A Nondeterministic Normalization based Scan Statistic (NN-scan) towards Robust Hotspot Detection: A Summary of Results
A Nondeterministic Normalization based Scan Statistic (NN-scan) towards Robust Hotspot Detection: A Summary of Results
复制标题
基于非确定性归一化的扫描统计（NN-scan）实现稳健的热点检测：结果总结
DOI：
10.1137/1.9781611975673.10
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Shekhar, Shashi.
中科院分区：
文献类型：
--
作者：
Xie, Yiqun;Shekhar, Shashi.
热点检测的目的是寻找空间中产生某些事件（如疾病、犯罪）的概率密度高于其他区域的子区域。热点搜索在公共卫生、犯罪分析、交通等领域都有重要的应用。现有的热点检测方法依赖于测试统计量（如似然比、密度），没有考虑空间不确定性，导致检测错误和缺失。我们对相关工作的局限性提供了理论见解，并提出了一个新的框架，即基于非确定性归一化的扫描统计量（NN-scan），以解决这些问题。我们还提出了一种动态线性近似（DILA）算法来提高神经网络扫描的效率。实验表明，神经网络扫描可以显著提高热点检测的精度和召回率，DILA可以大大降低计算成本。
Hotspot detection aims to find sub-regions of a space that have higher probability density of generating certain events (e.g., disease, crimes) than the other regions. Finding hotspots has important applications in many domains including public health, crime analysis, transportation, etc. Existing methods of hotspot detection rely on test statistics (e.g., likelihood ratio, density) that do not consider spatial nondeterminism, leading to false and missing detections. We provide theoretical insights into the limitations of related work, and propose a new framework, namely, Nondeterministic Normalization based scan statistic (NN-scan), to address the issues. We also propose a DynamIc Linear Approximation (DILA) algorithm to improve NN-scan's efficiency. In experiments, we show that NN-scan can significantly improve the precision and recall of hotspot detection and DILA can greatly reduce the computational cost.
影响因子：
7.2
作者：
Xun Tang;E. Eftelioglu;Dev Oliver;S. Shekhar
通讯作者：
Xun Tang;E. Eftelioglu;Dev Oliver;S. Shekhar