arXivDaily arXiv每日学术速递 周一至周五更新
arXiv physics/0608069physics.data-an
收藏

时间序列的多尺度重构

Multiscale reconstruction of time series

A. P. Nawroth, J. Peinke

摘要:

提出了一种新的方法,它允许重建的时间序列的基础上给出的一个分层过程的高阶多尺度统计。该方法不仅能够在特定尺度上对时间序列进行建模,而且能够在一定范围内对时间序列进行建模。可以生成完整的新时间序列,或者为给定的数据序列建模后续步骤。该方法本身是基于联合概率密度,它可以直接从给定的数据中提取,因此没有参数估计是必要的。这种方法的结果示出了一个真实世界的数据集,即湍流。原始和重建的时间序列的无条件和条件概率密度进行比较,并证明了再现这两种能力。因此,在马尔可夫性质的情况下,这里提出的方法能够生成具有正确的n点统计量的人工时间序列。

英文摘要:

A new method is proposed which allows a reconstruction of time series based on higher order multiscale statistics given by a hierarchical process. This method is able to model the time series not only on a specific scale but for a range of scales. It is possible to generate complete new time series, or to model the next steps for a given sequence of data. The method itself is based on the joint probability density which can be extracted directly from given data, thus no estimation of parameters is necessary. The results of this approach are shown for a real world dataset, namely for turbulence. The unconditional and conditional probability densities of the original and reconstructed time series are compared and the ability to reproduce both is demonstrated. Therefore in the case of Markov properties the method proposed here is able to generate artificial time series with correct n-point statistics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑