中文摘要：

根据艾略特波浪理论以及波浪理论中的各参数具有费波纳奇数列关系的特征,分析股票价格波形的特点;运用人工神经网络模型,提出基于波形分解与重构的神经网络预测方法,给出具体的实现过程。研究结果表明：通过波形分解与重构,把原始价格时间序列分解为规律相对简单、不同频率范围内的子波动序列来提高神经网络的预测精度,实现对特征不同的信号选取不同的参数模型进行预测;采用傅里叶反变换拟合出股价波动变化趋势的曲线,以达到预测股价波动变化周期的目的。

英文摘要：

According to Elliott wave theory and wave theory of the Fibonacci array,the stock price profile characteristics were analyzed.The neural network was researched and a neural network prediction method was brought out.Its concrete realization process based on wavelet decomposition and reconstruction were made.The results show that through this method,the price function is decomposed into a series of wavelets in different frequency ranges,whose fluctuation rule can be easily grasped.This method increases the neural network prediction precision,and makes it possible to predict signals with prediction models of different parameters.The inverse Fourier transform can be used to fit the stock price fluctuation change tendency,and to forecast stock price fluctuation cycle.