Stock Index Prediction Based on Multi-Level Transfer Function Quantum Neural Tree

Abstract:

The FlexibleNeural Tree uses a tree structure coding and has excellent predictiveability and function approximation capabilities. Due to it, a quantum neural tree model ispresented based on the multi-level transfer function quantum neuralnetwork and Flexible Neural Tree. In the new model, based on the structure of FlexibleNeural Tree, the transfer function of hidden layer quantum neurons is insteadof multiple superposition oftraditional transfer function, makes the model has a kind of inherent ambiguity.This paper used the improved neural tree asprediction model, particle swarm optimization to optimize the parameters of neuraltree, used probabilistic incremental program evolution to optimizethe structure of neural tree. The experiment result for stock index predictionshows the now method can improve the predictive accuracy rate

• Periodical: Applied Mechanics and Materials (Volumes 457-458)
• Pages: 1102-1106
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.457-458.1102
• Online since: October 2013
• Authors: Hao Teng, Shu Hui Liu, Yue Hui Chen
• Keywords: Flexible Neural Tree, Multi-Level Transfer Function, Quantum Neural Network, Stock Index Prediction

References

[1] V. Venkatasubramanian, R. Vaidyanathan, Y. Yamamoto. Process fault detection and diagnosis using neural networks—I. Steady-state processes[J]. Computers & Chemical Engineering, 1990, vol. 14, pp.699-712.

DOI: 10.1016/0098-1354(90)87081-y

[2] R. Salustowicz, J. Schmidhuber. Probabilistic incremental program evolution[J]. Evolutionary Computation, 1997, vol. 14, pp.123-141.

DOI: 10.1162/evco.1997.5.2.123

[3] J. Kennedy, R. Eberhart [C]/C., Particle swarm optimization, Proceedings of IEEE International Conference on Neural Networks, Piscataway, NJ. 1995: 1942-(1948).

[4] Y. Chen, B. Yang and J. Dong, Nonlinear System Modeling via Optimal Design of Neural Trees, International Journal of Neural Systems, Vol. 14, No. 2, pp.125-137, (2004).

DOI: 10.1142/s0129065704001905

[5] Y. Chen, B. Yang, J. Dong and A., Time-series Forecasting Using Flexible Neural Tree Model, Information Science, Vol. 174, Issues 3/4, pp.219-235, (2005).

DOI: 10.1016/j.ins.2004.10.005

[6] Y. Chen, A. Abraham, J. Yang and B. Yang, Hybrid Methods for Stock Index Modeling,  Fuzzy Systems and Knowledge Discovery: Second International Conference (FSKD 2005), China, Lecture Notes on Computer Science 3614, pp.1067-1070, (2005).

DOI: 10.1007/11540007_137

[7] Y. Chen, A. Abraham, Y. Zhang, Ensemble of Flexible Neural Trees for Breast Cancer Detection, The International Journal of Information Technology and Intelligent Computing, Vol. 1, No. 1, pp.187-201, (2006).

[8] Y. Chen, L. Peng, A. Abraham, Stock Index Modeling using Hierarchical RBF Networks, 10th International Conference on Knowledge-Based & Intelligent Information & Engineering Systems (KES'06), Part III, Lecture Notes on Artificial Intelligence, Vol. 4253, pp.398-405, (2006).

DOI: 10.1007/11893011_51

[9] Y. Shi, R. Eberhart, A modified particle swarm optimizer[C] /Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on. IEEE, 1998, pp.69-73.

DOI: 10.1109/icec.1998.699146

[10] D. Zhu, R. Wu, A multi-layer quantum neural networks recognition system for handwritten digital recognition[C]/Natural Computation, 2007. ICNC 2007. Third International Conference on. IEEE, 2007, 1, pp.718-722.

DOI: 10.1109/icnc.2007.70

[11] Gopathy P, Nicolaos B, Karayiannis NB, Quantum neural networks: Inherently fuzzy feedforwardneural networks, IEEE Trans on Neural Networks, vol. 8, pp.679-693, (1997).

DOI: 10.1109/72.572106

[12] X. Huang, Y. Chen, X. Feng, Optimization of Flexible Neural Tree Based on Improved Particle Swarm, Computer system & applications, 2010, Vol. 19 No. 8，pp.96-99 (in Chinese).