Abstract
Feedforward neural network prediction is the most commonly used method in time series prediction. In view of the low prediction accuracy of the conventional BPNN model when the time series data contain a certain linear relationship, this paper describes a neural network approach for time series prediction, that is BPNN–DIOC (back-propagation neural network with direct input-to-output connections). Eight different datasets were used to verify the validity of BPNN–DIOC model in time series prediction. In this paper, the BPNN was extended to four variants based on the presence or absence of output layer bias and input-to-output connections firstly, and the prediction accuracy of eight datasets are analyzed by statistic method secondly. Finally, the experimental results demonstrate that the BPNN–DIOC has better prediction accuracy compared to the conventional BPNN while the output layer bias has no significant effect. Therefore, the input-to-output connections can significantly improve the prediction ability of time series.
Similar content being viewed by others
References
Besteiro R, Arango T, Ortega JA, Rodríguez MR, Fernández MD, Velo R (2017) Prediction of carbon dioxide concentration in weaned piglet buildings by wavelet neural network models. Comput Electron Agric 143:201–207
Bozkurt Biricik G, Tayşi ZC (2017) Artificial neural network and SARIMA based models for power load forecasting in Turkish electricity market. PLoS One 12(4):e0175915
Camara A (2016) Time series forecasting using statistical and neural networks models. LAP LAMBERT Academic Publishing, Berlin
Chi G, Wang D, Hagedorn AD (2019) Future interstate highway system demands: predictions based on population projections. Case Stud Transp Policy 7(2):384–394
Cui X, Potok TE, Palathingal P (2005) Document clustering using particle swarm optimization. In: Proceedings 2005 IEEE swarm intelligence symposium 2005, SIS 2005, pp 185–191
Devi SR, Arulmozhivarman P, Venkatesh C (2017) ANN based rainfall prediction—a tool for developing a landslide early warning system. Adv Cult Living Landslides 3:175–182
Ding G, Zhong SS, Li Y (2008) Time series prediction using wavelet process neural network. Chin Phys B 17(6):1998–2003
Doucoure B, Agbossou K, Cardenas A (2016) Time series prediction using artificial wavelet neural network and multi-resolution analysis: application to wind speed data. Renew Energy 92:202–211
Fang Y, Fataliyev K, Wang LP, Fu XJ, Wang Y (2014) Improving the genetic-algorithm-optimized wavelet neural network approach to stock market prediction. In: 2014 International joint conference on neural networks (IJCNN 2014), pp 3038–3042
Gupta S, Wang LP (2010) Stock forecasting with feedforward neural networks and gradual data sub-sampling. Aust J Intell Inf Process Syst 11:14–17
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
Hou Y, Mai Y (2013) Chaotic prediction for traffic flow of improved BP neural network. Indones J Electr Eng Comput Sci 11(3):1682–1690
Jia J (2014) Financial time series prediction based on BP neural network. Appl Mech Mater 631–632:31–34
Jovic S, Miladinovic JS, Micic R, Markovic S, Rakic G (2019) Analysing of exchange rate and gross domestic product (GDP) by adaptive neuro fuzzy inference system (ANFIS). Phys A 513:333–338
Li G, Shi J (2010) On comparing three artificial neural networks for wind speed forecasting. Appl Energy 87(7):2313–2320
Li S, Hao Q, Yue Y, Liu H (2013) Prediction for chaotic time series of optimized BP neural network based on modified PSO. Comput Eng Appl 49(6):697–702
Li Z, Xu W, Zhang L, Lau RYK (2014) An ontology-based web mining method for unemployment rate prediction. Decis Support Syst 66:114–122
Looney CG (1996) Radial basis functional link nets as learning fuzzy systems. RES report. University of Nevada, Department of Computer Science
Pao YH, Park GH, Sobajic DJ (1994) Learning and generalization characteristics of the random vector functional-link net. Neurocomputing 6(2):163–180
Peng TM, Hubele NF, Karady GG (1992) Advancement in the application of neural networks for short-term load forecasting. IEEE Trans Power Syst 7(1):250–257
Ramana RV, Krishna B, Kumar SR, Pandey NG (2013) Monthly rainfall prediction using wavelet neural network analysis. Water Resour Manage 27(10):3697–3711
Ren Y, Suganthan PN, Srikanth N, Amaratunga G (2016) Random vector functional link network for short-term electricity load demand forecasting. Inf Sci 367:1078–1093
Samsudin R, Shabri A, Saad P (2010) A comparison of time series forecasting using support vector machine and artificial neural network model. J Appl Sci 10(11):950–958
Selvamuthu D, Kumar V, Mishra A (2019) Indian stock market prediction using artificial neural networks on tick data. Financ Innov 5(1):16
Szoplik J (2015) Forecasting of natural gas consumption with artificial neural networks. Energy 85:208–220
Taylor JW, de Menezes LM, McSharry P (2006) A comparison of univariate methods for forecasting electricity demand up to a day ahead. Int J Forecast 22(1):1–16
Teo KK, Wang LP, Lin ZP (2001) Wavelet packet multi-layer perceptron for chaotic time series prediction: effects of weight initialization. In: Computational science—ICCS 2001, proceedings Pt 2. vol 2074, pp 310–317
Wang JZ, Wang JJ, Zhang ZG, Guo SP (2011) Forecasting stock indices with back propagation neural network. Expert Syst Appl 38(11):14346–14355
Wang LP, Teo KK, Lin ZP (2001) Predicting time series with wavelet packet neural networks. In: 2001 IEEE international joint conference on neural networks (IJCNN 2001). pp 1593–1597
Yang H, Hu X (2016) Wavelet neural network with improved genetic algorithm for traffic flow time series prediction. Optik Int J Light Electron Opt 127(19):8103–8110
Zhang L, Suganthan PN (2016) A comprehensive evaluation of random vector functional link networks. Inf Sci 367:1094–1105
Zhu M, Wang LP (2010) Intelligent trading using support vector regression and multilayer perceptrons optimized with genetic algorithms. In: 2010 International joint conference on neural networks (IJCNN 2010)
Acknowledgements
This study was funded by Natural Science Foundation of Shanxi Province (Grant No. 201801D121141) and Joint Research Fund for Overseas Chinese Scholars and Scholars in Hong Kong and Macao (Grant No. 61828601).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Lipo Wang is Guest Editor of SI: ICNC-FSKD 2017. Other authors have no conflict of interest.
Human participants and/or animals
This research does not involve human nor animals.
Informed consent
I consent the journal to review the paper. I inform that the manuscript has not been submitted to other journal for simultaneous consideration. The manuscript has not been published previously. The study is not split up into several parts to increase the quantity of submissions and submitted to various journals or to one journal over time. No data have been fabricated or manipulated (including images) to support my conclusions. No data, text, or theories by others are presented as if they were of my own. Proper acknowledgements to other works are provided, and I use no material that is copyrighted. I consent to submit the paper, and I have contributed sufficiently to the scientific work and I am responsible and accountable for the results.
Additional information
Communicated by L. Wang.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, Y., Wang, L., Chang, Q. et al. Effects of direct input–output connections on multilayer perceptron neural networks for time series prediction. Soft Comput 24, 4729–4738 (2020). https://doi.org/10.1007/s00500-019-04480-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-019-04480-8