This paper identifies a bound for the worst‐case (largest) missed‐detection and false‐alarm probabilities for a chi‐square monitor in which the input signal vector cannot be perfectly decorrelated. A new method for bounding monitor missed‐detection performance is introduced that leverages the aspect ratio (aka, condition number) for the covariance matrix of the imperfectly decorrelated signal. An application to signal deformation monitoring for the global positioning system indicates that the new bound is both tight and relatively inexpensive to compute. Copyright © 2017 Institute of Navigation


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Robust Chi‐square Monitor Performance with Noise Covariance of Unknown Aspect Ratio


    Contributors:

    Published in:

    Navigation ; 64 , 3 ; 377-389


    Publication date :

    2017




    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English



    Classification :

    BKL:    53.84 Ortungstechnik, Radartechnik / 55.86 Schiffsverkehr, Schifffahrt / 55.54 Flugführung
    Local classification TIB:    770/5680/7035




    Robust Chi-Square Monitor Performance with Noise Covariance of Unknown Aspect-Ratio

    Rife, Jason | British Library Conference Proceedings | 2016


    Variational Nonlinear Kalman Filtering With Unknown Process Noise Covariance

    Lan, Hua / Hu, Jinjie / Wang, Zengfu et al. | IEEE | 2023


    The Effect of Uncertain Covariance on a Chi-Square Integrity Monitor

    Rife, J. H. | British Library Online Contents | 2013