The need for a cognitive radio in aeronautical mobile telemetry is motivated by the simultaneous use of three different versions of continuous phase modulation and bitrates that vary from test article to test article. The cognitive radio envisioned in this article comprises two parts: a machine learning algorithm that determines modulation type and bitrate, and a software-defined radio that performs demodulation and detection. The experiments presented in this article show that a quadratic discriminant classifier operating on power spectral density (PSD) estimates can successfully identify the modulation. Following the classifier, a Gaussian process regression model operating on the same PSD estimate can estimate the bitrate.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Cognitive Radio for Aeronautical Mobile Telemetry: A Machine Learning-Based Approach


    Beteiligte:
    Nelson, Nathan (Autor:in) / Garcia, Esteban (Autor:in) / Harris, Rachel (Autor:in) / Rice, Michael (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.06.2022


    Format / Umfang :

    1372513 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Aeronautical Telemetry Systems

    Stacey, Dale | Wiley | 2008



    Cellular 4G LTE Aeronautical Mobile Telemetry Flight Test Results

    Beck, E. / Erramilli, S. / Habiby, S. et al. | TIBKAT | 2020


    FEC Systems for Aeronautical Telemetry

    Perrins, Erik | IEEE | 2013


    Space–Time Block-Coded ARTM CPM for Aeronautical Mobile Telemetry

    Josephson, Chad / Perrins, Erik / Rice, Michael | IEEE | 2022