The effects of pre-processing methods on forecasting improvement of Artificial Neural Networks

A. Azadeh, M. Sheikhalishahi, M. Tabesh, Ashkan Negahban

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Along other methods, Intelligent Methods can be used in order to model the trend of changes of a certain variable. These methods require data to be preprocessed before being used in the forecasting process. Generally, the preprocessing step includes omitting outliers, assessment of the missing data, data smoothing, etc. In this paper, the effect of various smoothing methods on the final forecasted results is studied. Furthermore, data from the electricity consumption in Iran over the past 20 years were used as actual data. After being smoothed, these data are then incorporated into an Artificial Neural Network in order to forecast the electrical consumption. The comparisons between several Seasonal Decomposition, including Seasonal Adjustment Series (SAS) and Seasonal Trend Cycle (STC), Exponential Smoothing (Simple, Linear, Holt and Winter) and Box- Jenkins (Moving Average, Auto Regression, and Auto Regression Integrated Moving Average) methods show the superiority of SAS in Decomposition categorization over other methods. The structure of this study may be used for other data sets for improvement of data pre-processing.

Original languageEnglish (US)
Pages (from-to)570-580
Number of pages11
JournalAustralian Journal of Basic and Applied Sciences
Volume5
Issue number6
StatePublished - Jun 2011

Fingerprint

Neural networks
Decomposition
Processing
Electricity

All Science Journal Classification (ASJC) codes

  • General

Cite this

@article{b94f3568bb3c423c93c364319eab8cd9,
title = "The effects of pre-processing methods on forecasting improvement of Artificial Neural Networks",
abstract = "Along other methods, Intelligent Methods can be used in order to model the trend of changes of a certain variable. These methods require data to be preprocessed before being used in the forecasting process. Generally, the preprocessing step includes omitting outliers, assessment of the missing data, data smoothing, etc. In this paper, the effect of various smoothing methods on the final forecasted results is studied. Furthermore, data from the electricity consumption in Iran over the past 20 years were used as actual data. After being smoothed, these data are then incorporated into an Artificial Neural Network in order to forecast the electrical consumption. The comparisons between several Seasonal Decomposition, including Seasonal Adjustment Series (SAS) and Seasonal Trend Cycle (STC), Exponential Smoothing (Simple, Linear, Holt and Winter) and Box- Jenkins (Moving Average, Auto Regression, and Auto Regression Integrated Moving Average) methods show the superiority of SAS in Decomposition categorization over other methods. The structure of this study may be used for other data sets for improvement of data pre-processing.",
author = "A. Azadeh and M. Sheikhalishahi and M. Tabesh and Ashkan Negahban",
year = "2011",
month = "6",
language = "English (US)",
volume = "5",
pages = "570--580",
journal = "Australian Journal of Basic and Applied Sciences",
issn = "1991-8178",
publisher = "INSInet Publications",
number = "6",

}

The effects of pre-processing methods on forecasting improvement of Artificial Neural Networks. / Azadeh, A.; Sheikhalishahi, M.; Tabesh, M.; Negahban, Ashkan.

In: Australian Journal of Basic and Applied Sciences, Vol. 5, No. 6, 06.2011, p. 570-580.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The effects of pre-processing methods on forecasting improvement of Artificial Neural Networks

AU - Azadeh, A.

AU - Sheikhalishahi, M.

AU - Tabesh, M.

AU - Negahban, Ashkan

PY - 2011/6

Y1 - 2011/6

N2 - Along other methods, Intelligent Methods can be used in order to model the trend of changes of a certain variable. These methods require data to be preprocessed before being used in the forecasting process. Generally, the preprocessing step includes omitting outliers, assessment of the missing data, data smoothing, etc. In this paper, the effect of various smoothing methods on the final forecasted results is studied. Furthermore, data from the electricity consumption in Iran over the past 20 years were used as actual data. After being smoothed, these data are then incorporated into an Artificial Neural Network in order to forecast the electrical consumption. The comparisons between several Seasonal Decomposition, including Seasonal Adjustment Series (SAS) and Seasonal Trend Cycle (STC), Exponential Smoothing (Simple, Linear, Holt and Winter) and Box- Jenkins (Moving Average, Auto Regression, and Auto Regression Integrated Moving Average) methods show the superiority of SAS in Decomposition categorization over other methods. The structure of this study may be used for other data sets for improvement of data pre-processing.

AB - Along other methods, Intelligent Methods can be used in order to model the trend of changes of a certain variable. These methods require data to be preprocessed before being used in the forecasting process. Generally, the preprocessing step includes omitting outliers, assessment of the missing data, data smoothing, etc. In this paper, the effect of various smoothing methods on the final forecasted results is studied. Furthermore, data from the electricity consumption in Iran over the past 20 years were used as actual data. After being smoothed, these data are then incorporated into an Artificial Neural Network in order to forecast the electrical consumption. The comparisons between several Seasonal Decomposition, including Seasonal Adjustment Series (SAS) and Seasonal Trend Cycle (STC), Exponential Smoothing (Simple, Linear, Holt and Winter) and Box- Jenkins (Moving Average, Auto Regression, and Auto Regression Integrated Moving Average) methods show the superiority of SAS in Decomposition categorization over other methods. The structure of this study may be used for other data sets for improvement of data pre-processing.

UR - http://www.scopus.com/inward/record.url?scp=83355176798&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83355176798&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:83355176798

VL - 5

SP - 570

EP - 580

JO - Australian Journal of Basic and Applied Sciences

JF - Australian Journal of Basic and Applied Sciences

SN - 1991-8178

IS - 6

ER -