Combining Non-stationary Prediction, Optimization and Mixing for Data Compression

Author

Mattern, Christopher

Author_Institution

Fak. fur Inf. und Automatisierung, Tech. Univ. Ilmenau, Ilmenau, Germany

fYear

2011

fDate

21-24 June 2011

Firstpage

29

Lastpage

37

Abstract

In this paper an approach to modelling nonstationary binary sequences, i.e., predicting the probability of upcoming symbols, is presented. After studying the prediction model we evaluate its performance in two non-artificial test cases. First the model is compared to the Laplace and Krichevsky-Trofimov estimators. Secondly a statistical ensemble model for compressing Burrows-Wheeler-Transform output is worked out and evaluated. A systematic approach to the parameter optimization of an individual model and the ensemble model is stated.

Keywords

Laplace equations; data compression; optimisation; Burrows-Wheeler-Transform output; Krichevsky-Trofimov estimators; Laplace estimators; data compression; nonstationary prediction; parameter optimization; Approximation methods; Compression algorithms; Context; Numerical models; Optimization; Predictive models; Switches; combining models; data compression; ensemble prediction; mixing; numerical optimization; parameter optimization; sequential prediction;

fLanguage

English

Publisher

ieee

Conference_Titel

Data Compression, Communications and Processing (CCP), 2011 First International Conference on

Conference_Location

Palinuro

Print_ISBN

978-1-4577-1458-0

Electronic_ISBN

978-0-7695-4528-8

Type

conf

DOI

10.1109/CCP.2011.22

Filename

6061024