Zhiyuan Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhiyuan Sun has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
Huapu Lu
Institute of Transportation Engineering and Geomatics, Tsinghua University
5 shared publications- Jianyu Wang
Beijing Laboratory of General Aviation Technology, Beijing University of Civil Engineering and Architecture, Beijing 100044, China
5 shared publications - Huapu Lu
Institute of Transportation Engineering and Geomatics, Tsinghua University, Beijing 100084, China
4 shared publications Jianyu Wang
Beijing Key Laboratory of General Aviation Technology, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
2 shared publications- Tianshi Wang
Institute of Transportation Engineering and Geomatics, Tsinghua University, Beijing 100084, China
2 shared publications - Wencong Qu
Road Transport Books Center, China Communications Press Co., Ltd., Beijing 100011, China
2 shared publications
Latest Publications
- Top Cited Papers
- 30 August 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 222, 108220
Temporal heterogeneity in traffic crash delays: causal inference from multi-scale time factors and sample-wise structural decomposition
- 30 August 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 222, 108220
Top Cited PapersTemporal heterogeneity in traffic crash delays: causal inference from multi-scale time factors and sample-wise structural decomposition
- 1 July 2024
- Published by Taylor & Francis in International Journal of Crashworthiness
- Vol. 30 (1) , 80-94
Investigating the spatial heterogeneity of drunk-driving events in Beijing based on a hybrid method with LISA and GeoDetector
- 1 July 2024
- Published by Taylor & Francis in International Journal of Crashworthiness
- Vol. 30 (1) , 80-94
Investigating the spatial heterogeneity of drunk-driving events in Beijing based on a hybrid method with LISA and GeoDetector
- 6 February 2023
- Published by World Scientific Pub Co Pte Ltd in Modern Physics Letters B
- Vol. 37 (06)
Driving behavior of connected autonomous vehicles in mixed traffic flow within ramp segments on freeway based on an advanced cellular automata
Connected autonomous vehicles (CAV) are currently under development, and the mixed flow with CAV would make the traffic states more complicated. Due to the lack of mature applications, the future traffic with CAV are still full of uncertainties. Under the new situation, the traditional cellular automata (CA) model is in need of upgrade. To discover the characteristics of traffic flow under different CAV penetration rates, and considering the particularity of the ramp segments on freeway, this paper updates the current CA model and analyzes the car-following and lane-changing behavior of mixed traffic flow under the intelligent network. Results show that, as the CAV penetration rate continues to increase, the road operation performance continues to improve, and the capacity of the road segment increases accordingly.
- 6 February 2023
- Published by World Scientific Pub Co Pte Ltd in Modern Physics Letters B
- Vol. 37 (06)
Driving behavior of connected autonomous vehicles in mixed traffic flow within ramp segments on freeway based on an advanced cellular automata
Connected autonomous vehicles (CAV) are currently under development, and the mixed flow with CAV would make the traffic states more complicated. Due to the lack of mature applications, the future traffic with CAV are still full of uncertainties. Under the new situation, the traditional cellular automata (CA) model is in need of upgrade. To discover the characteristics of traffic flow under different CAV penetration rates, and considering the particularity of the ramp segments on freeway, this paper updates the current CA model and analyzes the car-following and lane-changing behavior of mixed traffic flow under the intelligent network. Results show that, as the CAV penetration rate continues to increase, the road operation performance continues to improve, and the capacity of the road segment increases accordingly.
- 30 January 2023
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 613
Towards higher efficiency and less consumption: Control Strategy and Simulation for CAV platooning
- 30 January 2023
- Published by Elsevier in Physica A: Statistical Mechanics and its Applications
- Vol. 613
Towards higher efficiency and less consumption: Control Strategy and Simulation for CAV platooning
- Open Access
- 28 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 79051-79059
Trip Generation Prediction Based on the Convolutional Neural Network-Multidimensional Long-Short Term Memory Neural Network Model at Grid Cell Scale
The prediction of trip generation is an essential problem for effective traffic engineering and urban management. Traditional methods are on the large spatial scale (e.g. Traffic analysis Zone, TAZ), based on the single source and fewer types data. It is difficult to carry out refined research on smaller spatial units, due to the high aggregation of personal trip survey data. In addition, the experience-based models cannot easily capture complex non-linear relationship, which leads to lower accuracy. Multi-sources data provides the possibility to improve the prediction accuracy of trip generation. Based on the point of interest data (POI), more disaggregate spatial unit are subdivided, and grid-scale spatial correlations are taken into consideration. This paper proposes a Convolutional Neural Network-Multidimensional Long-short term memory neural network (CNN-MDLSTM) model to analyze the spatial correlation between trip generation and land use features, capture prominent features in a spatial range through the convolution structure and describe the spatial interaction using the sequence transfer structure of Long-short term memory neural network (LSTM). The deformed Multi-Dimensional Long-Short Term Memory neural network (MDLSTM) is used to adapt to the two-dimensional spatial relationship. Through case analysis and comparative analysis between models, it is shown that CNN-MDLSTM characterizes the quantitative law of trip generation and land use features better than the other neural network models. In addition, this study also discusses the output prediction accuracy of different land use grid cells and the impact of different land use characteristics on the prediction accuracy.
- 28 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 79051-79059
Open AccessTrip Generation Prediction Based on the Convolutional Neural Network-Multidimensional Long-Short Term Memory Neural Network Model at Grid Cell Scale
The prediction of trip generation is an essential problem for effective traffic engineering and urban management. Traditional methods are on the large spatial scale (e.g. Traffic analysis Zone, TAZ), based on the single source and fewer types data. It is difficult to carry out refined research on smaller spatial units, due to the high aggregation of personal trip survey data. In addition, the experience-based models cannot easily capture complex non-linear relationship, which leads to lower accuracy. Multi-sources data provides the possibility to improve the prediction accuracy of trip generation. Based on the point of interest data (POI), more disaggregate spatial unit are subdivided, and grid-scale spatial correlations are taken into consideration. This paper proposes a Convolutional Neural Network-Multidimensional Long-short term memory neural network (CNN-MDLSTM) model to analyze the spatial correlation between trip generation and land use features, capture prominent features in a spatial range through the convolution structure and describe the spatial interaction using the sequence transfer structure of Long-short term memory neural network (LSTM). The deformed Multi-Dimensional Long-Short Term Memory neural network (MDLSTM) is used to adapt to the two-dimensional spatial relationship. Through case analysis and comparative analysis between models, it is shown that CNN-MDLSTM characterizes the quantitative law of trip generation and land use features better than the other neural network models. In addition, this study also discusses the output prediction accuracy of different land use grid cells and the impact of different land use characteristics on the prediction accuracy.
- Open Access
- 12 February 2020
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 17 (4) , 1146
Exploring Factors Influencing Injury Severity of Vehicle At-Fault Accidents: A Comparative Analysis of Passenger and Freight Vehicles
The objective of this study is to find factors influencing the injury severity of vehicle at-fault accidents in Shenyang (China), and discuss the commonalities and differences between passenger and freight vehicle accidents. We analyzed 1647 traffic accidents from 2015 to 2017, in which motor vehicles were fully or mainly responsible, including 1164 traffic accidents caused by passenger vehicles and 483 traffic accidents caused by freight vehicles. Twenty influencing factors from the aspects of accident, driver, time, space and environmental attributes are analyzed to find their statistical connection with injury severity using the binary logistic regression model. For passenger vehicles, five influencing factors (side collision; illegal act while driving; hit-and-run; season and administrative division), showed statistically significant correlations with the injury severity. For freight vehicles, three influencing factors (illegal act while driving; season and administrative division), showed statistically significant correlations with the injury severity. Illegal act while driving is the only common influencing factor for the injury severity of both passenger and freight vehicle accidents. Side collision and hit-and-run are significant influencing factors for the injury severity of passenger vehicle accidents, but not for freight vehicle accidents. Season and administrative division present different results on influencing passenger and freight vehicle accidents. Based on these results, measures including driver education and road infrastructure improvement could be implemented to reduce the injury severity of accidents in passenger and freight vehicles.
- 12 February 2020
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 17 (4) , 1146
Open AccessExploring Factors Influencing Injury Severity of Vehicle At-Fault Accidents: A Comparative Analysis of Passenger and Freight Vehicles
The objective of this study is to find factors influencing the injury severity of vehicle at-fault accidents in Shenyang (China), and discuss the commonalities and differences between passenger and freight vehicle accidents. We analyzed 1647 traffic accidents from 2015 to 2017, in which motor vehicles were fully or mainly responsible, including 1164 traffic accidents caused by passenger vehicles and 483 traffic accidents caused by freight vehicles. Twenty influencing factors from the aspects of accident, driver, time, space and environmental attributes are analyzed to find their statistical connection with injury severity using the binary logistic regression model. For passenger vehicles, five influencing factors (side collision; illegal act while driving; hit-and-run; season and administrative division), showed statistically significant correlations with the injury severity. For freight vehicles, three influencing factors (illegal act while driving; season and administrative division), showed statistically significant correlations with the injury severity. Illegal act while driving is the only common influencing factor for the injury severity of both passenger and freight vehicle accidents. Side collision and hit-and-run are significant influencing factors for the injury severity of passenger vehicle accidents, but not for freight vehicle accidents. Season and administrative division present different results on influencing passenger and freight vehicle accidents. Based on these results, measures including driver education and road infrastructure improvement could be implemented to reduce the injury severity of accidents in passenger and freight vehicles.
- Open Access
- 3 December 2018
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 15 (12) , 2722
Influence Factors on Injury Severity of Traffic Accidents and Differences in Urban Functional Zones: The Empirical Analysis of Beijing
The objective of this study was to identify influence factors on injury severity of traffic accidents and discuss the differences in urban functional zones in Beijing. A total of 3982 sets of accident data in Beijing were analyzed from the perspective of whole city and different urban functional zones. From the aspects of accident attribute, occurrence time, infrastructure, management status, and environmental condition, the influence factors set of injury severity of traffic accidents in Beijing are set up in this paper, which include 17 influence factors. Based on Pearson’s chi-squared test, factors are preselected. On the basis of binary logistic regression analysis, the impact of the value of influence factors on injury severity of traffic accidents is calibrated. Based on classification and regression tree analysis, the impact of influence factors is analyzed. Through Pearson’s chi-squared test and binary logistic regression analysis, it is found that there are similarities and differences among different urban functional zones. There are two common influence factors, including accident type and cross-section position, and six personalized influence factors, including lighting conditions, visibility, signal control, road physical isolation facility, occurrence period and road type, and the other nine weak influence factors. The results of binary logistic regression analysis and classification and regression tree analysis are basically the same. The factors that should be paid attention to in different urban functional zones and the value of the factors that need special attention are determined by synthesizing two methods.
- 3 December 2018
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 15 (12) , 2722
Open AccessInfluence Factors on Injury Severity of Traffic Accidents and Differences in Urban Functional Zones: The Empirical Analysis of Beijing
The objective of this study was to identify influence factors on injury severity of traffic accidents and discuss the differences in urban functional zones in Beijing. A total of 3982 sets of accident data in Beijing were analyzed from the perspective of whole city and different urban functional zones. From the aspects of accident attribute, occurrence time, infrastructure, management status, and environmental condition, the influence factors set of injury severity of traffic accidents in Beijing are set up in this paper, which include 17 influence factors. Based on Pearson’s chi-squared test, factors are preselected. On the basis of binary logistic regression analysis, the impact of the value of influence factors on injury severity of traffic accidents is calibrated. Based on classification and regression tree analysis, the impact of influence factors is analyzed. Through Pearson’s chi-squared test and binary logistic regression analysis, it is found that there are similarities and differences among different urban functional zones. There are two common influence factors, including accident type and cross-section position, and six personalized influence factors, including lighting conditions, visibility, signal control, road physical isolation facility, occurrence period and road type, and the other nine weak influence factors. The results of binary logistic regression analysis and classification and regression tree analysis are basically the same. The factors that should be paid attention to in different urban functional zones and the value of the factors that need special attention are determined by synthesizing two methods.
- Open Access
- 1 January 2018
- Published by Wiley in Complexity
- Vol. 2018 (1)
Unified Framework for Optimal Routing Choice under Guidance Information
In order to satisfy the diverse demand of travel service in the context of big data, this paper puts forward a unified framework for optimal routing choice under guidance information. With consideration of the influence of big data, the scenario analysis of routing choice is implemented, and the routing choice under guidance information is discussed. The optimal routing choice problem is abstracted into the collaboration optimization model of travel route choice, departure time choice, and travel mode choice. Based on some basic assumptions, the collaboration optimization model is formulated as a variational inequality model. The method of successive averages is applied to solve the proposed model. A case study is carried out to verify the applicability and reliability of the model and algorithm.
- 1 January 2018
- Published by Wiley in Complexity
- Vol. 2018 (1)
Open AccessUnified Framework for Optimal Routing Choice under Guidance Information
In order to satisfy the diverse demand of travel service in the context of big data, this paper puts forward a unified framework for optimal routing choice under guidance information. With consideration of the influence of big data, the scenario analysis of routing choice is implemented, and the routing choice under guidance information is discussed. The optimal routing choice problem is abstracted into the collaboration optimization model of travel route choice, departure time choice, and travel mode choice. Based on some basic assumptions, the collaboration optimization model is formulated as a variational inequality model. The method of successive averages is applied to solve the proposed model. A case study is carried out to verify the applicability and reliability of the model and algorithm.
- Open Access
- 2 July 2017
- Published by MDPI AG in Sustainability
- Vol. 9 (7) , 1148
Human-Scale Sustainability Assessment of Urban Intersections Based upon Multi-Source Big Data
To evaluate the sustainability of an enormous number of urban intersections, a novel assessment model is proposed, along with an indicator system and corresponding methods to determine the indicators. Considering mainly the demands and feelings of the urban residents, the three aspects of safety, functionality, and image perception are taken into account in the indicator system. Based on technologies such as street view picture crawling, image segmentation, and edge detection, GIS spatial data analysis, a rapid automated assessment method, and a corresponding multi-source database are built up to determine the indicators. The improved information entropy method is applied to obtain the entropy weights of each indicator. A case study shows the efficiency and applicability of the proposed assessment model, indicator system and algorithm.
- 2 July 2017
- Published by MDPI AG in Sustainability
- Vol. 9 (7) , 1148
Open AccessHuman-Scale Sustainability Assessment of Urban Intersections Based upon Multi-Source Big Data
To evaluate the sustainability of an enormous number of urban intersections, a novel assessment model is proposed, along with an indicator system and corresponding methods to determine the indicators. Considering mainly the demands and feelings of the urban residents, the three aspects of safety, functionality, and image perception are taken into account in the indicator system. Based on technologies such as street view picture crawling, image segmentation, and edge detection, GIS spatial data analysis, a rapid automated assessment method, and a corresponding multi-source database are built up to determine the indicators. The improved information entropy method is applied to obtain the entropy weights of each indicator. A case study shows the efficiency and applicability of the proposed assessment model, indicator system and algorithm.