A method for identification of combined deterministic stochastic systems (Q4381643)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1136458
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A method for identification of combined deterministic stochastic systems |
scientific article; zbMATH DE number 1136458 |
Statements
19 October 1998
0 references
system identification
0 references
subspace methods
0 references
stochastic and deterministic systems
0 references
state-space methods
0 references
time series analysis
0 references
0.8837194442749023
0 references
0.8452218174934387
0 references
0.8261920809745789
0 references
0.8257625699043274
0 references
A method for identification of combined deterministic stochastic systems (English)
0 references
Conclusions from the author: ``A method for subspace identification and realization of state space models on innovations form directly from given input and output data is presented. The method determines both the deterministic part and the stochastic part of the model. The algorithm gives exact results in the deterministic case and consistent results when the system is influenced by noise. The stochastic part of the model is computed from standard linear algebra decomposition methods and no matrix equations (e.g. Riccati or Lyapunov equations) need to be solved.'' Monte Carlo simulations are used to analyze the statistical properties of the algorithms as well as to compare them with existing algorithms. It is useful to compare this work with the results achieved by van Overschee, de Moor and Verhagen. For the entire collection see [Zbl 0855.00030].
0 references
