Abstract
To accurately predict the price of tungsten with an optimal architecture of neural networks (NNs) and better generalization performance, based on poor generalization and overfitting of a predictor such as a NNs, this paper presents a new hybrid constructive neural network method (HCNNM) to repair the impacting value in the original data in the same manner as the jumping points of a function. A series of theorems was proven that show a function with m jumping discontinuity points (or impacting points) can be approximated with the simplest NNs and a constructive decay Radial basis function (RBF) NNs, and a function with m jumping discontinuity points can be constructively approximated by hybrid constructive NNs. The hybrid networks have an optimal architecture and generalize well. Additionally, a practical problem regarding Tungsten prices from 1900 to 2014 is presented with some impacting points to more accurately approximate the sample data set and forecast future prices with the HCNNM, and some performance measures, such as the training time, testing RMSE and neurons, are compared with traditional algorithms (BP, SVM, ELM and Deep Learning) through many numerical experiments that fully verify the superiority, correctness and validity of the theory.
Similar content being viewed by others
References
Chakhmouradian AR, Smith MP, Kynicky J (2015) From strategic tungsten to green neodymium: a century of critical metals at a glance. Ore Geol Rev 64:455–458
Xibing YYL (2010) Statistic model of supply and demand factors’ affect and prediction on tungsten’s value [J]. Mod Mining 1:027
Stock JH, Watson MW (1988) A probability model of the coincident economic indicators. National Bureau of Economic Research, Cambridge
Tang H, Chun K, Xu L (2003) Finite mixture of ARMA-GARCH model for stock price prediction. In: Proc. of 3rd International Workshop on Computational Intelligence in Economics and Finance (CIEF2003), North Carolina, USA
Garcia RC, et al (2005) A GARCH forecasting model to predict day-ahead electricity prices. IEEE Trans Power Syst 20(2):867–874
Xi L, et al (2014) A new constructive neural network method for noise processing and its application on stock market prediction. Appl Soft Comput 15:57–66
Zekic M Neural network applications in stock market predictions-a methodology analysis. In: Proceedings of the 9th International Conference on Information and Intelligent Systems 1998: Citeseer
Wang Y-F (2002) Predicting stock price using fuzzy grey prediction system. Expert Syst Appl 22(1):33–38
Ince H, Trafalis TB (2007) Kernel principal component analysis and support vector machines for stock price prediction. IIE Trans 39(5):629–637
Muzhou H, Ming C, Yangchun Z (2015) A Self-Organizing Mixture Extreme Leaning Machine for Time Series Forecasting. In: Proceedings of ELM-2014, vol 1. Springer, pp 225–236
Palm RB (2012) Prediction as a candidate for learning deep hierarchical models of data. https://github.com/rasmusbergpalm/DeepLearnToolbox
Noriega JR, Wang H (1998) A direct adaptive neural-network control for unknown nonlinear systems and its application. IEEE Trans Neural Netw 9(1):27–34
Carpenter GA, Grossberg S (1988) The ART of adaptive pattern recognition by a self-organizing neural network. Computer 21(3):77–88
Liu Y-J, et al (2011) Adaptive neural output feedback tracking control for a class of uncertain discrete-time nonlinear systems. IEEE Trans Neural Netw 22(7):1162–1167
Ge S, Hang C, Zhang T (1999) Adaptive neural network control of nonlinear systems by state and output feedback. IEEE Trans Syst Man Cybern B Cybern 29(5):818–828
Polycarpou MM (1996) Stable adaptive neural control scheme for nonlinear systems. IEEE Trans Autom Control 41(3):447–451
Hagiwara K, Fukumizu K (2008) Relation between weight size and degree of over-fitting in neural network regression. Neural Netw 21(1):48–58
Tetko IV, Livingstone DJ, Luik AI (1995) Neural network studies. 1. Comparison of overfitting and overtraining. J Chem Inf Comput Sci 35(5):826–833
Schittenkopf C, Deco G, Brauer W (1997) Two strategies to avoid overfitting in feedforward networks. Neural Netw 10(3):505–516
Yu Z, et al The design of RBF neural networks for solving overfitting problem. In: intelligent control and automation, 2006. WCICA 2006. The Sixth World Congress on: IEEE
Perrone MP, Cooper LN (1992) When networks disagree: Ensemble methods for hybrid neural networks. DTIC Document
Tay F, Cao L (2001) Application of support vector machines in financial time series forecasting. Omega-Oxford-Pergamon Press- 29:309–317
Doan C, Liong S (2004) Generalization for multilayer neural network: Bayesian regularization or early stopping
Liu J, Demirci O, Calhoun VD (2008) A parallel independent component analysis approach to investigate genomic influence on brain function. IEEE Signal Process Lett 15:413–416
Soltani S (2002) On the use of the wavelet decomposition for time series prediction. Neurocomputing 48 (1):267–277
Karhunen J, et al (1997) A class of neural networks for independent component analysis. IEEE Trans Neural Netw 8(3):486–504
Hyvärinen A, Oja E (2000) Independent component analysis: algorithms and applications. Neural Netw 13(4-5):411–430
Prasad GK, Sahambi J Classification of ECG arrhythmias using multi-resolution analysis and neural networks. 2003: IEEE
Shyu LY, Wu YH, Hu W (2004) Using wavelet transform and fuzzy neural network for VPC detection from the Holter ECG. IEEE Trans Biomed Eng 51(7):1269–1273
He Y, Tan Y, Sun Y Wavelet neural network approach for fault diagnosis of analogue circuits. 2004: IET
Chen B, et al (1999) Application of wavelets and neural networks to diagnostic system development, 1, feature extraction. Comput Chem Eng 23(7):899–906
Shah S, Palmieri F, Datum M (1992) Optimal filtering algorithms for fast learning in feedforward neural networks. Neural Netw 5(5):779–787
Connor JT, Martin RD, Atlas L (1994) Recurrent neural networks and robust time series prediction. IEEE Trans Neural Netw 5(2):240–254
Feraund R, et al (2001) A fast and accurate face detector based on neural networks. IEEE Trans Pattern Anal Mach Intell 23(1):42–53
Haykin S Neural networks and learning machines. Vol. 3. 2009: Prentice Hall
Fan L, et al (2008) Singular points detection based on zero-pole model in fingerprint images. IEEE Trans Pattern Anal Mach Intell 30(5):929–940
Chang CC, Lin CJ (2011) LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27
Haykin S, Network N (2004) A comprehensive foundation. Neural Netw:2
Simon H Neural networks: a comprehensive foundation. 1999: Prentice Hall
Huang GB, Zhu QY, Siew CK Extreme learning machine: a new learning scheme of feedforward neural networks. 2004: IEEE
Huang GB, Chen L (2007) Convex incremental extreme learning machine. Neurocomputing 70 (16-18):3056–3062
Islam MM, Yao X, Murase K (2003) A constructive algorithm for training cooperative neural network ensembles. IEEE Trans Neural Netw 14(4):820–834
Liu D, Chang TS, Zhang Y (2002) A constructive algorithm for feedforward neural networks with incremental training. IEEE Transa Circuits Syst Part 1 Fundam Theory Appl 49(12):1876–1879
Park J, Sandberg IW (1991) Universal approximation using radial-basis-function networks. Neural Comput 3(2):246–257
Er MJ, et al (2002) Face recognition with radial basis function (RBF) neural networks. IEEE Trans Neural Netw 13(3):697–710
Mai-Duy N, Tran-Cong T (2003) Approximation of function and its derivatives using radial basis function networks. Appl Math Model 27(3):197–220
Hou M, Han X (2010) Constructive approximation to multivariate function by decay RBF neural network. IEEE Trans Neural Netw 21(9):1517–1523
Llanas B, Sainz F (2006) Constructive approximate interpolation by neural networks. J Comput Appl Math 188(2):283–308
Islam MM, et al (2009) A new constructive algorithm for architectural and functional adaptation of artificial neural networks. IEEE Trans Syst Man Cybern B Cybern 39(5):1590–1605
Zhao-qing K (2009) Analysis on periodical changes and the future trend of tungsten prices under domestic and overseas markets [J]. China Tungsten Ind 24(2):1–5
Hao Z, et al (2013) Decomposition laws of tungsten prices fluctuation since 1900 and its applications. Trans Nonferrous Metals Soc China 23(9):2807–2816
Kai W, et al (2008) An expanded training set based validation method to avoid overfitting for neural network classifier. In: Natural Computation, 2008. ICNC ’08 Fourth International Conference on
Liu ZP, Castagna JP (1999) Avoiding overfitting caused by noise using a uniform training mode. In: Neural Networks IJCNN ’99. International Joint Conference on, p 1999
Pinkus A (1999) Approximation theory of the MLP model in neural networks. Acta Numer 8(1):143–195
Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst (MCSS) 2(4):303–314
Chui CK (1992) An introduction to wavelets, vol 1. Academic Press, New York
Delyon B, Juditsky A, Benveniste A (1995) Accuracy analysis for wavelet approximations. IEEE Trans Neural Netw 6(2):332–348
Huang CJ, Chen PW, Pan WT (2011) Using multi-stage data mining technique to build forecast model for Taiwan stocks. Neural Comput & Applic:1–7
Huang G-B Extreme Learning Machines [Online]. http://www3.ntu.edu.sg/home/egbhuang
Lin CCCaCJ LIBSVM – A Library for Support Vector Machines. https://www.csie.ntu.edu.tw/cjlin/libsvm/
Acknowledgments
This work was supported by the Natural Science Foundation of China under Grants 61375063, 61271355, 11301549 and 11271378.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Muzhou, H., Taohua, L., Yunlei, Y. et al. A new hybrid constructive neural network method for impacting and its application on tungsten price prediction. Appl Intell 47, 28–43 (2017). https://doi.org/10.1007/s10489-016-0882-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-016-0882-z