Time series forecasting using neural networks : are recurrent connections necessary?

dc.contributor.authorAbdulkarim, Salihu Aish
dc.contributor.authorEngelbrecht, Andries P.
dc.date.accessioned2019-07-18T07:03:44Z
dc.date.issued2019-12
dc.description.abstractArtificial neural networks (NNs) are widely used in modeling and forecasting time series. Since most practical time series are non-stationary, NN forecasters are often implemented using recurrent/delayed connections to handle the temporal component of the time varying sequence. These recurrent/delayed connections increase the number of weights required to be optimized during training of the NN. Particle swarm optimization (PSO) is now an established method for training NNs, and was shown in several studies to outperform the classical backpropagation training algorithm. The original PSO was, however, designed for static environments. In dealing with non-stationary data, modified versions of PSOs for optimization in dynamic environments are used. These dynamic PSOs have been successfully used to train NNs on classification problems under non-stationary environments. This paper formulates training of a NN forecaster as dynamic optimization problem to investigate if recurrent/delayed connections are necessary in a NN time series forecaster when a dynamic PSO is used as the training algorithm. Experiments were carried out on eight forecasting problems. For each problem, a feedforward NN (FNN) is trained with a dynamic PSO algorithm and the performance is compared to that obtained from four different types of recurrent NNs (RNN) each trained using gradient descent, a standard PSO for static environments and the dynamic PSO algorithm. The RNNs employed were an Elman NN, a Jordan NN, a multirecurrent NN and a time delay NN. The performance of these forecasting models were evaluated under three different dynamic environmental scenarios. The results show that the FNNs trained with the dynamic PSO significantly outperformed all the RNNs trained using any of the other algorithms considered. These findings highlight that recurrent/delayed connections are not necessary in NNs used for time series forecasting (for the time series considered in this study) as long as a dynamic PSO algorithm is used as the training method.en_ZA
dc.description.departmentComputer Scienceen_ZA
dc.description.embargo2020-06-12
dc.description.librarianhj2019en_ZA
dc.description.urihttps://link.springer.com/journal/11063en_ZA
dc.identifier.citationAbdulkarim, S.A. & Engelbrecht, A.P. Time Series Forecasting Using Neural Networks: Are Recurrent Connections Necessary? Neural Processing Letters 50, 2763–2795 (2019) doi:10.1007/s11063-019-10061-5.en_ZA
dc.identifier.issn1370-4621 (print)
dc.identifier.issn1573-773X (online)
dc.identifier.other10.1007/s11063-019-10061-5
dc.identifier.urihttp://hdl.handle.net/2263/70762
dc.language.isoenen_ZA
dc.publisherSpringeren_ZA
dc.rights© Springer Science+Business Media, LLC, part of Springer Nature 2019. The original publication is available at : https://link.springer.com/journal/11063.en_ZA
dc.subjectCooperative quantum particle swarm optimizationen_ZA
dc.subjectParticle swarm optimization (PSO)en_ZA
dc.subjectRecurrent neural networksen_ZA
dc.subjectResilient propagationen_ZA
dc.subjectTime series forecastingen_ZA
dc.subjectQuantum particle swarm optimizationen_ZA
dc.subjectNon-stationary environmenten_ZA
dc.subjectModeling and forecastingen_ZA
dc.subjectDynamic optimization problem (DOP)en_ZA
dc.subjectDynamic environmentsen_ZA
dc.subjectClassical back-propagationen_ZA
dc.subjectTime seriesen_ZA
dc.subjectForecastingen_ZA
dc.subjectBackpropagation algorithmsen_ZA
dc.subjectArtificial neural network (ANN)en_ZA
dc.subjectNeural networken_ZA
dc.titleTime series forecasting using neural networks : are recurrent connections necessary?en_ZA
dc.typePostprint Articleen_ZA

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Abdulkarim_Time_2019.pdf
Size:
1.49 MB
Format:
Adobe Portable Document Format
Description:
Postprint Article

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.75 KB
Format:
Item-specific license agreed upon to submission
Description: