EM algorithm for sequence estimation over Gauss-Markov ISI channels

Author

Perry, Richard ; Berger, W. Andrew ; Buckley, Kevin

Author_Institution

Dept. of Electr. & Comput. Eng., Villanova Univ., PA, USA

Volume

1

fYear

2000

fDate

2000

Firstpage

16

Abstract

This paper presents a new algorithm, based on an EM (expectation-maximization) formulation, for ML (maximum likelihood) sequence estimation over unknown ISI (inter-symbol interference) channels with random channel coefficients which have a Gauss-Markov fast time-varying distribution. By using the EM formulation to marginalize over the channel coefficient distribution, maximum-likelihood estimates of the transmitted sequence are obtained. This EM algorithm is shown to perform better, in terms of BER, than existing algorithms which perform jointly-optimal sequence and channel estimation, or which do not take into account fast time-varying channel effects

Keywords

Gaussian distribution; error statistics; intersymbol interference; maximum likelihood sequence estimation; optimisation; phase shift keying; time-varying channels; transient response; BER; BPSK; EM algorithm; Gauss-Markov ISI channels; Gauss-Markov fast time-varying distribution; MLSE; channel coefficient distribution; channel estimation; expectation-maximization; fast time-varying channel effects; intersymbol interference; jointly-optimal sequence estimation; maximum likelihood sequence estimation; maximum-likelihood estimates; optimal channel estimation; random FIR channels; random channel coefficients; transmitted sequence; Bit error rate; Channel estimation; Finite impulse response filter; Gaussian channels; Gaussian distribution; Integrated circuit noise; Intersymbol interference; Maximum likelihood estimation; Signal processing algorithms; Time-varying channels;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, 2000. ICC 2000. 2000 IEEE International Conference on

Conference_Location

New Orleans, LA

Print_ISBN

0-7803-6283-7

Type

conf

DOI

10.1109/ICC.2000.853055

Filename

853055