Advanced approach to numerical forecasting using artificial neural networks
Current global market is driven by many factors, such as the information age, the time and amount of information distributed by many data channels it is practically impossible analyze all kinds of incoming information flows and transform them to data with classical methods. New requirements could be...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Mendel University Press
2009-01-01
|
| Series: | Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis |
| Subjects: | |
| Online Access: | https://acta.mendelu.cz/57/6/0297/ |
| _version_ | 1819049972773945344 |
|---|---|
| author | Michael Štencl Jiří Šťastný |
| author_facet | Michael Štencl Jiří Šťastný |
| author_sort | Michael Štencl |
| collection | DOAJ |
| description | Current global market is driven by many factors, such as the information age, the time and amount of information distributed by many data channels it is practically impossible analyze all kinds of incoming information flows and transform them to data with classical methods. New requirements could be met by using other methods. Once trained on patterns artificial neural networks can be used for forecasting and they are able to work with extremely big data sets in reasonable time. The patterns used for learning process are samples of past data. This paper uses Radial Basis Functions neural network in comparison with Multi Layer Perceptron network with Back-propagation learning algorithm on prediction task. The task works with simplified numerical time series and includes forty observations with prediction for next five observations. The main topic of the article is the identification of the main differences between used neural networks architectures together with numerical forecasting. Detected differences then verify on practical comparative example. |
| first_indexed | 2024-12-21T11:40:39Z |
| format | Article |
| id | doaj.art-dd5e4b433cf8419aa10f65b7379693dd |
| institution | Directory Open Access Journal |
| issn | 1211-8516 2464-8310 |
| language | English |
| last_indexed | 2024-12-21T11:40:39Z |
| publishDate | 2009-01-01 |
| publisher | Mendel University Press |
| record_format | Article |
| series | Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis |
| spelling | doaj.art-dd5e4b433cf8419aa10f65b7379693dd2022-12-21T19:05:18ZengMendel University PressActa Universitatis Agriculturae et Silviculturae Mendelianae Brunensis1211-85162464-83102009-01-0157629730410.11118/actaun200957060297Advanced approach to numerical forecasting using artificial neural networksMichael Štencl0Jiří Šťastný1Ústav informatiky, Mendelova zemědělská a lesnická univerzita v Brně, Zemědělská 1, 613 00 Brno, Česká republikaÚstav informatiky, Mendelova zemědělská a lesnická univerzita v Brně, Zemědělská 1, 613 00 Brno, Česká republikaCurrent global market is driven by many factors, such as the information age, the time and amount of information distributed by many data channels it is practically impossible analyze all kinds of incoming information flows and transform them to data with classical methods. New requirements could be met by using other methods. Once trained on patterns artificial neural networks can be used for forecasting and they are able to work with extremely big data sets in reasonable time. The patterns used for learning process are samples of past data. This paper uses Radial Basis Functions neural network in comparison with Multi Layer Perceptron network with Back-propagation learning algorithm on prediction task. The task works with simplified numerical time series and includes forty observations with prediction for next five observations. The main topic of the article is the identification of the main differences between used neural networks architectures together with numerical forecasting. Detected differences then verify on practical comparative example.https://acta.mendelu.cz/57/6/0297/artificial neural networksRadial basis functionNumerical ForecastingMulti Layer Perceptron Network |
| spellingShingle | Michael Štencl Jiří Šťastný Advanced approach to numerical forecasting using artificial neural networks Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis artificial neural networks Radial basis function Numerical Forecasting Multi Layer Perceptron Network |
| title | Advanced approach to numerical forecasting using artificial neural networks |
| title_full | Advanced approach to numerical forecasting using artificial neural networks |
| title_fullStr | Advanced approach to numerical forecasting using artificial neural networks |
| title_full_unstemmed | Advanced approach to numerical forecasting using artificial neural networks |
| title_short | Advanced approach to numerical forecasting using artificial neural networks |
| title_sort | advanced approach to numerical forecasting using artificial neural networks |
| topic | artificial neural networks Radial basis function Numerical Forecasting Multi Layer Perceptron Network |
| url | https://acta.mendelu.cz/57/6/0297/ |
| work_keys_str_mv | AT michaelstencl advancedapproachtonumericalforecastingusingartificialneuralnetworks AT jiristastny advancedapproachtonumericalforecastingusingartificialneuralnetworks |