Autoregressive Models and Artificial Neural Networks in Time Series Prediction
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60461373%3A22340%2F02%3A00007086" target="_blank" >RIV/60461373:22340/02:00007086 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Autoregressive Models and Artificial Neural Networks in Time Series Prediction
Original language description
The paper is devoted to the presentation possibilities in the MATLAB environment using namely the MATLAB Web Server. For statistical data analysis both MATLAB implemented functions and own algorithms have been used. The main goal of the paper is in analysis of methods of signal prediction by classical methods and using adaptive nonlinear algorithms. Both approaches have been tested by autoregressive models and by feed forward and recurrent artificial neural network model. The autoregressive model is based on SVD and QR methods. The determination of model quality has been verified by information tests including Akaike information criterion and mean squared error.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
BB - Applied statistics, operational research
OECD FORD branch
—
Result continuities
Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2002
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Sborník příspěvků 10. ročníku konference MATLAB 2002
ISBN
80-7080-500-5
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
435-442
Publisher name
VŠCHT Praha
Place of publication
Praha
Event location
Praha
Event date
Nov 7, 2002
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—