An improved Pi-Sigma neural network using error feedback for time series prediction

Time series prediction grabs much attention because of its effect on the vast range of real-life applications. Traditional time series forecasting tools have some limitations like slow training process, less efficient training methods that decrease the performance of the model. Higher Order Neural N...

Full description

Saved in:
Bibliographic Details
Main Author: Akram, Urooj
Format: Thesis
Language:English
English
English
Published: 2018
Subjects:
Online Access:http://eprints.uthm.edu.my/523/1/24p%20UROOJ%20AKRAM.pdf
http://eprints.uthm.edu.my/523/2/UROOJ%20AKRAM%20COPYRIGHT%20DECLARATION.pdf
http://eprints.uthm.edu.my/523/3/UROOJ%20AKRAM%20WATERMARK.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-uthm-ep.523
record_format uketd_dc
spelling my-uthm-ep.5232021-07-25T08:41:54Z An improved Pi-Sigma neural network using error feedback for time series prediction 2018-04 Akram, Urooj QA75-76.95 Calculating machines Time series prediction grabs much attention because of its effect on the vast range of real-life applications. Traditional time series forecasting tools have some limitations like slow training process, less efficient training methods that decrease the performance of the model. Higher Order Neural Network (HONN) using recurrent feedback appeared as a powerful technique in the domain of time series prediction and it has the ability to expand the input space, making them more efficient for solving complex problems and perform high learning abilities in time series prediction. This study proposed a model called improved Pi-Sigma Neural Network using Error Feedback (PSNN-EF) which combines the properties of Pi-Sigma Neural Network (PSNN), recurrence and error feedback. PSNN-EF uses backpropagation gradient descent algorithm for training purpose and is tested with physical time series signals of humidity, evaporation and wind direction datasets that are collected from Malaysian Meteorological Department (MMD). The prediction result is compared with Jordan Pi-Sigma Neural Network (JPSN) and the ordinary PSNN. The results clearly showed that the PSNN-EF significantly improved the computational efficiency of the training process and has been developed to produce more realistic and acceptable results. The average improvement of the proposed model on evaporation dataset is 2.06%, humidity is 7.45% and wind is 3.51% as compared to other models. The benefit of using error feedback is that it generates more accurate and promising results of prediction. Therefore, from the performance of the proposed method, it is noticed that PSNN-EF can provide better solution to JPSN for one-step-ahead prediction of those three datasets. 2018-04 Thesis http://eprints.uthm.edu.my/523/ http://eprints.uthm.edu.my/523/1/24p%20UROOJ%20AKRAM.pdf text en public http://eprints.uthm.edu.my/523/2/UROOJ%20AKRAM%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/523/3/UROOJ%20AKRAM%20WATERMARK.pdf text en validuser mphil masters Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology
institution Universiti Tun Hussein Onn Malaysia
collection UTHM Institutional Repository
language English
English
English
topic QA75-76.95 Calculating machines
spellingShingle QA75-76.95 Calculating machines
Akram, Urooj
An improved Pi-Sigma neural network using error feedback for time series prediction
description Time series prediction grabs much attention because of its effect on the vast range of real-life applications. Traditional time series forecasting tools have some limitations like slow training process, less efficient training methods that decrease the performance of the model. Higher Order Neural Network (HONN) using recurrent feedback appeared as a powerful technique in the domain of time series prediction and it has the ability to expand the input space, making them more efficient for solving complex problems and perform high learning abilities in time series prediction. This study proposed a model called improved Pi-Sigma Neural Network using Error Feedback (PSNN-EF) which combines the properties of Pi-Sigma Neural Network (PSNN), recurrence and error feedback. PSNN-EF uses backpropagation gradient descent algorithm for training purpose and is tested with physical time series signals of humidity, evaporation and wind direction datasets that are collected from Malaysian Meteorological Department (MMD). The prediction result is compared with Jordan Pi-Sigma Neural Network (JPSN) and the ordinary PSNN. The results clearly showed that the PSNN-EF significantly improved the computational efficiency of the training process and has been developed to produce more realistic and acceptable results. The average improvement of the proposed model on evaporation dataset is 2.06%, humidity is 7.45% and wind is 3.51% as compared to other models. The benefit of using error feedback is that it generates more accurate and promising results of prediction. Therefore, from the performance of the proposed method, it is noticed that PSNN-EF can provide better solution to JPSN for one-step-ahead prediction of those three datasets.
format Thesis
qualification_name Master of Philosophy (M.Phil.)
qualification_level Master's degree
author Akram, Urooj
author_facet Akram, Urooj
author_sort Akram, Urooj
title An improved Pi-Sigma neural network using error feedback for time series prediction
title_short An improved Pi-Sigma neural network using error feedback for time series prediction
title_full An improved Pi-Sigma neural network using error feedback for time series prediction
title_fullStr An improved Pi-Sigma neural network using error feedback for time series prediction
title_full_unstemmed An improved Pi-Sigma neural network using error feedback for time series prediction
title_sort improved pi-sigma neural network using error feedback for time series prediction
granting_institution Universiti Tun Hussein Onn Malaysia
granting_department Faculty of Computer Science and Information Technology
publishDate 2018
url http://eprints.uthm.edu.my/523/1/24p%20UROOJ%20AKRAM.pdf
http://eprints.uthm.edu.my/523/2/UROOJ%20AKRAM%20COPYRIGHT%20DECLARATION.pdf
http://eprints.uthm.edu.my/523/3/UROOJ%20AKRAM%20WATERMARK.pdf
_version_ 1747830630962429952