Browse > Article
http://dx.doi.org/10.5391/IJFIS.2008.8.1.031

Evolvable Neural Networks for Time Series Prediction with Adaptive Learning Interval  

Seo, Sang-Wook (School of Electrical and Electronic Engineering, Chung-Ang University)
Lee, Dong-Wook (School of Electrical and Electronic Engineering, Chung-Ang University)
Sim, Kwee-Bo (School of Electrical and Electronic Engineering, Chung-Ang University)
Publication Information
International Journal of Fuzzy Logic and Intelligent Systems / v.8, no.1, 2008 , pp. 31-36 More about this Journal
Abstract
This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the enviromuent. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.
Keywords
Evolvable neural networks; Time series prediction; Adaptive learning interval; L-system; DNA coding;
Citations & Related Records
연도 인용수 순위
  • Reference
1 H. A. Mayer and R. Schwaiger, "Evolutionary and coevolutionary approaches to time series prediction using generalized multi-layer predictions," Proc. of Congress on Evolutionary Computation, Vol. 1, pp.275-280, 1999
2 S. G. Kong, "Time series prediction with evolvable block-based neural networks," Proc. of Int. Joint Conf. on Neural Networks (IJCNN), 2004
3 X. Yao, "Evolving artificial neural networks," Proceedings of the IEEE, Vol. 87, No. 9, pp.1423-1447, 1999   DOI   ScienceOn
4 P. J. Angeline, G. M. Sauders, and J. B. Pollack, "An evolutionary algorithm that constructs recurrent neural networks," IEEE Trans. on Neural Networks, Vol. 5, No. 1, pp.54-65, 1994   DOI   ScienceOn
5 B. L. M Happel and J. M. J. Murre, "The design and evolution of modular neural network architecture," Neural Networks, Vol. 7, pp.985-1004, 1994   DOI   ScienceOn
6 M. S. Kim and S. G. Kong, "Parallel-structure fuzzy system for time series prediction," Int. J. of Fuzzy Systems, Vol. 3, No. 1, pp.331-339, 2001
7 A. Lindenmayer, "Mathematical models for cellular interaction in development, Part I, II," Journal of Theoretical Biology, Vol. 18, No. 3, pp.280-315, 1968   DOI
8 J. R. McDonnell and D. Waagen, "Evolving Recurrent Perceptrons for time-series modeling," IEEE Trans. on Neural Networks, Vol 5, No. 1, pp.24-38, 1994   DOI   ScienceOn
9 A. S. Wu and R. K. Lindsay, "A computation of the fixed and floating building block representation in genetic algorithms," Evolutionary Computation, Vol. 4, No. 2, pp.169-193, 1996   DOI   ScienceOn
10 E. J. W. Boers and I. G. Sprinkhuizen-Kuyper, "Combined biological metaphors," Advances in the Evolutionary Synthesis of Intelligent Agents, M. J. Patel, V. Honavar, and K. Balakrishnan, Eds., MIT Press, Ch. 6, pp.153-183, 2001
11 Y. Yoshikawa, T. Furuhashi, and Y. Uchikawa, "Knowledge acquisition of fuzzy control rules using DNA coding method and pseudo-bacterial GA," Lecture Notes in Artificial Intelligence, Springer, Vol. 1285, pp.126-135, 1997
12 S. W. Moon and S. G. Kong, "Block-based Neural Networks," IEEE Trans. on Neural Networks, Vol. 12, No. 2, pp.307-317, 2001   DOI   ScienceOn
13 F. Gruau, "Automatic definition of modular neural networks," Adaptive Behavior, Vol. 3, No. 2, pp.151-183, 1995   DOI
14 A. Cangelosi, S. Nolfi, and D. Parisi, "Artificial life models of neural development," On Growth, Form and Computers, S. Kumar and P. J. Bently, Eds., Elsevier Academic Press, pp.339- 352, 2003
15 J. Kodjabachian and J. A. Meyer, "Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects," IEEE Trans. on Neural Networks, Vol. 9, No. 5, pp.796-812, 1998   DOI   ScienceOn
16 X. Yao and Y. Lie, "A new evolutionary system for evolving artificial neural networks," IEEE Trans. on Neural Networks, Vol. 8, No. 3, pp.54-65, 1994
17 F. H. F. Leung, H. K. Lam, S. H. Ling, and P. K. S. Tam, "Tuning of the structure and parameters of neural network using an improved genetic algorithm," IEEE Trans. on Neural Networks, Vol. 14, No. 1, pp.79-88, 2003   DOI   ScienceOn
18 M. C. Mackey and L. Glass, "Oscillation and chaos in physiological control systems," Science, Vol. 197, pp.287-289, 1977   DOI