The Internet of Things and fast data streams: prospects for geospatial data science in emerging information ecosystems
The Internet of Things and fast data streams: prospects for geospatial data science in emerging information ecosystems
复制标题
DOI：
10.1080/15230406.2018.1503973
复制
发表时间：
2018-09
影响因子：
2.5
通讯作者：
M. Armstrong;Shaowen Wang;Zhe Zhang
中科院分区：
文献类型：
--
作者：
M. Armstrong;Shaowen Wang;Zhe Zhang
物联网的发展日新月异，其产生的海量数据流才刚刚开始，这些数据流给地理信息分析带来了机遇和挑战。这些挑战的出现是因为流数据量无法使用已被设计用于分析静态地理空间数据集的标准方法库进行分析。需要新的办法，不是取代而是补充这些现有的工具。重点放在数据速度（快速数据）的概念及其对采样和推理的影响。创新的数据摄取策略的基础上有关的原则，水库采样和素描。动态时态数据流对分布式（例如云）并行环境中的负载平衡提出了重大挑战，即使在exascale级别的性能下也是如此。需要进一步阐明在利用基于地理概念的数据局部性方面的进一步进展，以及基于边缘和近似计算的先进处理方法。概念说明使用数据库编译从分布式传感器网络的移动的放射性探测器。
ABSTRACT This paper surveys the rapid development of the Internet of Things, the massive data streams that are only now beginning to be generated from it, and the resulting opportunities and challenges that these data streams bring to geographic information analysis. These challenges arise because streaming data volumes cannot bt subjected to analysis using the standard repertoire of methods that have been designed to analyze static geospatial datasets. New approaches are needed, not to supplant, but to supplement, these existing tools. A focus is placed on the concept of data velocity (fast data) and its effects on sampling and inference. Innovative data ingestion strategies based on principles related to reservoir sampling and sketching are described. Dynamic temporal data flows present significant challenges to load balancing in distributed (e.g. cloud) parallel environments, even at exascale levels of performance. Further advances in the exploitation of data locality based on geographical concepts, as well as advanced processing methods based on edge and approximate computing, require further elucidation. Concepts are illustrated using a database compiled from a distributed sensor network of mobile radioactivity detectors.