Dynamic ridge polynomial neural network with Lyapunov function for time series forecasting

被引：0
作者：
Waddah Waheeb
Rozaida Ghazali
Abir Jaafar Hussain
机构：
[1] Universiti Tun Hussein Onn Malaysia,Faculty of Computer Science and Information Technology
[2] Liverpool John Moores University,undefined
来源：
Applied Intelligence | 2018年 / 48卷
关键词：
Dynamic ridge polynomial neural network; Recurrent neural network; Higher order neural network; Time series forecasting; Adaptive learning rate; Lyapunov function;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The ability to model the behaviour of arbitrary dynamic system is one of the most useful properties of recurrent networks. Dynamic ridge polynomial neural network (DRPNN) is a recurrent neural network used for time series forecasting. Despite the potential and capability of the DRPNN, stability problems could occur in the DRPNN due to the existence of the recurrent feedback. Therefore, in this study, a sufficient condition based on an approach that uses adaptive learning rate is developed by introducing a Lyapunov function. To compare the performance of the proposed solution with the existing solution, which is derived based on the stability theorem for a feedback network, we used six time series, namely Darwin sea level pressure, monthly smoothed sunspot numbers, Lorenz, Santa Fe laser, daily Euro/Dollar exchange rate and Mackey-Glass time-delay differential equation. Simulation results proved the stability of the proposed solution and showed an average 21.45% improvement in Root Mean Square Error (RMSE) with respect to the existing solution. Furthermore, the proposed solution is faster than the existing solution. This is due to the fact that the proposed solution solves network size restriction found in the existing solution and takes advantage of the calculated dynamic system variable to check the stability, unlike the existing solution that needs more calculation steps.
引用
收藏
页码：1721 / 1738
页数：17
相关论文
共 83 条
  • [1] Al-Jumeily D(2014)Predicting physical time series using dynamic ridge polynomial neural networks PLoS ONE 9 1-15
  • [2] Ghazali R(2000)New results on recurrent network training: unifying the algorithms and accelerating convergence IEEE Trans Neural Netw 11 697-709
  • [3] Hussain A(2012)Software fault prediction using nonlinear autoregressive with exogenous inputs (narx) network Appl Intell 37 121-129
  • [4] Atiya AF(2007)Dynamic parameter optimization of evolutionary computation for on-line prediction of time series with changing dynamics Appl Soft Comput 7 1170-1176
  • [5] Parlos AG(2016)A hybrid functional link dynamic neural network and evolutionary unscented kalman filter for short-term electricity price forecasting Neural Comput Applic 27 2123-2140
  • [6] Chatterjee S(2011)Dynamic ridge polynomial neural network: Forecasting the univariate non-stationary and stationary trading signals Expert Syst Appl 38 3765-3776
  • [7] Nigam S(2008)The application of ridge polynomial neural network to multi-step ahead financial time series prediction Neural Comput Appl 17 311-323
  • [8] Singh JB(2009)Non-stationary and stationary prediction of financial time series using dynamic ridge polynomial neural network Neurocomputing 72 2359-2367
  • [9] Upadhyaya LN(2015)Hybrid neural network for classification of graph structured data Int J Mach Learn Cybern 6 465-474
  • [10] Chen Y(2010)Chaos-based support vector regressions for exchange rate forecasting Expert Syst Appl 37 8590-8598
123456789