TrafPS: A shapley-based visual analytics approach to interpret traffic

Feng, Zezheng1,2; Jiang, Yifan1; Wang, Hongjun1; Fan, Zipei4; Ma, Yuxin1; Yang, Shuang-Hua1,3,5; Qu, Huamin2; Song, Xuan1

2024-08-01

10.1007/s41095-023-0351-7

COMPUTATIONAL VISUAL MEDIA   影响因子和分区

2096-0433

2096-0662

Recent achievements in deep learning (DL) have demonstrated its potential in predicting traffic flows. Such predictions are beneficial for understanding the situation and making traffic control decisions. However, most state-of-the-art DL models are considered "black boxes" with little to no transparency of the underlying mechanisms for end users. Some previous studies attempted to "open the black box" and increase the interpretability of generated predictions. However, handling complex models on large-scale spatiotemporal data and discovering salient spatial and temporal patterns that significantly influence traffic flow remain challenging. To overcome these challenges, we present TrafPS, a visual analytics approach for interpreting traffic prediction outcomes to support decision-making in traffic management and urban planning. The measurements region SHAP and trajectory SHAP are proposed to quantify the impact of flow patterns on urban traffic at different levels. Based on the task requirements from domain experts, we employed an interactive visual interface for the multi-aspect exploration and analysis of significant flow patterns. Two real-world case studies demonstrate the effectiveness of TrafPS in identifying key routes and providing decision-making support for urban planning.

data visualization model interpretation urban planning urban visual analytics

SCI ; EI

英语

第一 ; 通讯

Japan Society for the Promotion of Science (JSPS)[22H03573] ; National Natural Science Foundation of China["92067109","61873119"] ; Shenzhen Science and Technology Program["ZDSYS20210623092007023","GJHZ20210705141808024"] ; Guangdong Key Program[2021QN02X794]

Computer Science

Computer Science, Software Engineering

WOS:001303885200001

TSINGHUA UNIV PRESS

Web of Science

1.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen 18055, Peoples R China
2.Hong Kong Univ Sci & Technol, Dept Comp Sci & Engn, Hong Kong, Peoples R China
3.Univ Reading, Dept Comp Sci, Berkshire RG6 6AH, England
4.Univ Tokyo, Ctr Spatial Informat Sci, Tokyo 11300331, Japan
5.Southern Univ Sci & Technol, Shenzhen Key Lab Safety & Secur Next Generat Ind I, Shenzhen 518055, Peoples R China

Feng, Zezheng,Jiang, Yifan,Wang, Hongjun,et al. TrafPS: A shapley-based visual analytics approach to interpret traffic[J]. COMPUTATIONAL VISUAL MEDIA,2024.

Feng, Zezheng.,Jiang, Yifan.,Wang, Hongjun.,Fan, Zipei.,Ma, Yuxin.,...&Song, Xuan.(2024).TrafPS: A shapley-based visual analytics approach to interpret traffic.COMPUTATIONAL VISUAL MEDIA.

Feng, Zezheng,et al."TrafPS: A shapley-based visual analytics approach to interpret traffic".COMPUTATIONAL VISUAL MEDIA (2024).