Publication detail

Comparison of time series forecasting with artificial neural network and statistical approach

ŠTENCL, M. POPELKA, O. ŠŤASTNÝ, J.

Czech title

Comparison of time series forecasting with artificial neural network and statistical approach

English title

Comparison of time series forecasting with artificial neural network and statistical approach

Type

journal article - other

Language

en

Original abstract

The experiment described in this paper consists of a comparison of results computed by Multi-layer perceptron network with different learning algorithms previously published and results computed with different types of ARMA models. For the network configuration an analytical approach has been applied through the cross-validation method. We performed an exact comparison of both approaches on real-world data set. Results of two types of artificial neural network learning algorithms are compared with two algorithms of statistical prediction of future values.

Czech abstract

Experiment popsaný v příspěvku sestává z porovnání výsledků získaných pomocí neuronové sítě MLP trénované různými učícími algoritmy a výsledků získaných pomocí různých typů ARMA modelů. Oba uvedené přístupy byly porovnány na reálných datových souborech. Výsledky dvou typů učících algoritmů neuronové sítě byly porovnány se dvěma algoritmy pro statistickou predikci dat.

English abstract

The experiment described in this paper consists of a comparison of results computed by Multi-layer perceptron network with different learning algorithms previously published and results computed with different types of ARMA models. For the network configuration an analytical approach has been applied through the cross-validation method. We performed an exact comparison of both approaches on real-world data set. Results of two types of artificial neural network learning algorithms are compared with two algorithms of statistical prediction of future values.

Keywords in Czech

Umělé neuronové sítě, Komparační studie

Keywords in English

artificial neural networks, comparison study

RIV year

2011

Released

01.01.2011

ISSN

1211-8516

Volume

2011

Number

2

Pages from–to

347–352

Pages count

6

BIBTEX


@article{BUT74810,
  author="Michael {Štencl} and Ondřej {Popelka} and Jiří {Šťastný},
  title="Comparison of time series forecasting with artificial neural network and statistical approach",
  year="2011",
  volume="2011",
  number="2",
  month="January",
  pages="347--352",
  issn="1211-8516"
}