Zhiwei Cui

Mr. Zhiwei Cui


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
Chao GaoChao Gao
Chao Gao
XLXinyi Lai
Xinyi Lai
SLShasha Li
Shasha Li
ZCZhiwei Cui
Zhiwei Cui
Zhiyou LongZhiyou Long
Zhiyou Long
With the rapid pace of global urbanization, understanding the impact of the urban built environment on travel behavior has become increasingly significant for developing sustainable and efficient transportation systems. This study conducts a bibliometric review of related research over the past two decades (1997–2023), utilizing 1745 publications from the Web of Science database through network analysis and content analysis. It provides a comprehensive quantitative analysis encompassing publication trends, national and institutional collaborations, and keyword evolution clustering perspectives. The results reveal that (1) academic interest in exploring the implications of the urban built environment on travel behavior has grown markedly, especially in the past decade, with emerging technological approaches and research perspectives; (2) the USA, P.R.CHINA, and the United Kingdom are major research forces in this field, with notable contributions from research institutions in P.R.CHINA and the USA; (3) the “Transportation Research Part” series journals demonstrate extensive influence both in terms of publication count and citation count; (4) through keyword co-occurrence network analysis, three development stages along with five major clusters were identified: travel behavior modeling and public health, active transportation and sustainable development, urban development and carbon emissions, land use and transportation integration, and urban transportation systems and machine learning. Overall, sustained research remains warranted within this field, particularly focusing on selecting new built environment metrics while integrating emerging technologies into travel behavior modeling frameworks. The insights from this study have implications for urban transportation planning and policy, offering guidance on future research directions and policymaking.

27 September 2022 in International Journal of Logistics Research and Applications
Verified
Journal Article
Closed access
ZCZhiwei Cui
Zhiwei Cui
JWJianwei Wang
Jianwei Wang
CGChao Gao
Chao Gao
Shi DongShi Dong
Shi Dong
A logistics network structure plays a significant role in enhancing comprehensive logistics services and achieving high-quality development. However, few studies have summarised the application research on China’s logistics network structure. Thus, this study conducted a literature review to summarise such research. Data from 2009 to 2021 were collected from 60 papers from the China National Knowledge Infrastructure, and 13 from Scopus. This study analyzed the literature using descriptive analysis and research states based on the research questions. The descriptive analysis revealed information such as documents, trends, subject areas, and keywords for Chinese and foreign papers using VOSviewer and Gephi software. The research flow revealed the research object, method, and results using ArcGIS visualisation, research features, and perspectives. Finally, this study proposes contributions to practice and theory in three ways.

17 October 2024 in IEEE Access
Verified
Journal Article
Open access
LWLaijun Wang
Laijun Wang
ZCZhiwei Cui
Zhiwei Cui
Shi DongShi Dong
Shi Dong
NWNing Wang
Ning Wang
Low visibility is a major cause of flight delays and airport cancellations. Hence, providing accurate prediction of airport visibility is vital to prevent significant losses for airlines, accordingly to avoid catastrophic aviation accidents. Although many unimodal prediction methods have been developed, there is still room for improvement in airport visibility classification. Therefore, this study proposed an airport visibility classification model that employs a multimodal fusion of image and tabular data to improve classification performance. First, an enhanced image processing method on airport visibility was designed to extract more detailed features related to airport visibility. Next, EfficientNetB1 and Feature Tokenizer Transformer (FT-Transformer) were utilized to extract features from the images and tabular data, respectively. These features were then combined to classify airport visibility using a Multimodal Fusion Multilayer Perceptron with a focal loss function, validated through 5-fold stratified cross-validation. Experimental results on the 1864 pairs of image-tabular data from Nanjing Lukou International Airport showed that our model achieved an accuracy of 93.83%, and a Ma-F1 of 91.64%. Comparisons with various image extraction methods indicated that EfficientNetB1 with integrated images provides the best performance and shorter running time. The comparison of multimodal fusion and unimodal image classifications revealed that the accuracy and Ma-F1 of unimodal image classifications are lower than those for multimodal classification by 8.56% and 12.85%. In addition, ablation experiments also proved the effectiveness of the enhanced image processing and multimodal fusion modules.

21 February 2026 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
MZMingzhu Zheng
Mingzhu Zheng
CZChen Zuo
Chen Zuo
Shi DongShi Dong
Shi Dong
ZCZhiwei Cui
Zhiwei Cui
GGGengbin Guo
Gengbin Guo
DSDaniel Jian Sun
Daniel Jian Sun
Traffic crashes, especially rear-end collisions, fixed-object crashes, and rollovers, are common and severe, highlighting the need for comprehensive classification and management. However, research on classifying and managing imbalanced traffic crash data is limited. Therefore, this study proposes an analytic framework for imbalanced traffic crash type classification and management using a hybrid tabular transformer approach. The central idea is to analyze data using feature selection, multi-crash type classification, single-crash type clustering, and targeted safety recommendations. First, the multinomial logit model is used for feature selection, removing features with low correlation. Second, the Feature Tokenizer Transformer (FT-Transformer) with the Synthetic Minority Over-Sampling Technique (SMOTE) at varying ratios to perform multiclass crash classification is used. Third, mini-batch K-means clusters crash types based on key features are used. Finally, targeted safety recommendations for each cluster are developed. This study used 5,515 real-world traffic crash records from Anhui Province, China. The results show that: (1) the FT-Transformer model, with SMOTE at a 1:2:4 ratio, outperformed other machine learning models; and (2) rear-end, fixed-object, and rollovers were clustered into three, three, and five categories, respectively. Safety recommendations focus on traffic management (e.g., real time traffic updates), driver behavior (e.g., driving education), and road infrastructure (e.g., reinforced road markings).

26 August 2026 in Reliability Engineering & System Safety
Verified
Journal Article
Closed access
ZCZhiwei Cui
Zhiwei Cui
Shi DongShi Dong
Shi Dong
XCXiaoshi Cheng
Xiaoshi Cheng
YCYou Chen
You Chen
LXLiqin Xu
Liqin Xu