Zhang Weiwei

Dr. Zhang Weiwei


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 January 2025 in Vehicles
Verified
Journal Article
Open access
PDF file
YJYalan Jiang
Yalan Jiang
XQXianguo Qu
Xianguo Qu
ZWZhang Weiwei
Zhang Weiwei
WGWenfeng Guo
Wenfeng Guo
JXJiejie Xu
Jiejie Xu
CYChen Yang
Chen Yang
Traffic accident-related injuries and fatalities are a serious global public health and social development challenge. The accurate prediction of crash severity improves road safety and reduces casualties, as well as serving road managers and policy makers. Prediction models need to learn and analyze the various characteristic factors of traffic accidents and capture from them the inherent complex relationship between accident characteristics and the severity of traffic accidents. However, most accident prediction studies lack analytical predictions of injury severity, and predictive models rely on the content and quality of accident datasets. To increase the robustness and accuracy of prediction models, this paper leverages a Transformer-based architecture for the severity prediction of traffic collisions from human injury severity. This framework learns both text and sequence data from accident datasets. After comparative analysis, the framework can achieve the prediction of human injury severity under different data categories and show good prediction performance at low injury severity levels using only textual data or sequence data.

3 May 2025 in Vehicles
Verified
Journal Article
Open access
PDF file
PLPeng Liu
Peng Liu
ZWZhang Weiwei
Zhang Weiwei
XWXuncheng Wu
Xuncheng Wu
Wenfeng GuoWenfeng Guo
Wenfeng Guo
WYWangpengfei Yu
Wangpengfei Yu
Vehicle accidents, particularly PV-PV collisions, result in significant property damage and driver injuries, causing substantial economic losses and health risks. Most existing studies focus on macro-level predictions, such as accident frequency, but lack detailed collision-level analysis, which limits the precision of severity prediction. This study investigates various accident-related factors, including environmental conditions, vehicle attributes, driver characteristics, pre-crash scenarios, and collision dynamics. Data from NHTSA’s CRSS and FARS datasets were integrated and balanced using random over-sampling and under-sampling techniques to address severity-level data imbalances. The mRMR algorithm was employed for feature selection to minimize redundancy and identify key features. Five advanced machine learning models were evaluated for severity prediction, with XGBoost achieving the best performance: 84.9% accuracy, 84.85% precision, 84.90% recall, and an F1-score of 84.87%. SHAP analysis was utilized to interpret the model and conduct a comprehensive analysis of accident features, including their importance, dependencies, and combined effects on severity prediction. This study achieved high accuracy in predicting accident severity across all levels in PV-PV collisions. Moreover, by integrating the SHAP model interpretation method, we conducted detailed feature analysis at global, local, and individual case levels, thereby filling the gap in PV-PV accident severity prediction and feature analysis.

26 March 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
PLPeng Liu
Peng Liu
ZWZhang Weiwei
Zhang Weiwei
XWXuncheng Wu
Xuncheng Wu
Wenfeng GuoWenfeng Guo
Wenfeng Guo
Vehicle accidents, particularly passenger vehicle-to-passenger vehicle (PV-PV) collisions, cause significant property damage and driver injuries, resulting in substantial economic losses and health risks. Most existing studies focus on macro-level predictions, such as accident frequency, but lack detailed collision-level analysis, which limits precise severity prediction. This study investigates various accident-related factors, including environmental conditions, vehicle attributes, driver characteristics, pre-crash scenarios, and collision dynamics.Using data from the National Highway Traffic Safety Administration’s (NHTSA) Crash Report Sampling System (CRSS) and Fatality Analysis Reporting System (FARS), the dataset was balanced by integrating complementary severity-level data with random over-sampling and under-sampling techniques. The Minimum Redundancy Maximum Relevance (mRMR) algorithm was used for feature selection to minimize redundancy and identify key features.Five advanced machine learning models were employed for severity prediction, with Extreme Gradient Boosting (XGBoost) achieving the best performance: 84.9% accuracy, 84.85% precision, 84.90% recall, and an F1-score of 84.87%. SHapley Additive exPlanations (SHAP) analysis was employed to interpret the model and conduct a deep analysis of accident features, including feature importance, dependencies, and their combined effects on severity prediction.The findings highlight the effectiveness of interpretable machine learning in understanding accident severity and identifying key factors influencing driver injuries.

23 July 2025 in Signal, Image and Video Processing
Verified
Journal Article
Closed access
PDF file
ZWZhang Weiwei
Zhang Weiwei
MLMenghao Li
Menghao Li
HCHao Chen
Hao Chen
MNMi Ning
Mi Ning
WYWangpengfei Yu
Wangpengfei Yu
JLJun Li
Jun Li

10 July 2025 in Research Square
Verified
Preprint
Open access
PDF file
MLMenghao Li
Menghao Li
MWMingxun Wang
Mingxun Wang
ZWZhang Weiwei
Zhang Weiwei
WYWangpengfei Yu
Wangpengfei Yu
Wenfeng GuoWenfeng Guo
Wenfeng Guo
X-ray security inspection systems face significant challenges when deployed across different scanning devices due to domain shifts that substantially degrade prohibited item recognition performance. Existing deep learning approaches assume consistent label distributions between training and testing domains, which is impractical in real-world security scenarios where devices vary in penetration capabilities and imaging characteristics. To address this critical limitation, we propose a Weighted Adaptive Feature Adversarial Network (WAFAN) that leverages partial domain adaptation (PDA) to achieve robust cross-domain prohibited item recognition. Our approach introduces three key innovations: (1) a similarity-based weight assignment strategy that effectively distinguishes relevant target-domain classes from irrelevant source-domain categories, mitigating negative transfer effects; (2) an adaptive convolution module integrated via residual connections that explicitly captures and compensates for cross-domain feature distribution differences; and (3) a multi-space adversarial learning framework that ensures domain-invariant feature extraction. Comprehensive experiments on PIDray and SIXray datasets demonstrate that WAFAN achieves superior performance over state-of-the-art PDA methods, with classification accuracy exceeding 80% on target domains while maintaining computational efficiency. The proposed method offers a practical solution for deploying AI-powered security inspection systems across heterogeneous X-ray devices without requiring extensive retraining or domain-specific annotations.

16 April 2025 in Research Square
Verified
Preprint
Open access
PDF file
ZWZhang Weiwei
Zhang Weiwei
WYWangpengfei Yu
Wangpengfei Yu
Wenfeng GuoWenfeng Guo
Wenfeng Guo
CYChen Yang
Chen Yang
JLJun Li
Jun Li
With the popularization of social media andInternet technology, people are more and more easilydistracted when driving, which has a serious adverseimpact on the safety of expected functions, and reducesthe efficiency of control transmission between humanand computer. This article proposes a real-time pupil re-construction (PURE) algorithm for real-time detectionof pupil direction, and combines it with a 3D eye modelto obtain the gaze direction of the pupil in real time.Subsequently, the Posit algorithm was used to obtain real-time head posture, and the head posture and pupil gaze direction were used as improved input features toestimate the driver’s gaze area in real-time using a random forest model. Finally, this article comprehensivelyconsiders the impact of multiple real-time indicatorson driving attention, such as the number of eye gazeareas, eye scanning areas, road conditions, brain latency,and driving tasks, and proposes a prototype framework for real-time driver multi indicator attention evaluation.Through various real-time evaluation experiments,we have demonstrated that: 1) these context relatedattention features are universal when tested in real-timeon 16 drivers in a driving simulator; 2) The proposeddriver attention evaluation model performs well underreal-time conditions and can produce reliable results invarious driving scenarios.