误差熵的估计问题研究  

On Estimation of Error Entropy

作　　者：游扬声[1,2] 马力[2] 刘星[1] 

机构地区：[1]重庆大学土木工程学院,重庆市400044 [2]重庆市气象局,重庆市401147

出　　处：《武汉大学学报（信息科学版）》2008年第7期748-751,共4页Geomatics and Information Science of Wuhan University

基　　金：重庆市自然科学基金资助项目(2007BB2193);国家自然科学基金资助项目(40674015)

摘　　要：指出了具有复杂分布的随机量的总体熵的估计问题,首次给出了估计熵的最小截断误差限。推导了样本熵的近似估计公式,引入最优窗宽、全局最优窗宽的算法,首次解决了样本熵的估计值不惟一的问题。It is generally rather difficult to calculate the entropy of a random quantum in complicated distribution, for the truncation error must be considered when an infinite integral is conduced. The expressions of truncation error with integral limit is derived successfully. What is more, the expression for approximately estimating sample entropy is preserced by introducing optimal window-width arithmetic and the overall optimal window-width arithmetic. As a result, the problem of uncertain estimation value of the sample entropy is solved.

关 键 词：熵 不确定度 截断误差 核估计 窗宽 

分 类 号：P207[天文地球—测绘科学与技术]