arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1504.06274cs.LGstat.ML
收藏

生理时间序列的一种新方法

A new approach for physiological time series

AMSL Brion;Hong Kong University of Science and Technology(香港科技大学);Middle Tennessee State University(中田纳西州立大学)

Dong Mao, Yang Wang, Qiang Wu

摘要:

我们开发了一种新的方法来分析生理时间序列。迭代卷积滤波器用于将时间序列分解成各种分量。这些组件的统计数据被提取为特征,以表征时间序列的机制。研究表明,许多正常的生理系统都涉及不规则性,而不规则性的减少通常意味着异常,因此,组件中的“离群值”的统计数据被用作测量不规则性的特征。支持向量机被用来选择最相关的功能,能够区分正常和异常系统的时间序列。这种新的方法被成功地用于充血性心力衰竭的心搏间期时间序列的研究。

英文摘要:

We developed a new approach for the analysis of physiological time series. An iterative convolution filter is used to decompose the time series into various components. Statistics of these components are extracted as features to characterize the mechanisms underlying the time series. Motivated by the studies that show many normal physiological systems involve irregularity while the decrease of irregularity usually implies the abnormality, the statistics for "outliers" in the components are used as features measuring irregularity. Support vector machines are used to select the most relevant features that are able to differentiate the time series from normal and abnormal systems. This new approach is successfully used in the study of congestive heart failure by heart beat interval time series.

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。

↑