Issue No. 11 - November (1991 vol. 13)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.103278
<p>A method is proposed which solves the problem of the Bayes classification of ARMA (autoregressive moving average) signals when the models of classes and samples are not exactly known but only estimated from finite-length data sequences. Justified approximations and the hypothesis lead to decision rules including the variances of the estimations. The results obtained on a large set of simulated data show that this approach is superior to the best classical methods (cepstral distance or Kullback divergence), particularly in the common case where the hypothesis of those methods is not verified (short samples. small training sets. random classes).</p>
ARMA signals; optimal approach; random signals classification; Bayes classification; finite-length data sequences; decision rules; cepstral distance; Kullback divergence; Bayes methods; decision theory; pattern recognition; signal processing
C. Doncarli and E. LeCarpentier, "An Optimal Approach for Random Signals Classification," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 13, no. , pp. 1192-1196, 1991.