Signal Detection and Classification Using Matched Filtering and Higher Order Statistics

Georgios B. Giannakis, Michail K. Tsatsanis

Research output: Contribution to journalArticle

129 Scopus citations

Abstract

Signal detection and classification in the presence of additive Gaussian noise can be performed using higher than second-order statistics of the matched filter output. Deterministic and random, non-Gaussian distributed signals are detected via multiple correlations and cumulants, respectively. The detection algorithm is computationally simple, and contrary to standard matched filtering, it is insensitive to signal shifts, and does not require knowledge of the noise spectrum for prewhitening. The detector can be viewed as a likelihood ratio test between sampled higher order statistics, and its performance is evaluated using binary hypothesis testing. Signals are classified based on higher order statistics after designing them to have equal higher order correlation energies. Two-dimensional extensions of the one-dimensional algorithms are discussed briefly. Simulations illustrate successful performance of the detection and classification algorithms at low signal-to-noise ratio.

Original languageEnglish (US)
Pages (from-to)1284-1296
Number of pages13
JournalIEEE Transactions on Acoustics, Speech, and Signal Processing
Volume38
Issue number7
DOIs
StatePublished - Jul 1990

Fingerprint Dive into the research topics of 'Signal Detection and Classification Using Matched Filtering and Higher Order Statistics'. Together they form a unique fingerprint.

  • Cite this