Premium
Performance analysis of cumulant‐based detection of non‐gaussian signals
Author(s) -
Porat Boaz,
Friedlander Benjamin
Publication year - 1996
Publication title -
international journal of adaptive control and signal processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.73
H-Index - 66
eISSN - 1099-1115
pISSN - 0890-6327
DOI - 10.1002/(sici)1099-1115(199603)10:2/3<99::aid-acs343>3.0.co;2-#
Subject(s) - cumulant , gaussian , computer science , pattern recognition (psychology) , mathematics , speech recognition , statistics , artificial intelligence , physics , quantum mechanics
We consider the problem of detecting a linear stationary non‐Gaussian signal in additive Gaussian noise. Detection is assumed to be done in two steps: first a selected set of sample cumulants and/or moments of the data is computed; next a detection statistic based on these sample moments/cumulants is evaluated. Three types of detectors are considered: a likelihood ratio (optimal) detector, a weighted energy detector and a simple energy detector. The paper provides asymptotic performance analysis of these detectors for MA and ARMA signal and noise models. A simple example is worked out in detail.