Actionable Insights in Urban Multivariate Time-series
Actionable Insights in Urban Multivariate Time-series
复制标题
DOI：
10.1145/3459637.3482410
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Anika Tabassum;S. Chinthavali;Varisara Tansakul;B. Prakash
中科院分区：
文献类型：
--
作者：
Anika Tabassum;S. Chinthavali;Varisara Tansakul;B. Prakash
多元时间序列数据在应急管理、公共卫生等各种城市应用中越来越受欢迎。分割算法主要关注于识别这些数据中具有变化相位的离散事件。例如，考虑飓风期间停电的场景。每个时间序列可以表示一个国家在一段时间内的电力故障数量。这些时间序列中的片段是根据不同的阶段发现的，例如，当飓风开始时，郡县面临严重破坏，飓风结束时。灾害管理领域的专家通常希望在这些阶段确定受影响最严重的县（利益的时间序列）。这些可以有效地进行回顾性分析和决策，以便向这些地区分配资源，以减轻损害。然而，直接获得这些可操作的县（通过简单的可视化或查看分割算法）通常是困难的。因此，我们引入并形式化了一个新的问题RaTSS（合理化的时间序列分割），旨在找到这样的时间序列（合理化），这是可操作的分割。我们还提出了一种算法find - ratss来查找任何黑箱分割。我们发现Find-RaTSS在广义合成数据和真实数据上优于非平凡基线，还在多个城市领域，特别是灾害和公共卫生领域提供了可操作的见解。
Multivariate time-series data are gaining popularity in various urban applications, such as emergency management, public health, etc. Segmentation algorithms mostly focus on identifying discrete events with changing phases in such data. For example, consider a power outage scenario during a hurricane. Each time-series can represent the number of power failures in a county for a time period. Segments in such time-series are found in terms of different phases, such as, when a hurricane starts, counties face severe damage, and hurricane ends. Disaster management domain experts typically want to identify the most affected counties (time-series of interests) during these phases. These can be effective for retrospective analysis and decision-making for resource allocation to those regions to lessen the damage. However, getting these actionable counties directly (either by simple visualization or looking into the segmentation algorithm) is typically hard. Hence we introduce and formalize a novel problem RaTSS (Rationalization for time-series segmentation) that aims to find such time-series (rationalizations), which are actionable for the segmentation. We also propose an algorithm Find-RaTSS to find them for any black-box segmentation. We show Find-RaTSS outperforms non-trivial baselines on generalized synthetic and real data, also provides actionable insights in multiple urban domains, especially disasters and public health.