摘要
由于现有的采用欧氏距离确定相空间最邻近点的混沌预测方法对高维混沌时间序列预测的效果不太理想 ,因而首次提出以关联度代替欧氏距离来确定相空间最邻近点的思想。通过对水文径流序列预测的验证 ,在嵌入维数逐渐增大时 。
The chaos forecasting methods used recently, which apply Euclid distance to determine the nearest point in phase space to forecast chaos time series with high dimensions, are not so effective. In this paper, one new idea based on incidence-degree instead of Euclid distance is firstly put forward to determine the nearest point in phase space. The test result of runoff forecasting series shows that the precision of runoff forecasting is greatly improved by means of the new method when the embedded dimensions is high, compared with the method used recently.\;
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2002年第12期65-66,103,共3页
Systems Engineering and Electronics
基金
国家自然科学基金资助课题 (5 0 0 790 0 6)
关键词
关联度
混沌
径流预测
高嵌入维数
水文径流
Chaos
Degree of incidence
Runoff forecasting
High embedding dimension