In this paper, we used four types of artificial neural network (ANN) to predict the behavior of chaotic time series. Each neural network that used in this paper acts as global model to predict the future behavior of time series. Prediction process is based on embedding theorem and time delay determined by this theorem. This ANN applied to the time series that generated by Mackey-glass equation that has a chaotic behavior. At the end, all neural networks are used to solve this problem and their results are compared and analyzed.
ZhangJ. and ManK.F., Time series prediction using recurrent neural network in multi-dimension embedding phase space, IEEE International Conference on Systems, Man, and Cybernetics2 (1998), 11-14.
2.
AbarbanelH.D., FrisonT.W. and TsimringL., Obtaining order in a world of chaos, IEEE Signal Processing Magazine15(3) (1998), 49-65.
3.
OttE., Chaos in dynamical systems, 2nd edition, Cambridge, U.K.Cambridge University Press, 2002.
4.
SkiadasC.H., DimotikalisI. and SkiadasC., Chaos theory modeling, simulation and applications, World Scientific Publishing, 2011.
5.
PoskittD.S. and TremayneA.R., The selection and use of linear and bilinear time series models, International Journal of Forecasting2(1) (1986) 101-114.
6.
TongH., threshold models in nonlinear time series analysis, Springer Verlag, 1983.
7.
TongH., Non - linear time series: A dynamical system approach, Oxford University Press, 1990.
8.
TongH. and LimK.S., Threshold autoregression limit cycles and cyclical data, Journal of the Royal Statistical Society42(3) (1980), 245-292.
9.
De GooijerJ.G. and HyndmanR.J., 25 years of time series forecasting, International Journal of Forecasting22(3) (2006), 443-473.
10.
De GooijerJ.G. and KumarK., Some recent developments in non-linear time series modelling, testing, and forecasting, International Journal of Forecasting8(2) (1992), 135-156.
11.
WerbosP.J., Generalization of backpropagation with application to a recurrent gas market model, Neural Networks1(4) (1988), 339-356.
12.
AlpaydinE., Introduction to Machine Learning, The MIT Press, 2010.
13.
HerreraL.J., PomaresH., RojasI., GuillenA., PrietoA. and ValenzuelaO., Recursive prediction for long term time series forecasting using advanced models, Neurocomputing70 (2007), 2870-2880.
14.
MenezesJ.P. and BarretoG.A., Long - term time series prediction with the NARX network: An empirical evaluation, Neurocomputing71 (2008), 3335-3343.
15.
Ardalani-FarsaM. and ZolfaghariS., Chaotic time series prediction with residual analysis method using hybrid Elman - NARX neural networks, Neurocomputing73 (2010), 2540-2553.
16.
AbarbanelH., Analysis of observed chaotic data, Spinger-Verlag, New York, 1996.
17.
FuY., WuC., JengJ. and KoC., ARFNNs with SVR for prediction of chaotic time series with outliers, Expert Systems with Applications37 (2010), 4441-4451.
18.
NorgaardM., RavnO., PoulsenN.K. and HansenL.K., Neural Networks for Modelling and Control of Dynamic Systems, Springer, Berlin, (2000).
19.
LawrenceR., Using neural networks to forecast stock market prices, University of Manitoba, 1997.
20.
LiuF., QuekC. and NgG.S., Neural network model for time series prediction by reinforcement learning, Proceedings of the International Joint Conference on Neural Networks, Montreal, Canada, (2005).
21.
ParkY.R., MurrayT.J. and ChenC., Predicting sun spots using a layered perceptron neural network, IEEE Transactions on Neural Networks1(2) (1996), 501-505.
HaykinS., Neural networks: A comprehensive foundation, Macmillan College Publishing Company, New York, 1994.
24.
HaganM.T., DemuthH.B. and BealeM.H., Neural Network Design, 1996.
25.
KolenJ.F. and KremerS.C., A Field guide to dynamical recurrent networks, Wiley - IEEE Press, 2001.
26.
MaguireL.P., RocheB., McGinnityT.M. and Mc DaidL.J., Predicting a chaotic time series using a fuzzy neural network, Information Sciences112 (1998), 125-136.
27.
ZhangJ. and ManK.F., Time series prediction using recurrent neural network inmulti - dimension embedding phase space, IEEE International Conference on Systems, Man, and Cybernetics2 (1998), 11-14.
28.
ZemouriR., GouriveauR. and ZerhouniN., Defining and applying prediction performance metrics on a recurrent NARX time series model, Neurocomputing73 (2010), 2506-2521.
29.
AussemA., MurtaghF. and SarazinM., Dynamical recurrent neural networks towards environmental time series prediction, International Journal Neural Systems6(2) (1995), 145-170.
30.
ChandraR. and ZhangM., Cooperative coevolution of elman recurrent neural networks for chaotic time series prediction, Neurocomputing86 (2012), 116-123.
31.
AussemA., MurtaghF. and SarazinM., Dynamical recurrent neural networks and pattern recognition methods for time series prediction: Application to seeing and temperature forecasting in the context of ESO's VLT Astronomical Weather Station, Vistas iv Astronomy38 (1995), 357-374.
32.
ZhangJ. and ManK.F., Time series prediction using recurrent neural network in multi-dimension embedding phase space, IEEE International Conference on Systems, Man, and Cybernetics2 (1998) 11-14.
33.
KoskelaT., LehtokangasM., SaarinenJ. and KaskiK., Time series prediction with multilayer perceptron, FIR and elman neural networks, in: The Proceedings of the World Congress on Neural Networks (1996), 491-496.
34.
RumelhartD.E. and McClellandJ.L., Parallel distributed processing; exploration in the microstructure of cognation, MIT Press Cambridge, 1986.
35.
GevaA.B., Scale net - multiscale neural - network architecture for time series prediction, IEEE Transaction on Neural Network9(5) (1998).
36.
WabelA., HanzawaT., HintonG., ShikanoK. and LangK.J., Phoneme recognition using time delay neural network, IEEE Transaction on Acoustics, Speech, Signal Processing37(3) (1989).
37.
PrincipeJ.C., EulianoN.R. and LefebvreW.C., Neural adaptive systems: Fundamentals through simulations, Wiley, New York, 2000.
38.
PearlmutterB.A., Gradient calculations for dynamic recurrent neural networks: A survey, IEEE Tansactions on Neural Networks6(5) (1995), 1212-1228.
39.
SiegelmannH.T., HorneB.G. and GilesC.L., Computational capabilities of recurrent NARX neural networks, IEEE Transaction Systems27(2) (1997), 208-215.
40.
NarendraK.S. and ParthasarathyK., Identification and control of dynamical systems using neural networks, IEEE Transaction on Neural Networks1(1) (1990), 4-27.
41.
ChenS., BillingsS.A. and GrantP.M., Nonlinear system identification using neural networks, International Journal Control11(6) (1990), 1191-1214.
42.
LinT., HorneB.G., TinoP. and GilesC.L., A delay damage model selection algorithm for NARX neural networks, IEEE Transaction Signal Processing45(11) (1997), 2719-2730.
43.
WhiteheadB.A. and ChoateT.D., Cooperative - competitive genetic evolution of radial basis function centers and widths for time series prediction, IEEE Transactions on Neural Networks7(4) (1996), 869-880.
44.
RivasV.M., MereloJ.J., CastilloP.A., ArenasbM.G. and CastellanoJ.G., A evolving RBF neural networks for time - series forecasting with EvRBF, Information Sciences165 (2004), 207-220.
45.
SchwenkerF., KestlerH.A. and PalmmG., Three learning phases for radial - basis - function networks, Neural Networks14 (2001), 439-458.
46.
BroomheadD.S. and LoweD., Multi variable functional interpolation and adaptative networks, Complex Systems11 (1988), 321-355.
47.
AwadM., PomaresH., RojasI. and HamdonO.S., Prediction of time series using rbf neural networks: A new approach of clustering, The International Arab Journal of Information Technology6(2) (2009).
48.
MinZ. and ShilingL., Application of GRNN and uniform design to nonlinear system modeling, Computer Measurement and Control15(9) (2007), 1189-1191.
49.
SpechtD.A., General regression neural network, IEEE Transactions on Neural Network2 (1991), 568-576.
50.
LibiaoZ., GuangZ.C., MingM. and XiaohuaL., Solutions of multi-objective optimization problems based on particle swarm optimization, Journal of Computer Research and Development41(7) (2004), 1286-1291.
51.
ZhangJ., ChungH.S. and LoW., Chaotic time series prediction using a neuro - fuzzy system with time - delay coordinates, IEEE Transaction on Knowledge and Data Engineering20(7) (2008).
52.
YuxiaH. and HongtaoZ., Chaos optimization method of SVM parameters selection for chaotic time series forecasting, Proceedings of the International Conference on Solid State Devices and Materials Science, Physics Procedia25 (2012), 588-594.
53.
SamantaB., Prediction of chaotic time series using computational intelligence, Expert Systems with Applications38 (2011), 11406-11411.
54.
WangJ., ChiD., WuJ. and LuH., Chaotic time series method combined with particle swarm ptimization and trend adjustment for electricity demand forecasting, Expert Systems with Applications38 (2011), 8419-8429.
55.
KarunasingheD. and LiongS., Chaotic time series prediction with a global model: Artificial neural network, Journal of Hydrology323 (2006), 92-105.
56.
OmidvarA.E., Configuring radial basis function network using fractal scaling process with application to chaotic time series prediction, Chaos, Solitons and Fractals22 (2004), 757-766.
57.
SongH.J., MiaoC.Y., ShenZ.Q., RoelW., MajaD.H. and FranckyC., Design of fuzzy cognitive maps using neural networks for predicting chaotic time series, Neural Networks23 (2010), 1264-1275.
58.
AussemA., Dynamical recurrent neural networks towards prediction and modeling of dynamical systems, Neurocomputing28 (1999), 207-232.
59.
McNamesJ., Local averaging optimization for chaotic time series prediction, Neurocomputing48 (2002), 279-297.
60.
LauK.W. and WuQ.H., Local prediction of non - linear time series using support vector regression, Pattern Recognition41 (2008), 1539-1547.
61.
MirzaeeH., Long - term prediction of chaotic time series with multi - step prediction horizons by a neural network with levenberg - marquardt learning algorithm, Chaos, Solitons and Fractals41 (2009), 1975-1979.
62.
Li-yunS., Prediction of multivariate chaotic time series with local polynomial fitting, Computers and Mathematics with Applications59 (2010), 737-744.
63.
GromovV.A. and ShulgaA.N., Chaotic time series prediction with employment of ant colony optimization, Expert Systems with Applications39 (2012), 8474-8478.
64.
WuX. and SongZ., Multi - step prediction of chaotic time - series with intermittent failures based on the generalized nonlinear filtering methods, Applied Mathematics and Computation219 (2013), 8584-8594.
