| アイテムタイプ |
学術雑誌論文 / Journal Article(1) |
| 公開日 |
2025-06-18 |
| タイトル |
|
|
タイトル |
Scalable Pythagorean Mean-based Incident Detection in Smart Transportation Systems |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Weakly unsupervised learning |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
anomaly detection |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
smart transportation |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
graph algorithms |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
cluster analysis |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
regression |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
incident detection |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
approximation algorithm |
| 資源タイプ |
|
|
資源タイプ |
journal article |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
Islam, Md. Jaminur
Talusan, Jose Paolo
Bhattacharjee, Shameek
Tiausas, Francis
Dubey, Abhishek
安本, 慶一
Das, Sajal K.
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
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. |
| 書誌情報 |
en : ACM Transactions on Cyber-Physical Systems
巻 8,
号 2,
発行日 2024-05-14
|
| 出版者 |
|
|
出版者 |
ACM |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
2378-9638 |
| 出版者版DOI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1145/3603381 |
| 出版者版URI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://dl.acm.org/doi/10.1145/3603381 |
| 権利 |
|
|
権利情報 |
$00A9 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM |
| 著者版フラグ |
|
|
出版タイプ |
NA |
| 助成情報 |
|
|
|
助成機関名 |
National Science Foundation(NSF) |
|
|
研究課題番号 |
SATC-203061 |
| 助成情報 |
|
|
|
助成機関名 |
National Science Foundation(NSF) |
|
|
研究課題番号 |
CNS-1818942 |
| 助成情報 |
|
|
|
助成機関名 |
National Science Foundation(NSF) |
|
|
研究課題番号 |
CNS-1818901 |
| 助成情報 |
|
|
|
助成機関名 |
National Science Foundation(NSF) |
|
|
研究課題番号 |
SATC-2030624 |
| 助成情報 |
|
|
|
助成機関名 |
National Science Foundation(NSF) |
|
|
研究課題番号 |
OAC-2017289 |
