An Increasing Hybrid Morphological-Linear Perceptron with Evolutionary Learning and Phase Correction for Financial Time Series Forecasting
In this paper we present a suitable model to solve the financial time series forecasting problem, called increasing hybrid morphological-linear perceptron (IHMP). An evolutionary training algorithm is presented to design the IHMP (learning process), using a modified genetic algorithm (MGA). The learning process includes an automatic phase correction step that is geared at eliminating the time phase distortions that typically occur in financial time series forecasting. Furthermore, we compare the proposed IHMP with other neural and statistical models using two complex nonlinear problems of financial forecasting.
KeywordsLattice Theory Minimax Algebra Morphological Neural Networks Genetic Algorithms Financial Time Series Forecasting
Unable to display preview. Download preview PDF.
- 2.Gader, P.D., Khabou, M.A., Koldobsky, A.: Morphological regularization neural networks. Pattern Recognition, Special Issue on Mathematical Morphology and Its Applications 33(6), 935–945 (2000)Google Scholar
- 4.Sussner, P., Esmi, E.L.: Introduction to morphological perceptrons with competitive learning. In: Proceedings of the International Joint Conference on Neural Networks, Atlanta, GA, pp. 3024–3031 (2009)Google Scholar
- 5.Sussner, P., Esmi, E.L.: Morphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm. Information Sciences (2009) (accepted for publication)Google Scholar
- 6.Serra, J.: Image Analysis and Mathematical Morphology, Theoretical Advances, vol. 2. Academic Press, New York (1988)Google Scholar
- 11.Sussner, P., Esmi, E.L.: Constructive morphological neural networks: some theoretical aspects and experimental results in classification. In: Kacprzyk, J. (ed.) Constructive Neural Networks. Studies in Computational Intelligence. Springer, Heidelberg (2009)Google Scholar
- 12.de A. Araújo, R., Madeiro, F., de Sousa, R.P., Pessoa, L.F.C., Ferreira, T.A.E.: An evolutionary morphological approach for financial time series forecasting. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 2467–2474 (2006)Google Scholar
- 14.de A. Araújo, R., Ferreira, T.A.E.: A morphological-rank-linear evolutionary method for stock market prediction. Information Sciences (in Press, 2010)Google Scholar
- 19.Haykin, S.: Neural networks: A comprehensive foundation. Prentice Hall, New Jersey (1998)Google Scholar
- 21.Birkhoff, G.: Lattice Theory, 3rd edn. American Mathematical Society, Providence (1993)Google Scholar
- 22.Prechelt, L.: Proben1: A set of neural network benchmark problems and benchmarking rules. Technical Report 21/94 (1994)Google Scholar