UMP Institutional Repository

Time series forecasting based on wavelet decomposition and correlation feature subset selection

Ahmed, Ehab Ali and Syafiq Fauzi, Kamarulzaman and Gisen, J. I. A. and Zuriani, Mustaffa (2018) Time series forecasting based on wavelet decomposition and correlation feature subset selection. Advanced Science Letters, 24 (10). pp. 7549-7553. ISSN 1936-6612

[img]
Preview
Pdf
40. Time Series Forecasting Based on Wavelet Decomposition and Correlation Feature Subset Selection1.pdf

Download (28kB) | Preview

Abstract

Due to the possibility of extracting the features of data through wavelet transformation, its use in time series forecasting model has become popular. The appropriate wavelet function selection and the level of decomposition are very necessary for a successful use of the wavelet coupled with the artificial neural network (ANN) models. This is because it can enhance the performance of the model. A drawback of the wavelet-coupled models is their used a large output number to the ANN, thereby making it more difficult to calibrate the neural structure and need a long time to train the model. This study aims to develop a wavelet-coupled ANN for the detection of the dominant input data from the wavelet decomposition sub-series for use as ANN input to increase the model accuracy with minimum input number. The result showed that the Wavelet Transformation and Correlation Feature Subset Selection (CFS) with ANN can significantly improve the efficiency of the ANN models.

Item Type: Article
Additional Information: JCR® Category: Multidisciplinary Sciences. Quartile: Q2
Uncontrolled Keywords: ANN; MLPNN; Correlation Feature Subset Selection; Wavelet Decomposition
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty/Division: Centre of Excellence: IBM Centre of Excellence
Faculty of Computer System And Software Engineering
Depositing User: Mrs. Neng Sury Sulaiman
Date Deposited: 21 Mar 2018 08:23
Last Modified: 21 Nov 2018 03:55
URI: http://umpir.ump.edu.my/id/eprint/20684
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item