基于嵌入理论和神经网络技术的混沌数据预测及其在股票市场中的应用

被引:15
作者
杨一文
刘贵忠
张宗平
机构
[1] 西安交通大学电信学院信息与通信工程系!陕西西安
关键词
相空间重构; 神经网络; 预测;
D O I
暂无
中图分类号
F830.59 [投资]; TP183 [人工神经网络与计算];
学科分类号
120204 ;
摘要
提出了一种将延迟 -嵌入定理与人工神经网络相结合预测混沌数据的基本方法 ,首先讨论了嵌入延迟时间和嵌入维的计算方法 ,并从信号处理的角度分析了相空间重构同预测的关系 ,并以此确定神经网络的输入层结构 ;最后应用于股票指数和价格的预测 ,结果表明这种方法对解决一类问题具有广阔的前景 .
引用
收藏
页码:52 / 58+78 +78
页数:8
相关论文
共 9 条
[1]  
Johnson M A.The Random Walk and Beyond: An Inside Guide to the Stock Market. . 1989
[2]  
Alan Wolf,et al.Determining Lyapunov exponents from a time series. Physica D Nonlinear Phenomena . 1985
[3]  
Frosyth T B.A study of the ability of financial ratios to predict corporate failure and the relationship between bankruptcy model probability assessments and stock market behavior. . 1992
[4]  
Edgar E Peters.Chaos and Order in the Capital Markets. . 1991
[5]  
Edgar E Peters.Fractal Market Analysis: Applying Chaos Theory to Investment and Economics. . 1994
[6]  
Matthew B Kennel,et al.Determining embedding dimension for phase-space reconstruction using a geometrical construction. Physical Review . 1992
[7]  
Andrew M Fraser et al.Independent coordinates for strange attractors from mutual information. Physical Review . 1986
[8]  
Abarbanel H,et al.The analysis of observed chaotic data in physical system. Reviews of Modern Physics . 1993
[9]  
Haykin S,et al.Making sense of a complex world. IEEE Signal Processing Magazine . 1998