arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.06653cs.DB
收藏

基于时空轨迹的疑似感染人群检测

Efficient Suspected Infected Crowds Detection Based on Spatio-Temporal Trajectories

Huajun He, Ruiyuan Li, Rubin Wang, Jie Bao, Yu Zheng, Tianrui Li

摘要:

病毒在人与人之间的传播是全球公众面临的紧急事件。早期发现和隔离潜在的易感人群可以有效地控制其疾病的流行。现有的指标不能正确地解决轨迹上的感染率。为了解决这个问题,我们提出了一种新的时空感染率(IR)措施的基础上,人类的移动轨迹,可以充分描述被感染的风险由一个给定的查询轨迹的病人。然后,我们管理源数据通过一个有效的时空索引,使我们的系统更具可扩展性,并可以快速查询易感人群从海量的轨迹。此外,我们设计了几种剪枝策略,可以有效地减少计算量。此外,我们设计了一个空间首次(SFT)索引,这使我们能够快速查询多个轨迹,而没有太多的I/O消耗和数据冗余。基于真实和合成轨迹数据集的实验证明了该解决方案的性能,这些数据集显示了我们解决方案的有效性和效率。

英文摘要:

Virus transmission from person to person is an emergency event facing the global public. Early detection and isolation of potentially susceptible crowds can effectively control the epidemic of its disease. Existing metrics can not correctly address the infected rate on trajectories. To solve this problem, we propose a novel spatio-temporal infected rate (IR) measure based on human moving trajectories that can adequately describe the risk of being infected by a given query trajectory of a patient. Then, we manage source data through an efficient spatio-temporal index to make our system more scalable, and can quickly query susceptible crowds from massive trajectories. Besides, we design several pruning strategies that can effectively reduce calculations. Further, we design a spatial first time (SFT) index, which enables us to quickly query multiple trajectories without much I/O consumption and data redundancy. The performance of the solutions is demonstrated in experiments based on real and synthetic trajectory datasets that have shown the effectiveness and efficiency of our solutions.

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。

↑