Quantifying Uncertainty in Multivariate Time Series Pre-Processing
Quantifying Uncertainty in Multivariate Time Series Pre-Processing
复制标题
DOI：
10.2312/eurova.20191121
复制
发表时间：
2019
影响因子：
5.2
通讯作者：
C. Bors;J. Bernard;M. Bögl;T. Gschwandtner;J. Kohlhammer;S. Miksch
中科院分区：
文献类型：
--
作者：
C. Bors;J. Bernard;M. Bögl;T. Gschwandtner;J. Kohlhammer;S. Miksch
在多元时间序列分析中，预处理是实现分析的必要条件，但不可避免地会给数据带来不确定性。为了评估不确定性并允许不确定性意识分析，不确定性需要最初量化。我们通过形式化多变量时间序列预处理的不确定性量化来解决这一挑战。为了处理大的设计空间，我们详细阐述了量化和聚合不确定性的关键考虑因素。我们提供了一个例子，如何在多变量时间序列预处理应用中使用量化的不确定性来评估预处理步骤的有效性，并调整管道以最大限度地减少不确定性的引入。CCS概念•计算数学→时间序列分析；•信息系统→不确定性；•以人为中心的计算→可视化理论、概念和范式；视觉分析;•计算方法→不确定度量化；
In multivariate time series analysis, pre-processing is integral for enabling analysis, but inevitably introduces uncertainty into the data. Enabling the assessment of the uncertainty and allowing uncertainty-aware analysis, the uncertainty needs to be quantified initially. We address this challenge by formalizing the quantification of uncertainty for multivariate time series preprocessing. To tackle the large design space, we elaborate key considerations for quantifying and aggregating uncertainty. We provide an example how the quantified uncertainty is used in a multivariate time series pre-processing application to assess the effectiveness of pre-processing steps and adjust the pipeline to minimize the introduction of uncertainty. CCS Concepts •Mathematics of computing → Time series analysis; • Information systems → Uncertainty; •Human-centered computing → Visualization theory, concepts and paradigms; Visual analytics; • Computing methodologies → Uncertainty quantification;