A Visual Analytics System for Exploring, Monitoring, and Forecasting Road Traffic Congestion

被引：71

作者：

Lee, Chunggi ^{[1
]}

Kim, Yeonjun ^{[1
]}

Jin, Seungmin ^{[1
]}

Kim, Dongmin ^{[1
]}

Maciejewski, Ross ^{[2
]}

Ebert, David ^{[3
]}

Ko, Sungahn ^{[1
]}

机构：

[1] UNIST, Ulsan, South Korea

[2] Arizona State Univ, Sch Comp Informat & Decis Syst Engn, Tempe, AZ 85287 USA

[3] Purdue Univ, Elect & Comp Wngineering, W Lafayette, IN 47907 USA

来源：

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS | 2020年 / 26卷 / 11期

基金：

新加坡国家研究基金会;

关键词：

Roads; Forecasting; Data visualization; Surveillance; Task analysis; Urban areas; Traffic; road; congestion; visualization; deep learning; LSTM; surveillance; forecasting; predictive analysis; EXPLORATION; MOBILITY; NETWORKS;

D O I：

10.1109/TVCG.2019.2922597

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

We present an interactive visual analytics system that enables traffic congestion exploration, surveillance, and forecasting based on vehicle detector data. Through domain expert collaboration, we have extracted task requirements, incorporated the Long Short-Term Memory (LSTM) model for congestion forecasting, and designed a weighting method for detecting the causes of congestion and congestion propagation directions. Our visual analytics system is designed to enable users to explore congestion causes, directions, and severity. Congestion conditions of a city are visualized using a Volume-Speed Rivers (VSRivers) visualization that simultaneously presents traffic volumes and speeds. To evaluate our system, we report performance comparison results, wherein our model is more accurate than other forecasting algorithms. We demonstrate the usefulness of our system in the traffic management and congestion broadcasting domains through three case studies and domain expert feedback.

引用

页码：3133 / 3146

页数：14

共 62 条

[1] Visual Analytics of Mobility and Transportation: State of the Art and Further Research Directions [J].