WLAN",
    author = "Christos Laoudias and Paul Kemppi and {Panayiotou Christos}, G.",
    year = "2009",
    doi = "10.1109/GLOCOM.2009.5425278",
    language = "English",
    isbn = "978-1-4244-4148-8",
    booktitle = "Proceedings of GLOBECOM 2009",
    publisher = "IEEE Institute of Electrical and Electronic Engineers",
    address = "United States",

    }

    Laoudias, C, Kemppi, P & Panayiotou Christos, G 2009, Localization using radial basis function networks and signal strength fingerprints in WLAN. in Proceedings of GLOBECOM 2009: 2009 IEEE Global Telecommunications Conference. IEEE Institute of Electrical and Electronic Engineers , IEEE Global Telecommunications Conference, GLOBECOM 2009, Honolulu, United States, 30/11/09. https://doi.org/10.1109/GLOCOM.2009.5425278

    Localization using radial basis function networks and signal strength fingerprints in WLAN. / Laoudias, Christos; Kemppi, Paul; Panayiotou Christos, G.

    Proceedings of GLOBECOM 2009: 2009 IEEE Global Telecommunications Conference. IEEE Institute of Electrical and Electronic Engineers , 2009.

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

    TY - GEN

    T1 - Localization using radial basis function networks and signal strength fingerprints in WLAN

    AU - Laoudias, Christos

    AU - Kemppi, Paul

    AU - Panayiotou Christos, G.

    PY - 2009

    Y1 - 2009

    N2 - Fingerprinting localization techniques provide reliable location estimates and enable the development of location aware applications especially for indoor environments, where satellite based positioning is infeasible. In our approach we utilize Received Signal Strength (RSS) fingerprints collected in known locations and employ a Radial Basis Function (RBF) neural network to approximate the function that maps fingerprints to location coordinates. We present a clustering scheme to reduce the size and computational complexity of the RBF architecture and demonstrate the applicability of this approach in a real-world WLAN setup. Experimental results indicate that the RBF based method is an efficient approach to the location determination problem that outperforms existing techniques in terms of the positioning error.

    AB - Fingerprinting localization techniques provide reliable location estimates and enable the development of location aware applications especially for indoor environments, where satellite based positioning is infeasible. In our approach we utilize Received Signal Strength (RSS) fingerprints collected in known locations and employ a Radial Basis Function (RBF) neural network to approximate the function that maps fingerprints to location coordinates. We present a clustering scheme to reduce the size and computational complexity of the RBF architecture and demonstrate the applicability of this approach in a real-world WLAN setup. Experimental results indicate that the RBF based method is an efficient approach to the location determination problem that outperforms existing techniques in terms of the positioning error.

    KW - fingerprinting

    KW - localization

    KW - Radial Basis Function Networks

    KW - received signal strength

    KW - WLAN

    U2 - 10.1109/GLOCOM.2009.5425278

    DO - 10.1109/GLOCOM.2009.5425278

    M3 - Conference article in proceedings

    SN - 978-1-4244-4148-8

    BT - Proceedings of GLOBECOM 2009

    PB - IEEE Institute of Electrical and Electronic Engineers

    ER -

    Laoudias C, Kemppi P, Panayiotou Christos G. Localization using radial basis function networks and signal strength fingerprints in WLAN. In Proceedings of GLOBECOM 2009: 2009 IEEE Global Telecommunications Conference. IEEE Institute of Electrical and Electronic Engineers . 2009 https://doi.org/10.1109/GLOCOM.2009.5425278