Preview the predictive performance of the STR, ENN, and STR-ENN hybrid models
DOI:
https://doi.org/10.69923/IJAS.2024.010102Keywords:
STR-ENN hybrid , STR by using ARIMA , ENN , BP Algorithm , RNNAbstract
This paper presents the mathematical structure of the STR decomposition model and the Elman neural network, in addition to the structure of the hybrid model combining the two previous models. The stages of analysis and verification of each model are discussed separately, and the paper proposes the use of the STR decomposition model based on the autoregressive equation and moving averages, while the STR-ENN model is a model that combines the STR model and the ENN neural network.
To determine the forecast performance of each model, a practical application will be conducted in the MATLAB program on real data to find out which of the three models is better in terms of application, while comparing them using some well-known forecasting criteria.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Iraqi Journal for Applied Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Licenses and Copyright
The copyright of this article is retained by the author(s).
This article is published by the Iraqi Journal for Applied Science (IJAS) under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, reproduction, adaptation, and reuse of the work in any medium or format, including commercial use, provided that appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any modifications are indicated.
Authors retain full copyright of their work and grant IJAS a non-exclusive license to publish, archive, preserve, and disseminate the article, including registration of metadata and Digital Object Identifiers (DOIs) through Crossref.
Any third-party material included in this article remains subject to its respective copyright and licensing conditions. Authors are responsible for obtaining all necessary permissions for such material before publication.
For complete details regarding copyright, licensing, permissions, and reuse, please refer to the journal's Copyright and Licensing Policy available on the IJAS website.
License: https://creativecommons.org/licenses/by/4.0/
How to Cite
