Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction

Multivariable machine learning (ML) models are increasingly used for time series predictions. However, avoiding the overfitting and underfitting in ML-based time series prediction requires special consideration depending on the size and characteristics of the available training dataset. Predictive e...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ajla Kulaglic, B. Berk Ustundag
Formato:	article
Lenguaje:	EN
Publicado:	UIKTEN 2021
Materias:	predictive error compensated wavelet neural networks spatial dimension time series prediction multivariable time series prediction wavelet transform neural networks Education L Technology T
Acceso en línea:	https://doaj.org/article/6f27914c40f3491da232d18a5c8f83ff
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6f27914c40f3491da232d18a5c8f83ff
record_format	dspace
spelling	oai:doaj.org-article:6f27914c40f3491da232d18a5c8f83ff2021-12-01T22:40:14ZPredictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction10.18421/TEM104-612217-83092217-8333https://doaj.org/article/6f27914c40f3491da232d18a5c8f83ff2021-11-01T00:00:00Zhttps://www.temjournal.com/content/104/TEMJournalNovember2021_1955_1963.pdfhttps://doaj.org/toc/2217-8309https://doaj.org/toc/2217-8333Multivariable machine learning (ML) models are increasingly used for time series predictions. However, avoiding the overfitting and underfitting in ML-based time series prediction requires special consideration depending on the size and characteristics of the available training dataset. Predictive error compensating wavelet neural network (PEC-WNN) improves the time series prediction accuracy by enhancing the orthogonal features within a data fusion scheme. In this study, time series prediction performance of the PEC-WNNs have been evaluated on two different problems in comparison to conventional machine learning methods including the long short-term memory (LSTM) network. The results have shown that PECNET provides significantly more accurate predictions. RMSPE error is reduced by more than 60% with respect to other compared ML methods for Lorenz Attractor and wind speed prediction problems.Ajla KulaglicB. Berk UstundagUIKTENarticlepredictive error compensated wavelet neural networksspatial dimensiontime series predictionmultivariable time series predictionwavelet transformneural networksEducationLTechnologyTENTEM Journal, Vol 10, Iss 4, Pp 1955-1963 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	predictive error compensated wavelet neural networks spatial dimension time series prediction multivariable time series prediction wavelet transform neural networks Education L Technology T
spellingShingle	predictive error compensated wavelet neural networks spatial dimension time series prediction multivariable time series prediction wavelet transform neural networks Education L Technology T Ajla Kulaglic B. Berk Ustundag Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction
description	Multivariable machine learning (ML) models are increasingly used for time series predictions. However, avoiding the overfitting and underfitting in ML-based time series prediction requires special consideration depending on the size and characteristics of the available training dataset. Predictive error compensating wavelet neural network (PEC-WNN) improves the time series prediction accuracy by enhancing the orthogonal features within a data fusion scheme. In this study, time series prediction performance of the PEC-WNNs have been evaluated on two different problems in comparison to conventional machine learning methods including the long short-term memory (LSTM) network. The results have shown that PECNET provides significantly more accurate predictions. RMSPE error is reduced by more than 60% with respect to other compared ML methods for Lorenz Attractor and wind speed prediction problems.
format	article
author	Ajla Kulaglic B. Berk Ustundag
author_facet	Ajla Kulaglic B. Berk Ustundag
author_sort	Ajla Kulaglic
title	Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction
title_short	Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction
title_full	Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction
title_fullStr	Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction
title_full_unstemmed	Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction
title_sort	predictive error compensating wavelet neural network model for multivariable time series prediction
publisher	UIKTEN
publishDate	2021
url	https://doaj.org/article/6f27914c40f3491da232d18a5c8f83ff
work_keys_str_mv	AT ajlakulaglic predictiveerrorcompensatingwaveletneuralnetworkmodelformultivariabletimeseriesprediction AT bberkustundag predictiveerrorcompensatingwaveletneuralnetworkmodelformultivariabletimeseriesprediction
_version_	1718404105994502144

Predictive Error Compensating Wavelet Neural Network Model for Multivariable Time Series Prediction

Ejemplares similares