...
首页> 外文期刊>Zeitschrift fur Angewandte Mathematik und Mechanik >Adaptively Wavelet—smoothed Wigner Estimates of Evolutionary Spectra
【24h】

Adaptively Wavelet—smoothed Wigner Estimates of Evolutionary Spectra

机译:进化谱的自适应小波平滑Wigner估计

获取原文
获取原文并翻译 | 示例
           

摘要

We consider adaptive estimation of the evolutionary spectrum in the model of a locally stationary time series in the time-frequency plane. The estimate is based on a modification of a time-dependent periodogram (spectogram), which can be considered as a sort of smoothed pseudo-Wigner estimate. In our approach, the separable time-frequency smoothing kernel (weight) function is built by using 2-d tensor product wavelets which allows independent smoothing in both time and frequency. The estimator becomes adaptive to the local structure (and possibly different degree of smoothness) of the evolutionary spectrum, as we use non-linear thresholding of the empirical wavelet coefficients. Unlike traditional linear smoothing schemes, our estimator attains the usual near-optimal L_2-minimax rate, even for spectra with regularity being inhomogeneously distributed over the time-frequency plane.
机译:我们在时频平面中的局部平稳时间序列模型中考虑进化谱的自适应估计。该估计基于对时间相关的周期图(频谱图)的修改,可以将其视为一种平滑的伪维格纳估计。在我们的方法中,可分离的时频平滑核(权重)函数是通过使用二维张量积小波构建的,该函数允许在时间和频率上进行独立的平滑。当我们使用经验小波系数的非线性阈值时,估计器变得适应于演化谱的局部结构(可能还有不同程度的平滑度)。与传统的线性平滑方案不同,即使对于规则性不均匀分布在时频平面上的频谱,我们的估算器也能达到通常的接近最佳L_2-minimax速率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号