Multiobjective evolutionary optimization of training and topology of recurrent neural networks for time-series prediction

Computer Journal

Volumn 55, Issue 3, 2012, Pages 325-336

  Katagiri, Hideki ^a   Nishizaki, Ichiro ^a   Hayashida, Tomohiro ^a   Kadoma, Takanori ^a  

^a HIROSHIMA UNIVERSITY   (Japan)

Author keywords

multiobjective evolutionary algorithm; recurrent neural networks; time series prediction

Indexed keywords

EFFECTIVE ALGORITHMS; EVOLUTIONARY MULTIOBJECTIVE OPTIMIZATION; FEASIBLE REGIONS; LOCAL OPTIMAL SOLUTION; MULTI OBJECTIVE EVOLUTIONARY ALGORITHMS; MULTIOBJECTIVE EVOLUTIONARY OPTIMIZATION; NETWORK TOPOLOGY; PARETO FRONTIERS; PARETO OPTIMAL SOLUTIONS; PREDICTION CAPABILITY; PRESERVATION STRATEGIES; SELF-ADAPTIVE MUTATION; SMALL TRAINING; TIME SERIES PREDICTION; TIME-SERIES DATA;

ELECTRIC NETWORK TOPOLOGY; FORECASTING; OPTIMAL SYSTEMS; RECURRENT NEURAL NETWORKS; SEMANTICS;

MULTIOBJECTIVE OPTIMIZATION;

EID: 84858257374     PISSN: 00104620     EISSN: 14602067     Source Type: Journal    
DOI: 10.1093/comjnl/bxr042     Document Type: Article

References (31)

1. Lu, Y.-L., Mak, M.-W. and Siu, W.-C. (1995) Application of a fast real time recurrent learning algorithm to test-to-phone conversion. Proc. Int. Conf. Neural Netw., 5, 2853-2857.
2. De Vries, B. and Principe, J.C. (1990) A theory for neural networks with time delays. Proc. 1990 Conference on Advance in Neural Information Processing Systems 3, San Francisco, CA, USA, pp. 162-168. IEEE Press, New Jersey.
3. Zeng, A., Goodman, R. and Smyth, P. (1994) Discrete recurrent neural networks for grammatical inference. IEEE Trans. Neural Netw., 5, 320-330.
4. Prokhorov, D.V., Saad, E.W. and Wunsch, D.C. (1998) Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks. IEEE Trans. Neural Netw, 9, 1456-1470.
5. Barbounis, T.G. and Theocharis, J.B. (2007) Locally recurrent neural networks for wind speed prediction using spatial correlation. Inf. Sci., 177, 5775-5797.
6. Bengio, Y., Simard, P. and Frasconi, P. (1994) Learning longterm dependencies with gradient descent is difficult. IEEE Trans. Neural Netw., 5, 157-166.
7. Blanco, A., Delgado, M. and Pegalajar, M.C. (2000) A genetic algorithm to obtain the optimal recurrent neural network. Int. J. Approx. Reason., 23, pp. 67-83.
8. Garcia-Pedrajas, N., Hervas-Martinez, C. and Munoz-Perez, J. (2003) COVNET: A cooperative coevolutionary model for evolving artificial neural networks. IEEE Trans. Neural Netw., 14, 575-596.
9. Fieldsend, J. and Singh, S. (2005) Pareto evolutionary neural networks. IEEE Trans. Neural Netw., 16, 338-354.
10. Coello Coello, C.A., Van Veldhuizen, D.A. and Lamont, G.B. (2002) Evolutionary Algorithms for Solving Multi-Objective Problems. Kluwer, New York.
11. Delgado, M., Cuellar, M.P. and Pegalajar, M.C. (2008) Multiobjective hybrid optimization and training of recurrent neural networks. IEEE Trans. Syst., Man, Cybern. B, Cybern., 38, 381-403.
12. Zitzler, E., Laumanns, M. and Thiele, L. (2001) SPEA2: Improving the Strength Pareto Evolutionary Algorithm. Comput. Eng. and Netw. Lab. (TIK), Swiss Federal Inst. Technol. (ETH), Zurich, Switzerland, Technical Report, Vol. 103.
13. Deb, K., Pratap, A., Agrawal, S. and Meyarivan, T. (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput., 6, 182-197.
14. Cai, X., Zhang, N.,Venayagamoorthy, G. andWunsch, D. (2004) Time series prediction with recurrent neural networks using a hybrid PSO-EA algorithm. Proc. IJCNN, Budapest, Hungary, pp. 1647-1652.
15. Cellier, F.E. and Nebot, A. (2004) Multi-resolution timeseries prediction using fuzzy inductive reasoning. Proc. IJCNN, Budapest, Hungary, pp. 1621-1624.
16. Sarkka, S., Vehtari, A. and Lampinen, J. (2004) Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks. Proc. IJCNN, Budapest, Hungary, pp. 1615-1619.
17. Wichard, J.D. and Ogorzalek, M. (2004) Time series prediction with ensemble models. Proc. IJCNN, Budapest, Hungary, pp. 1625-1630.
18. Lendasse, A., Oja, E., Simula, O. and Verlevsen, M. (2004) Time series prediction competition: The CATS benchmark. Proc. IJCNN, Budapest, Hungary, pp. 1615-1620.
19. Elman, J.L. (1990) Finding structure in time. Cogn. Sci., 14, 179-211.
20. Huang, B.Q., Rashid, T. and Kechadi, M.-T. (2006) Multicontext recurrent neural network for time series application. Int. J. Comput. Intell., 3, 45-54.
21. Thierens, D. (2002) Adaptive mutation rate control schemes in genetic algorithms. Proc. CEC '02, IEEE, Honolulu, HI, Vol. 1, pp. 980-985.
22. Agrawal, S., Dahora, Y., Tiwari, M. K. and Son, Y.-J. (2008) Interactive particle swarm: A pareto-adaptive metaheuristic to multiobjective optimization. IEEE Trans. Syst., Man, Cybern. A, Syst., Humans, 38, 258-277.
23. Back, T. and Schutz, M. (1996) Intelligent mutation rate control in canonical genetic algorithms. In Ras, Z.W. and Michalewicz, M. (eds.) Proc. Ninth International Symposium on Foundations of Intelligent Systems, Vol. 3. ser. LNAI, Berlin, pp. 158-167.
24. Herrera, F., Lozano, M. and Verdegay, J.L. (1998) Tackling real-coded genetic algorithms: Operators and tolls for behavioral analysis. Artif. Intell. Rev., 12, 265-319.
25. Gershenfeld N. and Weigend, A. (1991) The Santa Fe time series competition data [Online]. http://www-psych.stanford. edu/~andreas/Time-Series/ SantaFe.html
26. Hyndman, R.J. Time series data library [Online]. http://www.robjhyndman. com/TSDL/index.htm.
27. Jang, J.-S.R. IEEE neural networks council standards committee [Online]. http://neural.cs.nthu.edu.tw/jang/benchmark/.
28. Lendasse, A. (2004) International joint conference on neural networks: TIME SERIES PREDICTION COMPETITION, the CATS benchmark [Online]. http://www.cis.hut.fi/lendasse/competition/competition.html.
29. Suykens, J. (1998) International workshop on advanced blackbox techniques for nonlinear modeling: Theory and applications [Online]. http://www.esat. kuleuven.ac.be/sista/workshop/index.html.
30. NOAA satellite and information service [Online]. http://www.ngdc.noaa. gov/ngdc.html.
31. Hyndman, R.J. and Koehler, A.B. (2006) Another look at measures of forecast accuracy. Int J Forecast., 22, 679-688.