Lai Zheng
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
Lai Zheng has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Tarek Sayed
Univ. of British Columbia
5 shared publications - Yanyong Guo
Southeast University
5 shared publications - Wei Wei
School of Transportation Science and Engineering, Harbin Institute of Technology, Nangang, Harbin, China
4 shared publications Xianghai Meng
Harbin Institute of Technology
4 shared publications- Hao Lyu
School of Transportation, Southeast University, Nanjing 211189, China; Jiangsu Key Laboratory of Urban ITS, Jiangsu Collaborative Innovation Center of Modern Urban Traffic Technologies, China
3 shared publications - Pan Liu
Southeast University
3 shared publications
Latest Publications
- 18 June 2026
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 235, 108627
A safety field-based surrogate measure for quantifying bikelane conflict risk considering physical and behavioral dynamics
- 18 June 2026
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 235, 108627
A safety field-based surrogate measure for quantifying bikelane conflict risk considering physical and behavioral dynamics
- 17 June 2026
- Published by Springer Nature
- p. 352-365
Developing Traffic Conflict-Based Safety Performance Functions for Urban Intersections
- 17 June 2026
- Published by Springer Nature
- p. 352-365
Developing Traffic Conflict-Based Safety Performance Functions for Urban Intersections
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4811-4823
Model-Agnostic Meta-Learning-Based Real-Time Traffic Conflict Prediction With Limited Sample at Heterogeneous Signalized Intersections
Machine learning-based real-time traffic conflict prediction has been a crucial part for proactive traffic safety management in Intelligent Transportation System. However, most existing models struggle with limited-sample data and poor generalization across different locations. This study proposes a Model-Agnostic Meta-Learning (MAML)-driven deep learning framework that integrates Transformer and Long Short-Term Memory (LSTM) architectures to address the challenges of real-time conflict prediction at signal cycle level for intersections. The MAML framework enables rapid adaptation to new intersections by learning a universal initialization from meta-tasks, while the Transformer-LSTM model captures complex relationships in multivariate traffic parameters and temporal variations in traffic flow characteristics. Standalone LSTM and Transformer models are employed as baselines and to validate the model-agnostic nature of MAML. Video recordings from four signalized intersections were used to extract key traffic features and lane configuration was incorporated as additional input features. Severe rear-end conflict events were labeled based on the 85th percentile threshold of the Modified Time to Collision (MTTC). Extensive comparative experiments show that the MAML-driven models significantly outperform their non-MAML counterparts. Among them, the MAML-driven Transformer-LSTM model significantly outperforms both MAML-driven standalone LSTM and Transformer models. The results underscore MAML’s advantage in implicitly capturing intersection heterogeneity and its effectiveness in handling traffic conflict prediction under limited-sample scenarios. Additionally, sensitivity analysis revealed that the model showed low sensitivity to the sliding time window and the percentile defining severe traffic conflict thresholds, while transferability analysis confirmed its ability to generalize across four intersections and external data from different urban region.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4811-4823
Model-Agnostic Meta-Learning-Based Real-Time Traffic Conflict Prediction With Limited Sample at Heterogeneous Signalized Intersections
Machine learning-based real-time traffic conflict prediction has been a crucial part for proactive traffic safety management in Intelligent Transportation System. However, most existing models struggle with limited-sample data and poor generalization across different locations. This study proposes a Model-Agnostic Meta-Learning (MAML)-driven deep learning framework that integrates Transformer and Long Short-Term Memory (LSTM) architectures to address the challenges of real-time conflict prediction at signal cycle level for intersections. The MAML framework enables rapid adaptation to new intersections by learning a universal initialization from meta-tasks, while the Transformer-LSTM model captures complex relationships in multivariate traffic parameters and temporal variations in traffic flow characteristics. Standalone LSTM and Transformer models are employed as baselines and to validate the model-agnostic nature of MAML. Video recordings from four signalized intersections were used to extract key traffic features and lane configuration was incorporated as additional input features. Severe rear-end conflict events were labeled based on the 85th percentile threshold of the Modified Time to Collision (MTTC). Extensive comparative experiments show that the MAML-driven models significantly outperform their non-MAML counterparts. Among them, the MAML-driven Transformer-LSTM model significantly outperforms both MAML-driven standalone LSTM and Transformer models. The results underscore MAML’s advantage in implicitly capturing intersection heterogeneity and its effectiveness in handling traffic conflict prediction under limited-sample scenarios. Additionally, sensitivity analysis revealed that the model showed low sensitivity to the sliding time window and the percentile defining severe traffic conflict thresholds, while transferability analysis confirmed its ability to generalize across four intersections and external data from different urban region.
- 30 December 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (9) , 542-557
Investigating the Hybrid Approach of Anomaly Detection and EVT for Conflict-Based Crash Estimation Considering Variations in Safety Hierarchy
The hybrid framework of extreme value theory (EVT) models and machine-learning-based anomaly detection methods has emerged as an effective approach for traffic-conflict-based crash estimation. This study investigates the generalizability of the hybrid framework across prevalent safety hierarchy models, namely pyramid-shaped and diamond-shaped hierarchies. Two anomaly detection methods—isolation forest (IForest) and minimum covariance determinant (MCD)—were integrated into the EVT modeling framework and compared with the conventional peak over threshold (POT) method. The methods were applied to two distinct datasets. One is the highD dataset corresponding to pyramid-shaped safety hierarchy, and the other is an intersection dataset corresponding to diamond-shaped hierarchy. The results reveal that IForest and MCD exhibit performance comparable to POT when applied to pyramid-shaped data with large sample sizes. However, these methods underperformed with diamond-shaped data because of its double-peak distribution, with performance improving when the data was reshaped to a pyramid shape. Furthermore, in the context of smaller datasets, an increase in the contamination rate for IForest and MCD was found to improve performance, surpassing POT in certain cases. Additionally, IForest displays sensitivity to the order of data, whereas MCD yields consistent outcomes regardless of the data arrangement.
- 30 December 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (9) , 542-557
Investigating the Hybrid Approach of Anomaly Detection and EVT for Conflict-Based Crash Estimation Considering Variations in Safety Hierarchy
The hybrid framework of extreme value theory (EVT) models and machine-learning-based anomaly detection methods has emerged as an effective approach for traffic-conflict-based crash estimation. This study investigates the generalizability of the hybrid framework across prevalent safety hierarchy models, namely pyramid-shaped and diamond-shaped hierarchies. Two anomaly detection methods—isolation forest (IForest) and minimum covariance determinant (MCD)—were integrated into the EVT modeling framework and compared with the conventional peak over threshold (POT) method. The methods were applied to two distinct datasets. One is the highD dataset corresponding to pyramid-shaped safety hierarchy, and the other is an intersection dataset corresponding to diamond-shaped hierarchy. The results reveal that IForest and MCD exhibit performance comparable to POT when applied to pyramid-shaped data with large sample sizes. However, these methods underperformed with diamond-shaped data because of its double-peak distribution, with performance improving when the data was reshaped to a pyramid shape. Furthermore, in the context of smaller datasets, an increase in the contamination rate for IForest and MCD was found to improve performance, surpassing POT in certain cases. Additionally, IForest displays sensitivity to the order of data, whereas MCD yields consistent outcomes regardless of the data arrangement.
- 25 September 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 223, 108249
Bayesian hierarchical non-stationary hybrid modeling for threshold estimation in peak over threshold approach
- 25 September 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 223, 108249
Bayesian hierarchical non-stationary hybrid modeling for threshold estimation in peak over threshold approach
- 28 August 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 221, 108215
How long is long enough for traffic conflict observation: An investigation using extreme value theory approaches
- 28 August 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 221, 108215
How long is long enough for traffic conflict observation: An investigation using extreme value theory approaches
- Open Access
Bayesian hierarchical non-stationary hybrid modeling for threshold estimation in peak over threshold approach
Extreme value theory (EVT) has been utilized to estimate crash risk from traffic conflicts with the peak over threshold approach. However, it's challenging to determine a suitable threshold to distinguish extreme conflicts in an objective way. The subjective and arbitrary selection of the threshold in the peak over threshold approach can result in biased estimation outcomes. This study proposes a Bayesian hierarchical hybrid modeling (BHHM) framework for the threshold estimation in the peak over threshold approach. Specifically, BHHM is based on a piecewise function to model the general conflicts with specific distribution while model the extreme conflicts with generalized Pareto distribution (GPD). The Bayesian hierarchical structure is used to combine traffic conflicts from different sites, incorporating covariates and site-specific unobserved heterogeneity. Five non-stationary BHHM models, including Normal-GPD, Cauchy-GPD, Logistic-GPD, Gamma-GPD, and Lognormal-GPD models, were developed and compared. Traditional graphical diagnostic and quantile regression approaches were also used for comparison. Traffic conflicts collected from three signalized intersections in the city of Surrey, British Columbia were used for the study. The results show that the proposed BHHM approach could estimate the threshold parameter objectively. The Lognormal-GPD model is superior to the other four BHHM models in terms of crash estimation accuracy and model fit. The crash estimates using the threshold determined by the BHHM outperform those estimated based on the graphical diagnostic and quantile regression approaches, indicating the superiority of the proposed threshold determination approach. The findings of this study contribute to enhancing the existing EVT methods for providing a threshold determination approach as well as producing reliable crash estimations.
Open AccessBayesian hierarchical non-stationary hybrid modeling for threshold estimation in peak over threshold approach
Extreme value theory (EVT) has been utilized to estimate crash risk from traffic conflicts with the peak over threshold approach. However, it's challenging to determine a suitable threshold to distinguish extreme conflicts in an objective way. The subjective and arbitrary selection of the threshold in the peak over threshold approach can result in biased estimation outcomes. This study proposes a Bayesian hierarchical hybrid modeling (BHHM) framework for the threshold estimation in the peak over threshold approach. Specifically, BHHM is based on a piecewise function to model the general conflicts with specific distribution while model the extreme conflicts with generalized Pareto distribution (GPD). The Bayesian hierarchical structure is used to combine traffic conflicts from different sites, incorporating covariates and site-specific unobserved heterogeneity. Five non-stationary BHHM models, including Normal-GPD, Cauchy-GPD, Logistic-GPD, Gamma-GPD, and Lognormal-GPD models, were developed and compared. Traditional graphical diagnostic and quantile regression approaches were also used for comparison. Traffic conflicts collected from three signalized intersections in the city of Surrey, British Columbia were used for the study. The results show that the proposed BHHM approach could estimate the threshold parameter objectively. The Lognormal-GPD model is superior to the other four BHHM models in terms of crash estimation accuracy and model fit. The crash estimates using the threshold determined by the BHHM outperform those estimated based on the graphical diagnostic and quantile regression approaches, indicating the superiority of the proposed threshold determination approach. The findings of this study contribute to enhancing the existing EVT methods for providing a threshold determination approach as well as producing reliable crash estimations.
- 16 March 2025
- Published by Springer Nature
- p. 486-494
Analyzing User Needs of Autonomous Transportation Systems with Activity Theory and Knowledge Graph
- 16 March 2025
- Published by Springer Nature
- p. 486-494
Analyzing User Needs of Autonomous Transportation Systems with Activity Theory and Knowledge Graph
- 15 July 2024
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 206, 107717
Bayesian hybrid gamma-GPD model for extreme traffic conflict threshold determination in the peak over threshold approach
- 15 July 2024
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 206, 107717
Bayesian hybrid gamma-GPD model for extreme traffic conflict threshold determination in the peak over threshold approach
- 21 March 2024
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2678 (10) , 916-925
Multi-Type Traffic Conflict Identification at Signalized Intersections Based on LiDAR Point Cloud
Traffic conflicts have been widely used for proactive road safety evaluation, and this study develops methods to automatically identify different types of traffic conflict based on LiDAR point cloud data. With 10 h of data collected from a signalized intersection in Harbin, China, trajectories of motorized vehicles, bicycles, and pedestrians were extracted, and methods to handle the issues of trajectory discontinuity, type identification error, and same object with different trajectories were developed. Traffic conflicts between right-turn vehicles and through vehicles, between right-turn vehicles and left-turn vehicles, and between right-turn vehicles and pedestrians were considered, and detailed procedures for calculating the conflict indicators (i.e., time to collision [TTC] and post encroachment time [PET]) of different types were proposed. The identified traffic conflicts were also compared with the ones that were identified manually. A total of 5,352 and 1,366 traffic conflicts were identified by PET ≤ 4 s and TTC ≤ 4 s, respectively. The majority were during the through phase, and traffic conflicts between right-turn vehicles and through vehicles were the most common, followed by conflicts between right-turn vehicles and vulnerable road users (i.e., cyclists and pedestrians).The proposed automatic method considers the actual sizes of involved road users and thus leads to more accurate conflict indicator calculation, with an average accuracy over 90%.
- 21 March 2024
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2678 (10) , 916-925
Multi-Type Traffic Conflict Identification at Signalized Intersections Based on LiDAR Point Cloud
Traffic conflicts have been widely used for proactive road safety evaluation, and this study develops methods to automatically identify different types of traffic conflict based on LiDAR point cloud data. With 10 h of data collected from a signalized intersection in Harbin, China, trajectories of motorized vehicles, bicycles, and pedestrians were extracted, and methods to handle the issues of trajectory discontinuity, type identification error, and same object with different trajectories were developed. Traffic conflicts between right-turn vehicles and through vehicles, between right-turn vehicles and left-turn vehicles, and between right-turn vehicles and pedestrians were considered, and detailed procedures for calculating the conflict indicators (i.e., time to collision [TTC] and post encroachment time [PET]) of different types were proposed. The identified traffic conflicts were also compared with the ones that were identified manually. A total of 5,352 and 1,366 traffic conflicts were identified by PET ≤ 4 s and TTC ≤ 4 s, respectively. The majority were during the through phase, and traffic conflicts between right-turn vehicles and through vehicles were the most common, followed by conflicts between right-turn vehicles and vulnerable road users (i.e., cyclists and pedestrians).The proposed automatic method considers the actual sizes of involved road users and thus leads to more accurate conflict indicator calculation, with an average accuracy over 90%.