Fanyun Meng

Fanyun Meng

Auto-generated profile, based on publicly available information

Fanyun Meng

School of Transportation, Jilin University, Changchun 130022, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
18 November 2022 in Journal of Cleaner Production
Verified
Journal Article
Closed access
LZLili Zheng
Lili Zheng
FMFanyun Meng
Fanyun Meng
TDTongqiang Ding
Tongqiang Ding
QYQingfang Yang
Qingfang Yang
ZXZifang Xie
Zifang Xie
ZJZhongtai Jiang
Zhongtai Jiang

17 December 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
LZLili Zheng
Lili Zheng
YZYanlin Zhang
Yanlin Zhang
TDTongqiang Ding
Tongqiang Ding
FMFanyun Meng
Fanyun Meng
YLYanlin Li
Yanlin Li
SCShiyu Cao
Shiyu Cao
Driver distraction is one of the significant causes of traffic accidents. To improve the accuracy of accident occurrence prediction under driver distraction and to provide graded warnings, it is necessary to classify the level of driver distraction. Based on naturalistic driving study data, distraction risk levels are classified using the driver’s gaze and secondary driving tasks in this paper. The classification results are then combined with road environment factors for accident occurrence prediction. Two ways are suggested to classify driver distraction risk levels in this study: one is to divide it into three levels based on the driver’s gaze and the AttenD algorithm, and the other is to divide it into six levels based on secondary driving tasks and odds ratio. Random Forest, AdaBoost, and XGBoost are used to predict accident occurrence by combining the classification results, driver characteristics, and road environment factors. The results show that the classification of distraction risk levels helps improve the model prediction accuracy. The classification based on the driver’s gaze is better than that based on secondary driving tasks. The classification method can be applied to accident risk prediction and further driving risk warning.

31 October 2024 in Heliyon
Verified
Journal Article
Open access
LZLili Zheng
Lili Zheng
YYYujing Yang
Yujing Yang
TDTongqiang Ding
Tongqiang Ding
HLHaode Liu
Haode Liu
FMFanyun Meng
Fanyun Meng
YZYanlin Zhang
Yanlin Zhang
In view of the suddenness, complexity and high-risk potential of bus crashes, the injury severity and its influencing factors have increasingly became the research focus in urban transportation safety management. The purpose of this study is to analyze the core elements of bus crash injury severity and its interaction mechanism, in order to provide a scientific basis for improving the bus operation safety. In this study, 283 crashes occurred in a Chongqing bus company from January to June 2022 were taken as samples around the dimensions of drivers' educational background, driving characteristics, weather, and corporate management strategies. PLS-SEM, CoMe index, MICOM, and permutation-based MGA are comprehensively applied to deeply analyze the direct and indirect effects among variables and reveal the conditional mediation effect. The study found crash injury severity effects ranked in order of crash liability, work intensity, weather conditions, violation tendency, education, and driving experience. Bus driver's crash liability plays a fully mediating role between several factors and injury severity, while improving education and increasing rest gap time are effective in reducing bus driver's crash liability. Notably, bad weather flat peaks and good weather peak periods are prone to more severe bus crashes. In addition, the mediating effect of driving experience on liability level through violation tendency was significant only in bus driver groups with moderate to high sense of work responsibility. This study deepens our understanding of bus crash injury severity and its interaction mechanism, guiding targeted safety measures for bus corporation and boosting overall public transportation safety.

27 January 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
ZWZhuorui Wang
Zhuorui Wang
DYDeXin Yu
DeXin Yu
XZXiaoyu Zheng
Xiaoyu Zheng
FMFanyun Meng
Fanyun Meng
XWXincheng Wu
Xincheng Wu
Bike-sharing has emerged as an innovative green transportation mode, showing promising potential in addressing the ‘last-mile’ transportation challenge in an eco-friendly manner. However, shared bikes around metro stations often face supply–demand imbalance problems during peak hours, causing bike shortages or congestion that compromise user experience and bike utilization. Accurate prediction enables operators to develop rational dispatch strategies, improve bike turnover rate, and promote synergistic metro–bike integration. However, state-of-the-art research predominantly focuses on improving complex deep-learning models while overlooking their inherent drawbacks, such as overfitting and poor interpretability. This study proposes a model–data dual-driven approach that integrates the classical statistical regression model as a model-driven component and the advanced deep-learning model as a data-driven component. The model-driven component uses the Seasonal Autoregressive Integrated Moving Average (SARIMA) model to extract periodic patterns and seasonal variations of historical data, while the data-driven component employs an Extended Long Short-Term Memory (xLSTM) neural network to process nonlinear relationships and unexpected variations. The fusion model achieved R-squared values of 0.9928 and 0.9770 for morning access and evening egress flows, respectively, and reached 0.9535 and 0.9560 for morning egress and evening access flows. The xLSTM model demonstrates an 8% improvement in R2 compared to the conventional LSTM model in the morning egress flow scenario. For the morning egress and evening access flows, which exhibit relatively high variability, classical statistical models show limited effectiveness (SARIMA’s R2 values are 0.8847 and 0.9333, respectively). Even in scenarios like morning access and evening egress, where classical statistical models perform well, our proposed fusion model still demonstrates enhanced performance. Therefore, the proposed data–model dual-driven architecture provides a reliable data foundation for shared bike rebalancing and shows potential for addressing the challenges of limited robustness in statistical regression models and the susceptibility of deep-learning models to overfitting, ultimately enhancing transportation ecosystem sustainability.

21 May 2025 in Buildings
Verified
Journal Article
Open access
PDF file
ZWZhuorui Wang
Zhuorui Wang
XZXiaoyu Zheng
Xiaoyu Zheng
FMFanyun Meng
Fanyun Meng
KWKang Wang
Kang Wang
XWXincheng Wu
Xincheng Wu
DYDeXin Yu
DeXin Yu
Modern cities are facing increasing challenges such as traffic congestion, high energy consumption, and poor air quality, making rail transit systems, known for their high capacity and low emissions, essential components of sustainable urban infrastructure. While numerous studies have examined how the built environment impacts transit ridership, the complex interactions among these factors warrant further investigation. Recent advancements in the reasoning capabilities of large language models (LLMs) offer a robust methodological foundation for analyzing the complex joint influence of multiple built environment factors. LLMs not only can comprehend the physical meaning of variables but also exhibit strong non-linear modeling and logical reasoning capabilities. This study introduces an LLM-based framework to examine how built environment factors and station characteristics shape the transit ridership dynamics by utilizing DeepSeek-R1. We develop a 4D + N variable system for a more nuanced description of the built environment of the station area which includes density, diversity, design, destination accessibility, and station characteristics, leveraging multi-source data such as points of interest (POIs), road network data, housing prices, and population data. Then, the proposed approach is validated using data from Qingdao, China, examining both single-factor and multi-factor effects on transit peak-hour ridership at the macro level (across all stations) and the meso level (specific station types). First, the variables that have a substantial effect on peak-hour transit ridership at both the macro and meso levels are discussed. Second, key and latent factor combinations are identified. Notably, some factors may appear to have limited importance at the macro level, yet they can substantially influence the peak-hour ridership when interacting with other factors. Our findings enable policymakers to formulate a balanced mix of soft and hard policies, such as integrating a flexitime policy with enhancements in active travel infrastructure to increase the attractiveness of public transit. The proposed analytical framework is adaptable across regions and applicable to various transportation modes. These insights can guide transportation managers and policymakers while optimizing Transit-Oriented Development (TOD) strategies to enhance the sustainability of the entire transportation system.

SLSiliang Luan
Siliang Luan
QYQingfang Yang
Qingfang Yang
ZJZhongtai Jiang
Zhongtai Jiang
HZHuxing Zhou
Huxing Zhou
FMFanyun Meng
Fanyun Meng
The purpose of this paper is to gain an insight into commuting and travel mode choices in the post-COVID-19 era. The surveys are divided into two waves in Qingdao, China: the first-wave questionnaires were collected under the background of a three-month zero growth of cases; the second wave was implemented after the new confirmed cases of COVID-19. The latent class nested logit (LCNL) model is applied to capture heterogeneous characteristics among the various classes. The results indicate that age, income, household composition, and the frequency of use of travel modes are latent factors that impact users’ attitudes toward mass transit and the private car nests when undergoing the shock of the COVID-19 pandemic. Individuals’ trepidation regarding health risks began to fade, but this is still a vital consideration in terms of mode choice and the purchase of vehicles. Moreover, economic reinvigoration, the increase in car ownership, and an increase in the desire to purchase a car may result in great challenges for urban traffic networks.