Article
Engineering, Industrial
Zhiyuan Sun, Yuxuan Xing, Jianyu Wang, Xin Gu, Huapu Lu, Yanyan Chen
Summary: This study analyzed crash data from different seasons using a hybrid method combining a random parameter logit (RP-logit) model and Bayesian network (BN). Results showed significant differences in vulnerable road user-motor vehicle crashes across seasons, with different significant factors identified in each season. The proposed hybrid method demonstrated the consistency of methods and highlighted the importance of personalized factors in different seasons.
Article
Green & Sustainable Science & Technology
Quan Yuan, Xianguo Zhai, Wei Ji, Tiantong Yang, Yang Yu, Shengnan Yu
Summary: This research investigates 378 traffic collisions between vehicles and vulnerable road users (VRUs) in China in 2021, analyzing factors that affect injury severity and providing suggestions for accident prevention to reduce harm to VRUs.
Article
Computer Science, Artificial Intelligence
Yufei Cui, Yu Mao, Ziquan Liu, Qiao Li, Antoni B. Chan, Xue Liu, Tei-Wei Kuo, Chun Jason Xue
Summary: Nested dropout is a variant of dropout operation that orders network parameters or features based on pre-defined importance. It has been explored in constructing nested nets and learning ordered representation.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Engineering, Civil
Tomoharu Iwata, Hitoshi Shimizu, Naoki Marumo
Summary: We propose a probabilistic model of pedestrian behavior that estimates population at each road using observed populations and routes. The model incorporates pedestrian dependence on road congestion and derives transition probabilities between roads using a Gaussian distribution. Parameters are estimated through gradient-based optimization methods, and experiments show accurate estimation of road populations.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Economics
Khandker Nurul Habib
Summary: The theory of Rational Inattention (RI) has been proposed in recent literature as an alternative to classical discrete choice models. This paper introduces estimable econometric formulations of RI-MNL and RI-NL models, and applies them to commuting mode choices in the GTHA. The empirical investigation shows that the integration of RI significantly improves model fit, with the RI-NL model outperforming the RI-MNL model and capturing asymmetric elasticities.
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2023)
Article
Ergonomics
Zhenggan Cai, Xiaoyan Wu
Summary: This study proposed a spatiotemporal interaction logit (STI-logit) model for regression analysis of single-vehicle crash severity in Shandong, China. The results showed that the STI-logit model outperformed other models, and simultaneously accommodating stable and unstable spatiotemporal risk patterns can further enhance model fit.
JOURNAL OF SAFETY RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Zhijian Zhang, Yubin Jiang, Zhijun Chen, Yubing Xiong
Summary: This study aimed to deeply analyze the influencing factors of drivers' traffic accident casualties and utilized Bayesian network and multinomial logit models for modeling and analysis. Complex interactions among various influencing factors were identified, and significant effects of drivers' age, gender, road conditions, alcohol and drug use, collision types on injury severity were revealed.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Computer Science, Information Systems
Xiuquan Li, Meizhen Wang, Xuejun Liu, Ziran Wang, Yuxia Bian
Summary: Road network models are essential for road network analysis, route planning, navigation, and traffic predictions. This study addresses the limitation of existing models in effectively representing the dynamic topological relationships among lanes. A time-dependent road network model (TRNM) is proposed to address this issue, and its construction method based on a traditional carriageway network model is presented. Experimental results demonstrate that TRNMs can be constructed easily from traditional road networks without introducing large volumes of data, while effectively representing the time-dependent topological relationships among lanes.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2022)
Article
Ergonomics
Muhammad Tahmidul Haq, Vincent-Michael Kwesi Ampadu, Khaled Ksaibati
Summary: Despite its critical role in vehicular operation, the braking system has not received adequate attention, leading to underrepresentation of brake failures in traffic safety. Limited literature exists on brake failure-related crashes, and previous studies have not extensively investigated the factors associated with brake failures and the corresponding injury severity. This study aims to fill this gap by examining brake failure-related crashes and assessing the factors influencing occupant injury severity.
JOURNAL OF SAFETY RESEARCH
(2023)
Article
Construction & Building Technology
Kubranur Cebi Karaaslan, Yahya Algul, Abdulkerim Karaaslan
Summary: The robust economic growth of the Turkish economy in recent decades has raised concerns over energy deficit and increasing foreign account deficits. The choice of household fuel is crucial due to the high dependence on imported fossil resources to meet the energy demand. Additionally, traditional fuels contribute to indoor air pollution and health hazards. This study utilizes cross-sectional data from the Turkish Statistical Institute's Household Budget Survey to analyze the factors influencing Turkish households' heating preferences. The findings indicate that dwelling characteristics and household characteristics significantly affect fuel choice. The study suggests that government support is necessary for a smooth transition from traditional fuels to modern fuels.
ENERGY AND BUILDINGS
(2022)
Article
Ergonomics
Yang-Jun Joo, Seung-Young Kho, Dong-Kyu Kim, Ho-Chul Park
Summary: This study proposes a probabilistic assessment method of crash risks for individual drivers using a large dataset. By analyzing 7.75 million violations and crashes of 5.5 million drivers in Seoul, the researchers successfully evaluated the crash and violation probabilities and classified drivers into different risk groups.
ACCIDENT ANALYSIS AND PREVENTION
(2022)
Article
Engineering, Manufacturing
Yanqiao Wang, Zuo-Jun Max Shen
Summary: The study focuses on the choice-based constrained assortment optimization problem under the multilevel nested logit model with a no-purchase option. A polynomial-time algorithm is provided to locate the optimal assortment for maximizing the expected profit per customer. The algorithm has a computational complexity of O(nmax{m, k}), where n is the number of products, m is the number of levels in the model, and k is the maximum number of products within any node in level m-1.
PRODUCTION AND OPERATIONS MANAGEMENT
(2021)
Article
Physics, Multidisciplinary
A. Chacoma, G. Abramson, M. N. Kuperman
Summary: This work studies the impact of a traffic light system on the flow of a single lane road using a traffic model based on cellular automaton with behavioral considerations. The analysis focuses on the macroscopic characteristics of the system, observing a phase transition between free flow and jams induced by instabilities at traffic lights. The effect of these instabilities on critical vehicle density for the transition is analyzed as a function of car inflow and drivers' behavior.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2021)
Article
Environmental Sciences
Huan Tong, Joshua L. Warren, Jian Kang, Mingxiao Li
Summary: This study examined the impact of road traffic noise on sleep deprivation at the county level in the United States. The results showed that an increase in traffic noise was associated with an increased likelihood of sleep deprivation, especially in relatively noisy areas. The study suggests that policymakers should implement different noise management strategies based on noise levels and incorporate geospatial noise indicators.
ENVIRONMENTAL RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Qiuyang Huang, Yongjian Yang, Yuanbo Xu, Funing Yang, Zhilu Yuan, Yongxiong Sun
Summary: Mobile signaling data has great value for urban traffic monitoring, improving coverage and accuracy.
Article
Transportation Science & Technology
Zhenning Li, Qiong Wu, Hao Yu, Cong Chen, Guohui Zhang, Zong Z. Tian, Panos D. Prevedouros
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2019)
Article
Transportation
Xiaowen Jiang, Peter J. Jin, Yizhou Wang
Summary: The article introduces a dynamic merge assistance method based on connected vehicles, which utilizes vehicle trajectory data to synchronize vehicle-gap pairing for improved mobility and safety in merging areas.
JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Engineering, Civil
Yuewen Yu, Shikun Liu, Peter J. Jin, Xia Luo, Mengxue Wang
TRANSPORTATION RESEARCH RECORD
(2020)
Article
Engineering, Civil
Saeed Vasebi, Yeganeh M. Hayeri, Peter J. Jin
Summary: Recent advancements in computational power and traffic data availability have allowed for a re-examination of drivers' car-following behavior. While classic models focus on the preceding vehicle, newer studies suggest that incorporating information from surrounding vehicles may improve performance. This study uses deep learning and long short-term memory models to explore the impact of surrounding vehicles on car-following performance. The results suggest that in this particular study, there were minimal differences in performance between classic models and those incorporating surrounding vehicle information.
TRANSPORTATION RESEARCH RECORD
(2021)
Article
Engineering, Civil
Fei Yang, Yanchen Wang, Peter J. Jin, Dingbang Li, Zhenxing Yao
Summary: Cellular phone data has been proven valuable in analyzing residents' travel patterns. This study proposes a random forest model for trip end identification using points of interest data, showing better performance compared to rule-based and clustering algorithms.
TRANSPORTATION RESEARCH RECORD
(2021)
Article
Engineering, Civil
Yi Ge, Peter J. Jin, Tianya Zhang, Jonathan Martinez
Summary: This paper explores the cloud- versus server-based deployment scenarios of an enhanced computer vision platform for potential deployment on low-resolution 511 traffic video streams. By enhancing existing algorithms and proposing new methods, the model shows promising performance in accuracy and computational efficiency for potential large-scale cloud deployment. Cost analysis reveals that cloud-based deployment is more convenient and cost-effective for on-demand network assessment, while dedicated-server-based deployment is more economical for long-term traffic detection deployment.
TRANSPORTATION RESEARCH RECORD
(2022)
Article
Transportation
Yudong Guo, Fei Yang, Peter Jing Jin, Haode Liu, Sai Ma, Zhenxing Yao
Summary: This paper proposes a vehicle path recognition model combined with mobile phone data, achieving high recognition accuracy of 90% and low error rate of 6% by combining fitting and recognition modules to smooth mobile phone data and match them to road networks.
TRANSPORTMETRICA A-TRANSPORT SCIENCE
(2022)
Article
Engineering, Civil
Tianya Zhang, Peter J. Jin, Yi Ge, Ryhan Moghe, Xiaowen Jiang
Summary: This study developed a vehicle detection and tracking method based on STMap, designed a novel deep-learning model that outperformed other models in various scenarios, and proposed a superior vehicle detection solution.
TRANSPORTATION RESEARCH RECORD
(2022)
Review
Economics
Da Yang, Bingmei Jia, Liyuan Dai, Jing Peter Jin, Lihua Xu, Fei Chen, Shiyu Zheng, Bin Ran
Summary: This paper focuses on the position decision problem of automated vehicles when exiting the freeway. The study proposes a model to find the optimal decision position that balances efficiency and safety. The results show that adjusting the speed of the automated vehicle can improve the success probability of exiting.
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2022)
Article
Engineering, Civil
Lilei Wang, Fei Yang, Peter J. Jin, Tao Zhou, Yudong Guo
Summary: This paper proposes a new method of using signaling positioning technology to identify and analyze individual travel characteristics. By matching the signaling data with the road network and using the wavelet transform modulus maximum algorithm to divide multimodal travel trajectories into single-mode trip segments, spatiotemporal information related to mode transfer can be obtained. An unsupervised fuzzy kernel c-means clustering algorithm is used to distinguish travel modes. The experimental results show that the method has high accuracy and effectiveness in identifying and analyzing travel characteristics.
TRANSPORTATION RESEARCH RECORD
(2022)
Article
Transportation Science & Technology
Yizhou Wang, Peter J. Jin
Summary: This paper proposes a new ACC and CACC framework that directly integrates the congestion shockwave damping and traffic congestion mitigation into the objective function of a dynamic control framework. Experimental studies indicate promising results of proposed models in reducing shockwave propagation speed and mitigating traffic congestion under different environments compared with existing ACC and CACC models.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2023)
Article
Engineering, Civil
Yi Ge, Peter J. Jin, Tianya T. Zhang, Anjiang Chen
Summary: This paper develops an assessment and optimization model for configuring roadside LiDAR installation, which can analyze the impact of detection blind zones on vehicle detection and tracking capabilities. Evaluation metrics are proposed to assess the severity of blind zones, and a simulation model is used to identify optimal configurations for different scenarios.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Tianya Terry Zhang, Peter J. Jin, Thomas M. Brennan Jr, Kelly McVeigh, Mohammad Jalayer, Deep Patel
Summary: This paper addresses the limitation of using existing detection and controller data to build performance metrics in the ATSPMs platform of signalized intersections. It presents a vehicle trajectory reconstruction algorithm based on shockwave theory to estimate advanced vehicle detections. The research utilizes existing data sources and provides a new coordination diagram to improve intersection performance measures.
JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS
(2023)
Article
Engineering, Civil
Tianya Terry Zhang, Peter J. J. Jin
Summary: This paper proposed the SiCK solution, which utilizes semantic segmentation for vehicle movement extraction, enabling high-resolution trajectory reconstruction and validation. The DMD method decomposes the STMap into sparse foreground and low-rank background to extract vehicle strands. By adapting two prevalent deep learning architectures, the Res-UNet+ neural networks significantly improved the performance of STMap-based vehicle detection and tracking. The solution is accurate and robust against various challenging factors, and addresses data quality issues through trajectory correction using computer vision tools. Extracting high-fidelity vehicle trajectories is a systematic process, and this framework greatly enhances the accuracy and reliability of video-based trajectory data acquisition.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Ergonomics
Rong Zou, Hanyi Yang, Wanxin Yu, Hao Yu, Cong Chen, Guohui Zhang, David T. Ma
Summary: Rear-end crashes are a significant cause of injuries and fatalities in traffic accidents. This study investigates the risk factors and heterogeneity in driver injury severity in rear-end crashes between passenger cars and light trucks. Using a latent class multinomial logit model, the study considers four crash configuration types and finds that the leading vehicle type and certain factors like road conditions, seatbelt usage, and driver age greatly influence the severity of driver injuries. The findings provide important insights for developing countermeasures and strategies to mitigate injury severity in rear-end crashes involving passenger cars and light trucks.
ACCIDENT ANALYSIS AND PREVENTION
(2023)
Article
Transportation Science & Technology
Yue Zhao, Liujiang Kang, Huijun Sun, Jianjun Wu, Nsabimana Buhigiro
Summary: This study proposes a 2-population 3-strategy evolutionary game model to address the issue of subway network operation extension. The analysis reveals that the rule of maximum total fitness ensures the priority of evolutionary equilibrium strategies, and proper adjustment minutes can enhance the effectiveness of operation extension.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Hongtao Hu, Jiao Mob, Lu Zhen
Summary: This study investigates the challenges of daily storage yard management in marine container terminals considering delayed transshipment of containers. A mixed-integer linear programming model is proposed to minimize various costs associated with transportation and yard management. The improved Benders decomposition algorithm is applied to solve the problem effectively and efficiently.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Zhandong Xu, Yiyang Peng, Guoyuan Li, Anthony Chen, Xiaobo Liu
Summary: This paper studied the impact of range anxiety among electric vehicle drivers on traffic assignment. Two types of range-constrained traffic assignment problems were defined based on discrete or continuous distributed range anxiety. Models and algorithms were proposed to solve the two types of problems. Experimental results showed the superiority of the proposed algorithm and revealed that drivers with heightened range anxiety may cause severe congestion.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Chuanjia Li, Maosi Geng, Yong Chen, Zeen Cai, Zheng Zhu, Xiqun (Michael) Chen
Summary: Understanding spatial-temporal stochasticity in shared mobility is crucial, and this study introduces the Bi-STTNP prediction model that provides probabilistic predictions and uncertainty estimations for ride-sourcing demand, outperforming conventional deep learning methods. The model captures the multivariate spatial-temporal Gaussian distribution of demand and offers comprehensive uncertainty representations.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Benjamin Coifman, Lizhe Li
Summary: This paper develops a partial trajectory method for aligning views from successive fixed cameras in order to ensure high fidelity with the actual vehicle movements. The method operates on the output of vehicle tracking to provide direct feedback and improve alignment quality. Experimental results show that this method can enhance accuracy and increase the number of vehicles in the dataset.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Mohsen Dastpak, Fausto Errico, Ola Jabali, Federico Malucelli
Summary: This article discusses the problem of an Electric Vehicle (EV) finding the shortest route from an origin to a destination and proposes a problem model that considers the occupancy indicator information of charging stations. A Markov Decision Process formulation is presented to optimize the EV routing and charging policy. A reoptimization algorithm is developed to establish the sequence of charging station visits and charging amounts based on system updates. Results from a comprehensive computational study show that the proposed method significantly reduces waiting times and total trip duration.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
