Introducing the contrast profile: a novel time series primitive that allows real world classification

Introducing the contrast profile: a novel time series primitive that allows real world classification
复制标题

介绍对比度配置文件:一种新颖的时间序列原语,允许现实世界分类

DOI:
10.1007/s10618-022-00824-5
复制
发表时间:
2022
影响因子:
4.8
通讯作者:
Ryan Mercer, Sara Alaee
Ryan Mercer, Sara Alaee
中科院分区:
计算机科学3区
文献类型:
--
作者:
Ryan Mercer, Sara Alaee

文献摘要

参考文献

相似文献

时间序列数据仍然是数据挖掘中考虑的一种长期重要的数据类型。在过去的十年里,人们越来越认识到,时间序列数据可以通过推理时间序列的相似性的基础上,他们与其他的相似性:两个最熟悉的这样的时间序列概念是motifs和discords。时间序列基序指的是两个特别接近的连续性,而时间序列不一致表示距离最近的邻居很远的连续性。然而,我们认为,它有时是有用的,同时原因的子序列的接近某些数据和其他数据的距离。在这项工作中,我们引入了一种新的原语称为对比度配置文件,使我们能够有效地计算这样的定义在一个原则性的方式。正如我们将要展示的,对比度配置文件有许多下游用途,包括异常检测、数据探索和预处理非结构化数据以进行分类。我们通过展示它如何允许在具有数百亿数据点的数据集中进行端到端分类,以及如何使用它来探索数据集并揭示可能逃脱我们注意的微妙模式,来展示对比度配置文件的实用性。此外,我们展示了对比度配置文件的一般性,在地震学,动物行为学和心脏病学等领域的详细案例研究。
Time series data remains a perennially important datatype considered in data mining. In the last decade there has been an increasing realization that time series data can be best understood by reasoning about time series subsequences on the basis of their similarity to other subsequences: the two most familiar such time series concepts beingmotifsanddiscords. Time series motifs refer to two particularly close subsequences, whereas time series discords indicate subsequences that are far from their nearest neighbors. However, we argue that it can sometimes be useful to simultaneously reason about a subsequence’s closeness to certain data and its distance to other data. In this work we introduce a novel primitive called the Contrast Profile that allows us to efficiently compute such a definition in a principled way. As we will show, the Contrast Profile has many downstream uses, including anomaly detection, data exploration, and preprocessing unstructured data for classification. We demonstrate the utility of the Contrast Profile by showing how it allows end-to-end classification in datasets with tens of billions of datapoints, and how it can be used to explore datasets and reveal subtle patterns that might otherwise escape our attention. Moreover, we demonstrate the generality of the Contrast Profile by presenting detailed case studies in domains as diverse as seismology, animal behavior, and cardiology.
MERLIN:海量时间序列档案中任意长度异常的无参数发现
DOI: 10.1109/icdm50108.2020.00147
发表时间: 2020
期刊: ICDM 2020
影响因子: --
作者:
Nakamura, Takaaki;Imamura, Makoto;Mercer, Ryan;Keogh, Eamonn
通讯作者: Keogh, Eamonn
时间序列数据挖掘的瑞士军刀:使用矩阵配置文件和十行代码可以做的十件有用的事情
DOI: 10.1007/s10618-019-00668-6
发表时间: 2020
影响因子: 4.8
作者:
Yan Zhu;Shaghayegh Gharghabi;Diego Furtado Silva;Hoang Anh Dau;Chin;N. S. Senobari;Abdulaziz Almaslukh;Kaveh Kamgar;Zachary Zimmerman;G. Funning;A. Mueen;E. Keogh
通讯作者: E. Keogh
探测、分析和消除洞察号火星地震数据中的故障
DOI: --
发表时间: 2020
影响因子: 3.1
作者:
John‐Robert Scholz;R. Widmer;P. Davis;P. Lognonné;B. Pinot;Raphaël F. Garcia;K. Hurst;L. Pou;F. Nimmo;S. Barkaoui;Sebastien de Raucourt;B. Knapmeyer‐Endrun;M. Knapmeyer;G. Orhand;N. Compaire;Arthur Cuvier;É. Beucler;Mickael Bonnin;R. Joshi;G. Sainton;É. Stutzmann;M. Schimmel;A. Horleston;M. Böse;S. Ceylan;J. Clinton;M. van Driel;T. Kawamura;Amir Khan;S. Stähler;D. Giardini;C. Charalambous;A. Stott;W. Pike;Ulrich R. Christensen;W. Banerdt
通讯作者: W. Banerdt
DOI: 10.1038/nature04931
发表时间: 2006-07-13
期刊: NATURE
影响因子: 64.8
作者:
Shelly, David R.;Beroza, Gregory C.;Nakamula, Sho
通讯作者: Nakamula, Sho
时间序列分类:研究鸡行为时在(字面)领域学到的经验教训
DOI: --
发表时间: 2019
期刊: 2019 IEEE International Conference on Big Data (Big Data)
影响因子: --
作者:
Alireza Abdoli;A. Murillo;A. Gerry;Eamonn J. Keogh
通讯作者: Eamonn J. Keogh