@inproceedings{12f7f985cb5f4478a009d498981afc27,
title = "A random time-series decomposition and its applications in time-series identification",
abstract = "In this paper a decomposition of observed mixtures of wide-sense stationary time-series coming from different sources into the corresponding orthogonal components being autoregressive-moving-average (ARMA) time-series is proposed. The first step is to estimate power spectral density or autocorrelation function for the observed mixture. Models of the mentioned orthogonal components are obtained by an optimisation algorithm utilizing ideas of randomized search. Exemplary applications of the proposed decomposition in identification of ARMA time-series models using ultra low- and ultra high-power measurements obtained with data acquisition system equipped with quantizer having saturation as well as in identification of ARMA components of time-series being outputs of classical Wiener or Hammerstein systems excited by white noise are presented. The presented discussion is illustrated by a set of simulated identification experiments.",
author = "Jaroslaw Figwer",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 21st International Conference on Methods and Models in Automation and Robotics, MMAR 2016 ; Conference date: 29-08-2016 Through 01-09-2016",
year = "2016",
month = sep,
day = "22",
doi = "10.1109/MMAR.2016.7575134",
language = "English",
series = "2016 21st International Conference on Methods and Models in Automation and Robotics, MMAR 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "206--211",
booktitle = "2016 21st International Conference on Methods and Models in Automation and Robotics, MMAR 2016",
address = "United States",
}