Paper:

# Time-Series Forecasting Using Fuzzy-Neural System with Evolutionary Rule Base

## Arit Thammano^{*} and Sirinda Palahan^{**}

^{*}Computational Intelligence Laboratory, Faculty of Information Technology, King Mongkut’s Institute of Technology Ladkrabang, Ladkrabang, Bangkok 10520, Thailand

^{**}School of Science, University of the Thai Chamber of Commerce, 126/1 Vibhavadee-Rangsit Road, Dindaeng, Bangkok 10400, Thailand

This paper proposes a new hybrid time-series forecasting system which is the fusion of fuzzy systems and artificial neural networks. The proposed fuzzy-neural system consists of 5 layers: an input layer, fuzzification layer, rule layer, hidden layer, and output layer. The artificial neural network is used as the fuzzy inference engine and the genetic algorithm is used to optimize the fuzzy rule base. This proposed system was tested with 20 time-series datasets. The results obtained were very encouraging.

*J. Robot. Mechatron.*, Vol.18, No.5, pp. 672-679, 2006.

- [1] B. Bouqata, A. Bensaid, R. Palliam, and A. F. Gómez Skarmeta, “Time series prediction using crisp and fuzzy neural networks: A comparative study,” Proceedings of the IEEE/ IAFE/ INFORMS 2000 Conference on Computational Intelligence for Financial Engineering, pp. 170-173, 2000.
- [2] T. Masters, Practical neural network recipes in C++, Academic Press, 1993.
- [3] T. Kolarik and G. Rudorfer, “Time series forecasting using neural networks,” APL Quote Quad, 25(1), pp. 86-94, 1994.
- [4] T. Chenoweth, Z. Obradovic, and S. S. Lee, “Embedding technical analysis into neural network based trading systems,” Applied Artificial Intelligence, 10(6), pp. 523-541, 1996.
- [5] P. K. Dash, G. Ramakrishna, A. C. Liew, and S. Rahman, “Fuzzy neural networks for time-series forecasting of electric load,” IEE Proceedings-Generation, Transmission and Distribution, 142(5), pp. 535-544, 1995.
- [6] A. Thammano, “A new forecasting approach with neuro-fuzzy architecture,” Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, pp. 386-389, 1999.
- [7] M. Valença and T. Ludermir, “Monthly streamflow forecasting using a neural fuzzy network model,” Proceedings of the 6
^{th}Brazilian Symposium on Neural Networks, pp. 117-119, 2000. - [8] P. K. Kasabov and Q. Song, “DENFIS: Dynamic evolving neural-fuzzy inference system and its application for time-series prediction,” IEEE Transactions on Fuzzy Systems, 10(2), pp. 144-154, 2002.
- [9] K. H. Lee, First course on fuzzy theory and applications, Springer, 2005.
- [10] A. M. Tang, C. Quek, and G. S. Ng, “GA-TSKfnn: Parameters tuning of fuzzy neural network using genetic algorithms,” Expert Systems with Applications, 29(4), pp. 769-781, 2005.
- [11] J. S. R. Jang, “ANFIS: Adaptive-Network-Based Fuzzy Inference System,” IEEE Transactions on Systems, Man, and Cybernetics, 23(3), pp. 665-685, 1993.
- [12] J. Yen and R. Langari, Fuzzy logic: Intelligence, control, and information, Prentice Hall, 1999.
- [13] K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” Neural Networks, 2, pp. 359-366, 1989.
- [14] M2 Competition, Retrieved May 27, 2003, from

http://www.forecasters.org/data/m2comp/m2comp.htm - [15] M3 Competition, Retrieved May 27, 2003, from

http://www.forecasters.org/data/m3comp/m3comp.htm - [16] M. C. Mackey and L. Glass, “Oscillation and chaos in physiological control system,” Science, 197, pp. 287-289, 1977.
- [17] S. Makridakis, S. C. Wheelwright, and R. J. Hyndman, Forecasting: Methods and Application, Wiley, 1998.

Copyright© 2006 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.