research-article

DF-TAR: A Deep Fusion Network for Citywide Traffic Accident Risk Prediction with Dangerous Driving Behavior

Authors:

Jae-Gil LeeAuthors Info & Claims

WWW '21: Proceedings of the Web Conference 2021

Pages 1146 - 1156

https://doi.org/10.1145/3442381.3450003

Published: 03 June 2021 Publication History

Abstract

Because traffic accidents cause huge social and economic losses, it is of prime importance to precisely predict the traffic accident risk for reducing future accidents. In this paper, we propose a Deep Fusion network for citywide Traffic Accident Risk prediction (DF-TAR) with dangerous driving statistics that contain the frequencies of various dangerous driving offences in each region. Our unique contribution is to exploit these statistics, obtained by processing the data from in-vehicle sensors, for modeling the traffic accident risk. Toward this goal, we first examine the correlation between dangerous driving offences and traffic accidents, and the analysis shows a strong correlation between them in terms of both location and time. Specifically, quick start (0.83), rapid acceleration (0.76), and sharp turn (0.76) are the top three offences that have the highest average correlation scores. We then train the DF-TAR model using the dangerous driving statistics as well as external environmental features. By extensive experiments on various frameworks, the DF-TAR model is shown to improve the accuracy of the baseline models by up to 54% by virtue of the integration of dangerous driving into the modeling of traffic accident risk.

References

[1]

Korean National Police Agency. 2014. Traffic Safety Act of the Republic of Korea. Chapter Article 55 (Equipment with An Operation Recording Device and Utilization of the Operation Recording, etc.).

[2]

IM Almeida, Regina Célia P Leal-Toledo, Elson Magalhães Toledo, Diego Carrico Cacau, and GVP Magalhães. 2018. Drivers’ Behavior Effects in the Occurrence of Dangerous Situations Which May Lead to Accidents. In Proceedings of the 13th International Conference on Cellular Automata. 441–450.

[3]

Korea Transportation Safety Authority. 2015. Dangerous Driving Behavior Criteria. https://etas.ts2020.kr/etas/frtl0401/pop/goList.do

[4]

Gianmarco Baldini, Luigi Sportiello, Michel Chiaramello, and Vincent Mahieu. 2018. Regulated Applications for the Road Transportation Infrastructure: The Case Study of the Smart Tachograph in the European Union. International Journal of Critical Infrastructure Protection 21 (2018), 3–21.

[5]

Jie Bao, Pan Liu, and Satish V Ukkusuri. 2019. A Spatiotemporal Deep Learning Approach for Citywide Short-term Crash Risk Prediction with Multi-source Data. Accident Analysis & Prevention 122 (2019), 239–254.

[6]

Ruth Bergel-Hayat, Mohammed Debbarh, Constantinos Antoniou, and George Yannis. 2013. Explaining the Road Accident Risk: Weather Effects. Accident Analysis & Prevention 60 (2013), 456–465.

[7]

Michal Bíl, Richard Andrášik, and Zbyněk Janoška. 2013. Identification of Hazardous Road Locations of Traffic Accidents by Means of Kernel Density Estimation and Cluster Significance Evaluation. Accident Analysis & Prevention 55 (2013), 265–273.

[8]

Ciro Caliendo, Maurizio Guida, and Alessandra Parisi. 2007. A Crash-Prediction Model for Multilane Roads. Accident Analysis & Prevention 39, 4 (2007), 657–670.

[9]

Li-Yen Chang and Wen-Chieh Chen. 2005. Data Mining of Tree-based Models to Analyze Freeway Accident Frequency. Journal of Safety Research 36, 4 (2005), 365–375.

[10]

Chao Chen, Xiaoliang Fan, Chuanpan Zheng, Lujing Xiao, Ming Cheng, and Cheng Wang. 2018. SDCAE: Stack Denoising Convolutional Autoencoder Model for Accident Risk Prediction via Traffic Big Data. In Proceedings of the 6th International Conference on Advanced Cloud and Big Data. 328–333.

[11]

Quanjun Chen, Xuan Song, Zipei Fan, Tianqi Xia, Harutoshi Yamada, and Ryosuke Shibasaki. 2018. A Context-Aware Nonnegative Matrix Factorization Framework for Traffic Accident Risk Estimation via Heterogeneous Data. In Proceedings of the 2018 IEEE Conference on Multimedia Information Processing and Retrieval. 346–351.

[12]

Quanjun Chen, Xuan Song, Harutoshi Yamada, and Ryosuke Shibasaki. 2016. Learning Deep Representation from Big and Heterogeneous Data for Traffic Accident Inference. In Proceedings of the 30th AAAI Conference on Artificial Intelligence. 338–344.

[13]

Jongseok Cho, Hyunsuk Lee, Jaeyoung Lee, and Ducknyung Kim. 2017. The Hazardous Expressway Sections for Drowsy Driving Using Digital Tachograph in Truck. Journal of Korean Society of Transportation 35, 2 (2017), 160–168.

[14]

Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv preprint arXiv:1412.3555(2014).

[15]

Mark D Dunlop, Marc Roper, Mark Elliot, Rebecca McCartan, and Bruce McGregor. 2016. Using Smartphones in Cities to Crowdsource Dangerous Road Sections and Give Effective In-car Warnings. In Proceedings of the 2016 on Smart Cities for Better Living with HCI and UX. 14–18.

Digital Library

[16]

Gokhan Egilmez and Deborah McAvoy. 2017. Predicting Nationwide Road Fatalities in the US: A Neural Network Approach. International Journal of Metaheuristics 6, 4 (2017), 257–278.

Digital Library

[17]

Daniel Eisenberg. 2004. TheThe Mixed Effects of Precipitation on Traffic Crashes. Accident Analysis & Prevention 36, 4 (2004), 637–647.

[18]

Veronika Harantová, Simona Kubíková, and Luboš Rumanovskỳ. 2019. Traffic Accident Occurrence, Its Prediction and Causes. In Proceedings of the 19th International Conference on Transport Systems Telematics. 123–136.

[19]

Chao Huang, Chuxu Zhang, Peng Dai, and Liefeng Bo. 2019. Deep Dynamic Fusion Network for Traffic Accident Forecasting. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 2673–2681.

Digital Library

[20]

Joon-Gyu Kang, Yoo-Won Kim, and Moon-Seog Jun. 2015. Real-time Dangerous Driving Behavior Analysis Utilizing the Digital Tachograph and Smartphone. Journal of the Korea Society of Computer and Information 20, 12(2015), 37–44.

[21]

Do-Gyeong Kim, Chungwon Lee, and Byung-Jung Park. 2016. Use of Digital Tachograph Data to Provide Traffic Safety Education and Evaluate Effects on Bus Driver Behavior. Transportation Research Record 2585, 1 (2016), 77–84.

[22]

Korea Road Traffic Authority. 2020. What Causes Traffic Accidents?https://www.koroad.or.kr/en_web/view/trfEnv4.do

[23]

Lei Lin, Qian Wang, and Adel W Sadek. 2015. A Novel Variable Selection Method based on Frequent Pattern Tree for Real-time Traffic Accident Risk Prediction. Transportation Research Part C: Emerging Technologies 55 (2015), 444–459.

[24]

Yisheng Lv, Shuming Tang, and Hongxia Zhao. 2009. Real-Time Highway Traffic Accident Prediction Based on the k-Nearest Neighbor Method. In Proceedings of the 2009 International Conference on Measuring Technology and Mechatronics Automation, Vol. 3. 547–550.

Digital Library

[25]

Jason Metz. 2018. Your Car’s OBD-II: What Is It?EverQuote, Inc. https://www.everquote.com/blog/car-insurance/your-car-obd/

[26]

Ali Moradi, Hamid Soori, Amir Kavousi, Farshid Eshghabadi, Ensiyeh Jamshidi, and Salahdien Zeini. 2016. Spatial Analysis to Identify High Risk Areas for Traffic Crashes Resulting in Death of Pedestrians in Tehran. Medical Journal of the Islamic Republic of Iran 30 (2016), 450.

[27]

Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. 2016. WaveNet: A Generative Model for Raw Audio. arXiv preprint arXiv:1609.03499(2016).

[28]

World Health Organization. 2015. Global Status Report on Road Safety 2015.

[29]

Geun Young Park. 2014. What If You Could Give a Driver with a Good Driving Habit a Discount on His Car Insurance?Korea Road Traffic Authority. https://www.koroad.or.kr/kp_web/krPrView.do?board_code=GABBS_050&board_num=126843

[30]

Seong-hun Park, Sung-min Kim, and Young-guk Ha. 2016. Highway Traffic Accident Prediction Using VDS Big Data Analysis. The Journal of Supercomputing 72, 7 (2016), 2815–2831.

Digital Library

[31]

Sang Young Park. 2020. Automatically Record Business Vehicles of Speeding, Sudden Stop, and Reckless Driving through Smartphones.The Kyunghyang Shinmun. http://news.khan.co.kr/kh_news/khan_art_view.html?art_id=202003302130005

[32]

Honglei Ren, You Song, Jingwen Wang, Yucheng Hu, and Jinzhi Lei. 2018. A Deep Learning Approach to the Citywide Traffic Accident Risk Prediction. In Proceedings of the 21st International Conference on Intelligent Transportation Systems. 3346–3351.

Digital Library

[33]

Aliasghar Sadeghi, Esmaeel Ayati, and Mohammadali Pirayesh Neghab. 2013. Identification and Prioritization of Hazardous Road Locations by Segmentation and Data Envelopment Analysis Approach. PROMET-Traffic&Transportation 25, 2 (2013), 127–136.

[34]

Tara N Sainath, Oriol Vinyals, Andrew Senior, and Haşim Sak. 2015. Convolutional, Long Short-Term Memory, Fully Connected Deep Neural Networks. In Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing. 4580–4584.

[35]

John M Scanlon, Rini Sherony, and Hampton C Gabler. 2017. Models of Driver Acceleration Behavior Prior to Real-World Intersection Crashes. IEEE Transactions on Intelligent Transportation Systems 19, 3(2017), 774–786.

[36]

Paul Stenquist. 2020. Letting Your Insurer Ride Shotgun, for a Discounted Rate. The New York Times Company. https://www.nytimes.com/2020/07/16/business/car-insurance-app-discounts.html

[37]

JD Tamerius, X Zhou, R Mantilla, and T Greenfield-Huitt. 2016. Precipitation Effects on Motor Vehicle Crashes Vary by Space, Time, and Environmental Conditions. Weather, Climate, and Society 8, 4 (2016), 399–407.

[38]

Cherise Threewitt and John M Vincent. 2018. How Do Those Car Insurance Tracking Devices Work?US News & World Report. https://cars.usnews.com/cars-trucks/car-insurance/how-do-those-car-insurance-tracking-devices-work

[39]

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. arXiv preprint arXiv:1706.03762(2017).

[40]

Zhixiao Xie and Jun Yan. 2013. Detecting Traffic Accident Clusters with Network Kernel Density Estimation and Local Spatial Statistics: An Integrated Approach. Journal of Transport Geography 31 (2013), 64–71.

[41]

Zhuoning Yuan, Xun Zhou, and Tianbao Yang. 2018. Hetero-ConvLSTM: A Deep Learning Approach to Traffic Accident Prediction on Heterogeneous Spatio-Temporal Data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 984–992.

Digital Library

[42]

Cuiping Zhang, Xuedong Yan, Lu Ma, and Meiwu An. 2014. Crash Prediction and Risk Evaluation Based on Traffic Analysis Zones. Mathematical Problems in Engineering(2014).

[43]

Zhengyang Zhou, Yang Wang, Xike Xie, Lianliang Chen, and Hengchang Liu. 2020. RiskOracle: A Minute-Level Citywide Traffic Accident Forecasting Framework. In Proceedings of the 34th AAAI Conference on Artificial Intelligence. 1258–1265.

[44]

Lei Zhu, Tianrui Li, and Shengdong Du. 2019. TA-STAN: A Deep Spatial-Temporal Attention Learning Framework for Regional Traffic Accident Risk Prediction. In Proceedings of the 2019 International Joint Conference on Neural Networks. 1–8.

Cited By

Arciniegas-Ayala CMarcillo PValdivieso Caraguay ÁHernández-Álvarez M(2024)Prediction of Accident Risk Levels in Traffic Accidents Using Deep Learning and Radial Basis Function Neural Networks Applied to a Dataset with Information on Driving EventsApplied Sciences10.3390/app1414624814:14(6248)Online publication date: 18-Jul-2024
https://doi.org/10.3390/app14146248
Hu JLiu XFan ZLiang YZimmermann R(2024)Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal Graph LearningProceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems10.1145/3678717.3691235(135-146)Online publication date: 29-Oct-2024
https://dl.acm.org/doi/10.1145/3678717.3691235
Bhardwaj NPal ABhumika Das D(2024)Adaptive Context Based Road Accident Risk Prediction Using Spatio-Temporal Deep LearningIEEE Transactions on Artificial Intelligence10.1109/TAI.2023.33285785:6(2872-2883)Online publication date: Jun-2024
https://doi.org/10.1109/TAI.2023.3328578
Show More Cited By

Recommendations

A Deep Learning Approach to the Citywide Traffic Accident Risk Prediction
2018 21st International Conference on Intelligent Transportation Systems (ITSC)
With the rapid development of urbanization, the boom of vehicle numbers has resulted in serious traffic accidents, which led to casualties and huge economic losses. The ability to predict the risk of traffic accident is important in the prevention of the ...
Performance Evaluation of Citywide Intersections Traffic Control Algorithm inVANETs-Based
Internet of Vehicles. Technologies and Services Toward Smart Cities
Abstract
The massive improvement in wireless communications pertains a real time and accurate delivery of information, which makes it possible to remotely control and manage a wide number of applications and services. The ability to connect to mobile and ...
Urban traffic accident risk prediction for knowledge-based mobile multimedia service
Abstract
Traditional accident prediction models have been mostly designed with statistical analysis that finds and analyzes the causal relationships between traffic accidents and a variety of human, road geometry, and environmental factors. However, these ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

WWW '21: Proceedings of the Web Conference 2021

April 2021

4054 pages

ISBN:9781450383127

DOI:10.1145/3442381

Editors:
Jure Leskovec
Stanford
,
Marko Grobelnik
Jožef Stefan Institute
,
Marc Najork
Google
,
Jie Tang
Tsinghua University
,
Leila Zia
Wikimedia Foundation

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGWEB: ACM Special Interest Group on Hypertext, Hypermedia, and Web

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 03 June 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

WWW '21

Sponsor:

SIGWEB

WWW '21: The Web Conference 2021

April 19 - 23, 2021

Ljubljana, Slovenia

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
688
Total Downloads

Downloads (Last 12 months)89
Downloads (Last 6 weeks)5

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Arciniegas-Ayala CMarcillo PValdivieso Caraguay ÁHernández-Álvarez M(2024)Prediction of Accident Risk Levels in Traffic Accidents Using Deep Learning and Radial Basis Function Neural Networks Applied to a Dataset with Information on Driving EventsApplied Sciences10.3390/app1414624814:14(6248)Online publication date: 18-Jul-2024
https://doi.org/10.3390/app14146248
Hu JLiu XFan ZLiang YZimmermann R(2024)Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal Graph LearningProceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems10.1145/3678717.3691235(135-146)Online publication date: 29-Oct-2024
https://dl.acm.org/doi/10.1145/3678717.3691235
Bhardwaj NPal ABhumika Das D(2024)Adaptive Context Based Road Accident Risk Prediction Using Spatio-Temporal Deep LearningIEEE Transactions on Artificial Intelligence10.1109/TAI.2023.33285785:6(2872-2883)Online publication date: Jun-2024
https://doi.org/10.1109/TAI.2023.3328578
Kurucan M(2024)Traffic Management System With Symbolic Discrete Controller Synthesis TechniqueIEEE Access10.1109/ACCESS.2024.343571312(105393-105402)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3435713
Pei YHou L(2024)Safety Assessment and Risk Management of Urban Arterial Traffic Flow Based on Artificial Driving and Intelligent Network Connection: An OverviewArchives of Computational Methods in Engineering10.1007/s11831-023-10062-731:5(2925-2943)Online publication date: 23-Jan-2024
https://doi.org/10.1007/s11831-023-10062-7
Du WDash ALi JWei HWang G(2023)Safety in Traffic Management Systems: A Comprehensive SurveyDesigns10.3390/designs70401007:4(100)Online publication date: 10-Aug-2023
https://doi.org/10.3390/designs7040100
Yang GZhang YHang JFeng XXie ZZhang DYang YFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)CARPG: Cross-City Knowledge Transfer for Traffic Accident Prediction via Attentive Region-Level Parameter GenerationProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614802(2939-2948)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3614802
Trirat PYoon SLee J(2023)MG-TAR: Multi-View Graph Convolutional Networks for Traffic Accident Risk PredictionIEEE Transactions on Intelligent Transportation Systems10.1109/TITS.2023.323707224:4(3779-3794)Online publication date: 1-Apr-2023
https://dl.acm.org/doi/10.1109/TITS.2023.3237072
Stephen Neal Joshua ETirupati Rao NBhattacharyya DJoys N(2023)Criminal Tendency Identification Using Deep Learning Approaches: A Novel Approach for Security ProtectionMachine Intelligence Techniques for Data Analysis and Signal Processing10.1007/978-981-99-0085-5_21(249-258)Online publication date: 31-May-2023
https://doi.org/10.1007/978-981-99-0085-5_21
Zogan HRazzak IWang XJameel SXu G(2022)Explainable depression detection with multi-aspect features using a hybrid deep learning model on social mediaWorld Wide Web10.1007/s11280-021-00992-225:1(281-304)Online publication date: 1-Jan-2022
https://dl.acm.org/doi/10.1007/s11280-021-00992-2

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents