Scalable Pythagorean Mean based Incident Detection in Smart Transportation Systems

Scalable Pythagorean Mean based Incident Detection in Smart Transportation Systems
复制标题

智能交通系统中基于可扩展毕达哥拉斯均值的事件检测

DOI:
10.1145/3603381
复制
发表时间:
2023
影响因子:
2.3
通讯作者:
Das, Sajal K.
Das, Sajal K.
中科院分区:
--
文献类型:
--
作者:
Islam, Md. Jaminur;Talusan, Jose Paolo;Bhattacharjee, Shameek;Tiausas, Francis;Dubey, Abhishek;Yasumoto, Keiichi;Das, Sajal K.

文献摘要

参考文献

相似文献

现代智慧城市需要智能交通解决方案来快速检测城市中的各种交通紧急情况和事件,以避免连锁交通中断。为了实现这一目标,正在部署路边单元和环境交通传感器来收集速度数据,以便监测每个路段的交通状况。在这篇文章中,我们首先提出了一个可扩展的数据驱动的基于异常的交通事件检测框架的城市规模的智能交通系统。具体来说,我们提出了一种增量区域增长逼近算法,用于路段及其数据的最佳时空聚类;这样,路段就被战略性地划分为高度相关的集群。高度相关的聚类使得能够将基于毕达哥拉斯均值的不变量识别为异常检测度量,该异常检测度量在没有事件的情况下是高度稳定的,但在存在事件的情况下显示出偏差。我们学习的不变量的界限,在一个强大的方式,使异常检测可以推广到看不见的事件,即使从真实的噪声数据学习。其次,使用集群级检测,我们提出了一个折叠高斯分类器,以查明特定的片段在一个集群中的事件发生在一个自动化的方式。我们使用从田纳西州四个城市收集的移动数据进行了广泛的实验验证,并与最先进的ML方法进行了比较,以证明我们的方法可以实时检测每个集群中的事件,并优于已知的ML方法。
Modern smart cities need smart transportation solutions to quickly detect various traffic emergencies and incidents in the city to avoid cascading traffic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traffic conditions on each road segment. In this article, we first propose a scalable data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. Second, using cluster-level detection, we propose a folded Gaussian classifier to pinpoint the particular segment in a cluster where the incident happened in an automated manner. We perform extensive experimental validation using mobility data collected from four cities in Tennessee and compare with the state-of-the-art ML methods to prove that our method can detect incidents within each cluster in real-time and outperforms known ML methods.
DOI: 10.1145/3417337
发表时间: 2019-08
期刊: ACM Transactions on Knowledge Discovery from Data (TKDD)
影响因子: --
作者:
Yue Hu;D. Work
通讯作者: Yue Hu;D. Work
智能计量基础设施中的攻击上下文嵌入式数据驱动的信任诊断
DOI: --
发表时间: 2021
影响因子: 2.3
作者:
S. Bhattacharjee, P. Madhavarapu
通讯作者: S. Bhattacharjee, P. Madhavarapu
智能计量基础设施中隐形数据篡改的检测和取证
DOI: 10.1109/tdsc.2018.2889729
发表时间: 2019
影响因子: 7.3
作者:
Bhattacharjee, Shameek;Das, Sajal K.
通讯作者: Das, Sajal K.
实现对发起数据伪造攻击的智能电表的快速半监督识别
DOI: 10.1145/3196494.3196551
发表时间: 2018
期刊: Proceedings of the 2018 on Asia Conference on Computer and Communications Security
影响因子: --
作者:
Shameek Bhattacharjee;Aditya Thakur;Sajal K. Das
通讯作者: Sajal K. Das
DOI: 10.1177/1550147718815845
发表时间: 2018-11-29
影响因子: 2.3
作者:
Iqbal, Zafar;Khan, Majid Iqbal
通讯作者: Khan, Majid Iqbal