摘要
对于三维空间中时间序列的复杂度分析,多采用多尺度样本熵(MSE),针对MSE方法随着时间序列复杂度的增加样本熵估计的准确率下降的缺陷,提出采用多尺度样本熵模型。对提出的MSE模型进行实验验证分析,根据时间序列复杂程度的不同,分别采用复合多尺度样本熵(CMSE)以及改进复合多尺度样本熵(RCMSE)对时间序列进行研究分析,得出不同的仿真结果。证明对于时间序列的复杂度研究,采用MSE的方法能达到提高准确率的效果。
The multiscale sample entropy(MSE)is mostly used to analyze the time series complexity in3D space.Sincethe time series complexity of MSE method can reduce the accuracy of the sample entropy estimation with the increase of time series complexity,a multiscale sample entropy model is proposed.The experiments were carried out to verify the multiscale sample entropy model.According to the different complexity of time sequences,the composite multiscale sample entropy(CMSE)and refined composite multiscale sample entropy(RCMSE)are used respectively to study and analyze the time series to obtaindifferent simulation results.The result proves that the multi-scale sample entropy method can achieve the effect of improving theaccuracy rate.
作者
尚传福
SHANG Chuanfu(Institute of Mathematics and Information Engineering,Chongqing University of Education,Chongqing 400065,China)
出处
《现代电子技术》
北大核心
2017年第17期40-43,共4页
Modern Electronics Technique
基金
重庆市统筹城乡教师教育研究中心工作室资助项目
