Maximum likelihood trend estimation in exponential noise

Author

Trump, Tõnu

Author_Institution

Ericsson Radio Syst. AB, Stockholm, Sweden

Volume

49

Issue

9

fYear

2001

fDate

9/1/2001 12:00:00 AM

Firstpage

2087

Lastpage

2095

Abstract

This paper considers the problem of estimating a linear trend in noise, where the noise is modeled as independent and identically distributed (i.i.d.) random process with exponential distribution. The corresponding maximum likelihood parameter estimator of the trend and noise parameters is derived, and its performance is analyzed. It turns out that the resulting maximum likelihood estimator has to solve a linear programming problem with number of constraints equal to the number of received data. A recursive form of the maximum likelihood estimator, which makes it suitable for implementation in real-time systems, is then proposed. The memory requirements of the recursive algorithm are data dependent and are investigated by simulations using both computer-generated and recorded data sets

Keywords

digital simulation; exponential distribution; least squares approximations; linear programming; maximum likelihood estimation; packet switching; random noise; recursive estimation; signal sampling; telecommunication networks; MLE; computer-generated data sets; exponential distribution; exponential noise; i.i.d. random process; independent identically distributed random process; least squares estimator; linear programming problem; linear trend estimation; maximum likelihood parameter estimator; maximum likelihood trend estimation; memory requirements; noise parameters; packet switched network; performance analysis; received data; recorded data sets; recursive algorithm; recursive maximum likelihood estimator; signal sampling; simulations; trend parameters; Computational modeling; Computer simulation; Exponential distribution; Linear programming; Maximum likelihood estimation; Parameter estimation; Performance analysis; Random processes; Real time systems; Recursive estimation;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.942636

Filename

942636