Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Posts

ZFighting: An Interesting Experience of AI-Human Coding FPS Game

1 minute read

Published: November 05, 2025

This post shares my experience of developing a FPS game using Gemini AI Studio and Cursor, showcasing the collaborative potential between AI and human in game creation.

publications

Trajectory Data Based Freeway High-Risk Events Prediction and Its Influencing Factors Analyses

Rongjie Yu, Lei Han, Hui Zhang*

Published in Accident Analysis & Prevention, 2021

This study uses High-D realistic vehicle trajectory data to predict high-risk events on freeways using random-parameter logistic regression models, achieving 97% prediction accuracy 2 seconds ahead of the occurrence of events.

DOI

Traffic Conflicts Analysis Trajectory Data Statistics

</div>

Effects of Spacing of Highway Roadside Millimeter-Wave Radar Detectors on the Accuracy of a Crash Risk Evaluation Model

Dongfeng Yang, Jie Dai, Yueyan Zhang, Lei Han, Rongjie Yu*

Published in 交通信息与安全, 2023

This study investigates optimal spacing for millimeter-wave radar detectors on highways using a deep forest model. It achieves AUC of 0.849 with 80.9% recall, which is higher than CNN and RF models. It also finds that 750 m spacing balances cost and crash risk evaluation accuracy.

DOI

Crash Prediction Detector Data ML

</div>

Driving Risk Assessment Under the Connected Vehicle Environment: A CNN-LSTM Modeling Approach

Yin Zheng, Lei Han, Jiqing Yu, Rongjie Yu*

Published in Digital Transportation and Safety, 2023

This study proposes a CNN-LSTM hybrid model for driving risk assessment using connected vehicle data. It takes time-series top views of CV driving environment as inputs, achieving an AUC of 0.997 by capturing spatial interactions and temporal variability.

DOI

Traffic Conflicts Analysis Trajectory Data DL

</div>

Improving Model Robustness of Traffic Crash Risk Evaluation via Adversarial Mix-Up Under Traffic Flow Fundamental Diagram

Rongjie Yu, Lei Han, Mohamed Abdel-Aty, Liqiang Wang, Zihang Zou*

Published in Accident Analysis & Prevention, 2024

This study addresses robustness issues in deep learning-based crash risk evaluation models. By proposing a coverage-oriented adversarial training method, it generates traffic flow adversarial examples (TF-AEs) to prevent 76.5% accuracy drops and 98.9% sensitivity drops.

DOI

Crash Prediction Detector Data DL

</div>

Utilizing Angle-Based Outlier Detection Method with Sliding Window Mechanism to Identify Real-Time Crash Risk

Zhen Gao, Jingning Xu, Rongjie Yu*, Lei Han

Published in Journal of Transportation Safety & Security, 2024

This study introduces an unsupervised Angle-Based Outlier Detection approach with sliding window mechanism for real-time expressway crash risk identification, achieving 80.4% sensitivity and addressing data imbalance issues.

DOI

Crash Prediction Detector Data ML

</div>

Effects of Speed Difference on Injury Severity of Freeway Rear-End Crashes: Insights from Correlated Joint Random Parameters Bivariate Probit Models and Temporal Instability

Chenzhu Wang*, Mohamed Abdel-Aty, Lei Han

Published in Analytic Methods in Accident Research, 2024

This study investigates the impact of speed differences on rear-end crash severity using joint random parameters bivariate probit models, accounting for temporal instability during COVID-19.

DOI

Crash Severity Crash Data Statistics

</div>

Transformer-Based Modeling of Abnormal Driving Events for Freeway Crash Risk Evaluation

Lei Han, Rongjie Yu*, Chenzhu Wang, Mohamed Abdel-Aty

Published in Transportation Research Part C: Emerging Technologies, 2024

This study proposes a Transformer-based model for freeway crash risk evaluation using abnormal driving events, achieving 84.1% accuracy and 77.7% AUC and outperforming traditional methods. It also reveals the temporal-spatial decay and collective effect of abnormal driving events.

DOI

Crash Prediction Risky Driving Behavior CV Data DL

</div>

LSTM + Transformer Real-Time Crash Risk Evaluation Using Traffic Flow and Risky Driving Behavior Data

Lei Han, Mohamed Abdel-Aty, Rongjie Yu*, Chenzhu Wang

Published in IEEE Transactions on Intelligent Transportation Systems, 2024

This study develops an LSTM + Transformer approach integrating traffic flow data from millimeter-wave radars and risky driving behavior data from connected vehicles, achieving 77.7% accuracy and 78.5% AUC for real-time crash risk evaluation.

DOI

Crash Prediction Risky Driving Behavior CV Data Detector Data DL

</div>

Analyzing Speed-Difference Impact on Freeway Joint Injury Severities of Leading-Following Vehicles Using Statistical and Data-Driven Models

Chenzhu Wang, Mohamed Abdel-Aty, Lei Han*, Said Easa

Published in Accident Analysis & Prevention, 2024

This study analyzes the impact of speed differences on joint injury severities in freeway rear-end crashes using joint statistical and machine learning models.

DOI

Crash Severity Crash Data ML

</div>

Effects of Helmet Usage on Moped Riders’ Injury Severity in Moped-Vehicle Crashes: Insights from Partially Temporal Constrained Random Parameters Bivariate Probit Models

Chenzhu Wang, Mohamed Abdel-Aty, Pengfei Cui*, Lei Han

Published in Accident Analysis & Prevention, 2024

This study examines the association between helmet usage and injury severity in moped-vehicle crashes using partially temporally constrained random parameters bivariate probit models.

DOI

Crash Severity Crash Data Statistics

</div>

Impact of Speed on Injury Severity in Single-Vehicle Run-Off-Road Crashes: Insights from Partially Temporal Constrained Modeling Approach

Zhe Wang, Chenzhu Wang*, Mohamed Abdel-Aty, Lei Han, Helai Huang, Jinjun Tang

Published in Accident Analysis & Prevention, 2025

This study investigates the impact of speed on injury severity in single-vehicle run-off-road crashes using a partially temporal constrained modeling approach.

DOI

Crash Severity Crash Data Statistics

</div>

Tunnel Crash Severity and Congestion Duration Joint Evaluation Based on Cross-Stitch Networks

Chenzhu Wang, Mohamed Abdel-Aty, Lei Han*

Published in Accident Analysis & Prevention, 2025

This study proposes a joint cross-stitch network model to simultaneously evaluate tunnel crash severity and congestion duration, achieving improved performance over separate models by capturing coupling relationships between the two outcomes.

DOI

Crash Severity Crash Data ML

</div>

Intersection Crash Frequency Analysis Considering Visual Environment Features Using Random Parameter Negative Binomial-Lindley Model

Lei Han*, Mohamed Abdel-Aty, Yang-Jun Joo, Shaoyan Zhai, Dongdong Wang

Published in Transportation Research Record, 2025

This study incorporates visual environment features from Google Street View images into a random parameter negative binomial-Lindley model for intersection crash frequency analysis.

DOI

Crash Frequency Crash Data Streetview Statistics

</div>

Intersection Crash Analysis Considering Longitudinal and Lateral Risky Driving Behavior from Connected Vehicle Data: A Spatial Machine Learning Approach

Lei Han*, Mohamed Abdel-Aty

Published in Accident Analysis & Prevention, 2025

This study proposes a spatial-ML framework integrating longitudinal and lateral risky driving behaviors from connected vehicle data for intersection crash analysis.

DOI

Crash Frequency Risky Driving Behavior Spatial Modeling CV Data ML

</div>

Grouped Random Parameters Poisson-Lindley Model with Spatial Effects Addressing Crashes at Intersections: Insights from Visual Environment Features and Spatiotemporal Instability

Chenzhu Wang, Mohamed Abdel-Aty, Lei Han*

Published in Analytic Methods in Accident Research, 2025

This study develops a grouped random-parameters Poisson-Lindley model with spatial effects to analyze intersection crashes with visual environment features and spatiotemporal variations.

DOI

Crash Frequency Spatial Modeling Crash Data Streetview Statistics

</div>

Multiscale Geographical Random Forest: A Novel Spatial ML Approach for Traffic Safety Modeling Integrating Street-View Semantic Visual Features

Pengfei Cui, Mohamed Abdel-Aty, Lei Han*, Xiaobao Yang

Published in Transportation Research Part C: Emerging Technologies, 2025

This study proposes a Multiscale Geographical Random Forest (MGRF) integrating street-view semantic visual features for traffic safety modeling by capturing multiscale spatial heterogeneity.

DOI

Crash Frequency Spatial Modeling Streetview ML

</div>

Segment Level Safety Analysis Using Lane-Changing Behavior and Driving Volatility Features from Connected Vehicle Trajectories

Lei Han*, Mohamed Abdel-Aty

Published in Scientific Reports, 2025

This study analyzes segment-level safety using lane-changing and driving volatility features from CV trajectories, revealing critical relationships between risky driving behaviors and crash types.

DOI

Crash Frequency Risky Driving Behavior CV Data Statistics

</div>

Crash Prediction Under Limited CV Coverage: An Ensemble Deep Learning Model Integrating Multi-Source Traffic Data

Samgyu Yang*, Mohamed Abdel-Aty, Lei Han

Published in Transportation Research Part C: Emerging Technologies, 2026

This study develops an ensemble deep learning model integrating MVDS and connected vehicle data for crash prediction, demonstrating superior performance over single-source models, with CV-only models achieving sensitivity exceeding 0.79 at 4% penetration or higher.

DOI

Crash Prediction CV Data Detector Data DL

</div>

Real-time Secondary Crash Likelihood Prediction Excluding Post Primary Crash Features

Lei Han*, Mohamed Abdel-Aty, Zubayer Islam, Chenzhu Wang

Preprint, Under Reviewed in IEEE Transactions on Intelligent Transportation Systems

A hybrid model for real-time secondary crash likelihood prediction that excludes post-crash features, using dynamic spatial-temporal windows and ensemble machine learning methods to achieve 91% identification accuracy with AUC of 0.952.

Crash Prediction Secondary Crash Detector Data ML

</div>

MMCAformer: Macro-Micro Cross-Attention Transformer for Traffic Speed Prediction with Microscopic Connected Vehicle Driving Behavior

Lei Han*, Mohamed Abdel-Aty, Younggun Kim, Yang-Jun Joo, Zubayer Islam

Preprint, Under Reviewed in IEEE Transactions on Intelligent Transportation Systems

A Macro-Micro Cross-Attention Transformer (MMCAformer) model that integrates CV data-based micro driving behavior features with macro traffic features for freeway speed prediction.

Traffic State Prediction Risky Driving Behavior CV Data DL

</div>

Arterial Network Traffic State Prediction with Connected Vehicle Data: An Abnormality-Aware Spatiotemporal Network

Lei Han*, Mohamed Abdel-Aty, Yang-Jun Joo

Preprint, Under Reviewed in Transportation Research Part C: Emerging Technologies

This study proposes a CV data-based arterial traffic prediction framework with two-stage traffic-state extraction and an AASTGCN for arterial delay and queue predictions.

Traffic State Prediction CV Data DL

</div>

Lei Han

Sitemap

Pages

Posts

publications