Least squares matrix algorithm for state-space modelling of dynamic systems

Juuso T. Olkkonen (Corresponding Author), Hannu Olkkonen

Research output: Contribution to journalArticleScientificpeer-review

Abstract

This work presents a novel least squares matrix algorithm (LSM) for the analysis of rapidly changing systems using state-space modelling. The LSM algorithm is based on the Hankel structured data matrix representation. The state transition matrix is updated without the use of any forgetting function. This yields a robust estimation of model parameters in the presence of noise. The computational complexity of the LSM algorithm is comparable to the speed of the conventional recursive least squares (RLS) algorithm. The knowledge of the state transition matrix enables feasible numerical operators such as interpolation, fractional differentiation and integration. The usefulness of the LSM algorithm was proved in the analysis of the neuroelectric signal waveforms.
Original languageEnglish
Pages (from-to)287-291
JournalJournal of Signal and Information Processing
Volume2
Issue number4
DOIs
Publication statusPublished - 2011
MoE publication typeA1 Journal article-refereed

Fingerprint

Dynamical systems
Differentiation (calculus)
Mathematical operators
Computational complexity
Interpolation

Keywords

  • State-Space Modelling
  • Dynamic System Analysis
  • EEG

Cite this

Olkkonen, Juuso T. ; Olkkonen, Hannu. / Least squares matrix algorithm for state-space modelling of dynamic systems. In: Journal of Signal and Information Processing. 2011 ; Vol. 2, No. 4. pp. 287-291.
@article{27d5183efbaa43e5a7da6eba7b423862,
title = "Least squares matrix algorithm for state-space modelling of dynamic systems",
abstract = "This work presents a novel least squares matrix algorithm (LSM) for the analysis of rapidly changing systems using state-space modelling. The LSM algorithm is based on the Hankel structured data matrix representation. The state transition matrix is updated without the use of any forgetting function. This yields a robust estimation of model parameters in the presence of noise. The computational complexity of the LSM algorithm is comparable to the speed of the conventional recursive least squares (RLS) algorithm. The knowledge of the state transition matrix enables feasible numerical operators such as interpolation, fractional differentiation and integration. The usefulness of the LSM algorithm was proved in the analysis of the neuroelectric signal waveforms.",
keywords = "State-Space Modelling, Dynamic System Analysis, EEG",
author = "Olkkonen, {Juuso T.} and Hannu Olkkonen",
year = "2011",
doi = "10.4236/jsip.2011.24041",
language = "English",
volume = "2",
pages = "287--291",
journal = "Journal of Signal and Information Processing",
issn = "2159-4465",
publisher = "Scientific Research Publishing",
number = "4",

}

Least squares matrix algorithm for state-space modelling of dynamic systems. / Olkkonen, Juuso T. (Corresponding Author); Olkkonen, Hannu.

In: Journal of Signal and Information Processing, Vol. 2, No. 4, 2011, p. 287-291.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Least squares matrix algorithm for state-space modelling of dynamic systems

AU - Olkkonen, Juuso T.

AU - Olkkonen, Hannu

PY - 2011

Y1 - 2011

N2 - This work presents a novel least squares matrix algorithm (LSM) for the analysis of rapidly changing systems using state-space modelling. The LSM algorithm is based on the Hankel structured data matrix representation. The state transition matrix is updated without the use of any forgetting function. This yields a robust estimation of model parameters in the presence of noise. The computational complexity of the LSM algorithm is comparable to the speed of the conventional recursive least squares (RLS) algorithm. The knowledge of the state transition matrix enables feasible numerical operators such as interpolation, fractional differentiation and integration. The usefulness of the LSM algorithm was proved in the analysis of the neuroelectric signal waveforms.

AB - This work presents a novel least squares matrix algorithm (LSM) for the analysis of rapidly changing systems using state-space modelling. The LSM algorithm is based on the Hankel structured data matrix representation. The state transition matrix is updated without the use of any forgetting function. This yields a robust estimation of model parameters in the presence of noise. The computational complexity of the LSM algorithm is comparable to the speed of the conventional recursive least squares (RLS) algorithm. The knowledge of the state transition matrix enables feasible numerical operators such as interpolation, fractional differentiation and integration. The usefulness of the LSM algorithm was proved in the analysis of the neuroelectric signal waveforms.

KW - State-Space Modelling

KW - Dynamic System Analysis

KW - EEG

U2 - 10.4236/jsip.2011.24041

DO - 10.4236/jsip.2011.24041

M3 - Article

VL - 2

SP - 287

EP - 291

JO - Journal of Signal and Information Processing

JF - Journal of Signal and Information Processing

SN - 2159-4465

IS - 4

ER -