Article
Multidisciplinary Sciences
Christopher King, N. W. F. Bode
Summary: This study investigates pedestrian destination choice behavior through virtual experiments and finds that it is influenced by building layout, destination schedules, and environmental conditions. The results suggest that virtual experiments can elicit various destination choice behaviors, demonstrating the flexibility of this experimental paradigm.
ROYAL SOCIETY OPEN SCIENCE
(2022)
Article
Transportation
Weimeng Li, Shoufeng Ma, Ning Jia, Zhengbing He
Summary: This paper proposes an analyzable agent-based route choice modeling framework which allows heterogeneous individual learning rules and learning rates. The approximation for network flow distribution from the perspective of the stochastic process captures phenomena observed in laboratory experiments.
TRANSPORTMETRICA A-TRANSPORT SCIENCE
(2022)
Article
Economics
Hang Qi, Ning Jia, Xiaobo Qu, Zhengbing He
Summary: This study aims to bridge the gap between traffic dynamic theories and laboratory experiments in urban transportation networks. By conducting a series of experiments and observing unanticipated behavior regularities, the researchers propose a new dynamic model that incorporates these observations. The model improves the existing theories and provides a real behavioral basis for network equilibrium or DTD dynamic models.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2023)
Article
Transportation
Humberto Gonzalez Ramirez, Ludovic Leclercq, Nicolas Chiabaut, Cecile Becarie, Jean Krug
Summary: Recent empirical studies have shown that travelers tend to evaluate relative rather than absolute differences in travel time, with 60.5% choosing the fastest route when it is at least 30% faster than alternatives. Only 10% of individuals consistently chose the fastest route, indicating bounded rationality.
TRAVEL BEHAVIOUR AND SOCIETY
(2021)
Article
Computer Science, Interdisciplinary Applications
Jeroen Verstraete, Chris M. J. Tampere
Summary: This paper presents a general framework for the RC module of efficient stochastic DTA without the need for topological ordering, demonstrating smooth and consistent convergence. Computational modifications are necessary to ensure limited numerical errors and improve efficiency for practical use. The resulting ESDTA's computation time scales linearly with respect to all relevant complexity dimensions.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Engineering, Civil
Jihao Deng, Lei Gao, Xiaohong Chen, Quan Yuan
Summary: Traffic congestion is a major concern for policymakers in large cities worldwide. In order to combat congestion, individual-based active travel demand management (ATDM) has been proposed as a more efficient policy alternative. However, the factors influencing individuals' routing choices during commuting in response to ATDM incentives are still mostly unknown. By analyzing a desensitized one-week travel trajectory dataset of 5641 personal electric vehicles, this study identifies the major influencing factors of commuting route stability and provides suggestions for targeting responsive commuters. The findings contribute to the understanding of individual route choices and can help urban managers develop more refined ATDM policies to alleviate traffic congestion in the future.
Article
Transportation Science & Technology
Yunhe Tong, Nikolai W. F. Bode
Summary: This study introduces a mathematical model to investigate the decision-making processes in sequences of consecutive pedestrian route choices. It found that the sensitivity to environmental information diminishes as pedestrians make more sequential decisions, particularly when only information on the movement of others is available. The findings suggest that this diminishing sensitivity may lead to more predictable route choice dynamics across pedestrian crowds.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Physics, Multidisciplinary
Longyan Gong, Jinze Zha, Hongli Zeng, Zhengxin Wang, Xuechao Zhai
Summary: The study investigates the route-choice problem in two-route traffic systems with real-time particle densities provided. By considering different scenarios with informed and uninformed particles, along with different route-choice rules, the stability conditions and average travel times of different types of particles in various phases are analyzed. The results can be useful for optimizing traffic flow on traffic networks.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2021)
Article
Transportation
Yunhe Tong, Nikolai W. F. Bode
Summary: This study introduces a method based on spatial network theory for generating buildings with various layout properties, and conducts a virtual experiment to investigate the influence of layout properties on pedestrian route choice. The findings suggest that buildings with more connections and possible routes result in worse route recall for pedestrians, and pedestrians prefer more regular building layouts.
TRANSPORTMETRICA A-TRANSPORT SCIENCE
(2022)
Article
Physics, Multidisciplinary
X. Lu, H. Blanton, T. Gifford, A. Tucker, N. Olderman
Summary: Occupants in building fires often face difficulties evacuating safely, and providing guidance can assist them in choosing proper escape routes. This study demonstrates that optimized guidance is effective in alleviating congestion and improving evacuation efficiency, while also conducting a sensitivity analysis on the different impacts of psychological factors.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2021)
Article
Transportation
Si-Yang Wang, Ren-Yong Guo, Hai-Jun Huang
Summary: This paper investigates the impact of route choice set of networks on day-to-day traffic dynamics through experiments. Results show that networks with smaller route choice sets are more likely to reach a deterministic user equilibrium state. Three day-to-day models are calibrated using experimental data, revealing linear relationships and variations in model performance across different networks.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2021)
Article
Medicine, General & Internal
Colin G. Walsh, Kevin B. Johnson, Michael Ripperger, Sarah Sperry, Joyce Harris, Nathaniel Clark, Elliot Fielstein, Laurie Novak, Katelyn Robinson, William W. Stead
Summary: This study evaluated the performance of a suicide attempt risk prediction model implemented in clinical systems, showing reasonable numbers needed to screen and maintained performance across different demographic subgroups.
Article
Physics, Multidisciplinary
Claudio Meneguzzer
Summary: This study investigates the effects of contrarian behavior on the day-to-day evolution of a traffic system. The results show that a moderate proportion of contrarian choices can ensure system stability, and introducing memory and learning can counter the destabilizing effect of cost sensitivity. The study also finds that direct and contrarian travelers have the same mean travel cost within the stability region, but the minority group has a competitive advantage outside this region, albeit at the expense of deteriorated network performance.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
Article
Geography
Karl Rehrl, Stefan Kranzinger, Simon Groechenig
Summary: In the context of intelligent transport systems, dynamic route planning algorithms' performance and scalability have been widely studied, while the route qualities have been neglected. This research proposes a method to assess the quality of arbitrary routes based on seven spatio-temporal metrics, and demonstrates the usefulness of the approach through a cross-evaluation of route qualities in different dimensions. By matching route planning results to a reference digital road network and using reference travel times, the approach objectively evaluates the quality of dynamic routes.
TRANSACTIONS IN GIS
(2021)
Article
Biochemical Research Methods
Benedikt Haeusele, Maxim B. Gindele, Helmut Coelfen
Summary: Asymmetrical flow field-flow fractionation is a versatile method for size-based separation of colloids, biomolecules, and polymers, but there is no consensus on the correct data processing method. Different approaches and calibration algorithms were compared, indicating that current AF4 setups do not meet the requirements for absolute measurements of D.
JOURNAL OF CHROMATOGRAPHY A
(2021)
Article
Engineering, Civil
Wenbo Fan, Zhenkun Tang, Pengyao Ye, Feng Xiao, Jun Zhang
Summary: This paper proposes a deep learning-based dynamic traffic assignment (DTA) model using a convolutional neural network (CNN) to consider the spatial correlation of origin-destination (OD) pairs. The experiments show that the trained CNN-based DTA model outperforms other statistical/machine learning algorithms in terms of accuracy. It also exhibits robustness to data incompleteness, small-sized dataset, data noise, and network changes.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Dapeng Zhang, Feng Xiao, Gang Kou, Jian Luo, Fan Yang
Summary: Accurate and reliable taxi demand prediction is crucial for intelligent planning and management in the transportation system. Existing studies often overlook the local statistical differences throughout a city's geographical layout, limiting the accuracy improvement of prediction models. In this paper, we propose a new deep learning framework, LC-ST-FCN, that simultaneously learns the spatial-temporal correlations and local statistical differences among regions. Evaluation on a real dataset shows significant improvements compared to baseline models, and visualization results demonstrate the better localization and capture of spatial-related features.
JOURNAL OF ADVANCED TRANSPORTATION
(2023)
Article
Computer Science, Artificial Intelligence
Yun Wan, Feng Xiao, Dapeng Zhang
Summary: This paper proposes a framework for early phishing detection, dividing the phishing scams into three stages and developing a feature extraction method. Experimental results show that this method outperforms existing graph embedding methods on a real-world Ethereum transaction dataset. Additionally, the analysis of feature differences between phishing users and normal users provides useful insights for regulators and platforms.
Article
Computer Science, Artificial Intelligence
Xiao Yan, Gang Kou, Feng Xiao, Dapeng Zhang, Xianghua Gan
Summary: In this paper, the region-based demand forecasting problem in bike-sharing systems is studied, and a multiple spatiotemporal fusion network called MSTF-Net is proposed to address the challenge of extracting correlations among the fragments. MSTF-Net outperforms seven baseline models on bike-sharing datasets.
Article
Computer Science, Artificial Intelligence
Dapeng Zhang, Feng Xiao
Summary: Solving the demand prediction problem is crucial for enhancing the efficiency and reliability of ride-hailing services. Most existing studies focus on region-level demand prediction, neglecting the origin-destination (OD) demand prediction issue. This research proposes the Dynamic Auto-structuring Graph Neural Network (DAGNN) framework to address the OD demand prediction problem by developing a Dynamic Graph Decomposition and Recombination layer (DGDR) and learning graph representations from trainable and time-aware edge-induced subgraphs. Experimental results demonstrate the superior performance and efficiency of the proposed model compared to baseline models.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Economics
Yang Xia, Wenjia Zeng, Canrong Zhang, Hai Yang
Summary: This paper addresses the vehicle routing problem with load-dependent drones (VRPLD). A facility called the docking hub is introduced to enhance the collaboration between trucks and drones. A mixed-integer model is proposed, and a branch-and-price-and-cut algorithm is developed to solve the problem efficiently. The computational results demonstrate the effectiveness of the proposed algorithm compared to existing methods.
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2023)
Article
Economics
Hongxing Ding, Hai Yang, Hongli Xu, Ting Li
Summary: Based on the status quo-dependent route choice model in Xu et al. (2017), this study integrates the model into traffic assignment modeling and establishes a Status quo-dependent User Equilibrium (SDUE) model. The SDUE model considers cognitive limitations, satisficing behavior, inertial behavior, and variation in value of time (VOTs) in route choice behavior. The study also demonstrates that equilibrium solutions from previous UE models can be included in the SDUE solution set by varying VOTs among users and scenarios.
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2023)
Article
Transportation Science & Technology
Zheng Zhu, Meng Xu, Jintao Ke, Hai Yang, Xiqun (Michael) Chen
Summary: In this paper, a Bayesian clustering ensemble Gaussian process (BCEGP) model is proposed for network-wide traffic flow clustering and prediction. The model combines hard clustering and Gaussian process learning methods to effectively tackle limitations of machine learning models in traffic flow prediction, such as interpretability, generalization, and reliance on image data processing. Experimental results show that the BCEGP model performs well in predictive accuracy, computational speed, and applicability.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2023)
Article
Transportation Science & Technology
Yun Wang, Yu Zhou, Hai Yang, Xuedong Yan
Summary: This paper systematically investigates the bus bridging service design problem in urban rail transit, aiming to minimize operator and passenger costs while effectively addressing service disruptions. A column generation-based approach is proposed to quickly generate high-quality emergency response plans for public transit operators. Our method has been tested and proven effective in real case studies.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2023)
Article
Construction & Building Technology
Hao Tang, Juan Yu, Borong Lin, Yang Geng, Zhe Wang, Xi Chen, Li Yang, Tianshu Lin, Feng Xiao
Summary: Passengers have a significant impact on airport terminal energy consumption and indoor environmental quality. Accurate passenger forecasting is crucial for optimizing the operation and management of airport terminals. However, the COVID-19 pandemic has increased uncertainty in airport passenger trends. There is a lack of research on which pandemic-related variables should be considered in forecasting airport passenger trends under the impact of COVID-19 outbreaks.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Economics
Yue Bao, Hai Yang, Ziyou Gao, Hongli Xu
Summary: This study investigates the impact of pre-event activities on attendees' departure-time choices and traffic congestion near a venue. A bottleneck model is proposed to analyze the heterogeneous pre-event utility of attendees, considering the attractiveness of the venue. Different distributions of pre-event utility sensitivity are used to analyze the equilibrium at the bottleneck and determine the conditions to eliminate queues. The study also examines the impact of venue attractiveness on attendees' pre-event utility sensitivity and determines optimal pricing and facility levels to maximize venue profit and attendees' trip utilities.
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2023)
Article
Economics
Xiaoshu Ding, Qi Qi, Sisi Jian, Hai Yang
Summary: Mobility-as-a-Service (MaaS) is a new transport model that offers multiple travel modes through a single platform. The MaaS operator acts as a middleman, purchasing resources from different service providers and offering seamless transport services to meet travelers' needs. The challenge lies in matching travelers to providers, ensuring profitability for the providers and efficiency for the system.
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2023)
Article
Transportation Science & Technology
Minyu Shen, Weihua Gu, Sangen Hu, Feng Xiao
Summary: This paper proposes a simple heuristic method and a cluster-based nested partition algorithm for berth allocation at bus stops. The methods do not rely on complex simulation models or extensive input data, and can generate near-optimal berth allocation plans with lower computational cost and shorter time.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2023)
Article
Transportation Science & Technology
Kehua Chen, Jindong Han, Siyuan Feng, Meixin Zhu, Hai Yang
Summary: This article studies the issue of driver profiling in ride-hailing services and proposes a Hierarchical Graph Contrastive Learning (HGCL) framework that automatically learns low-dimensional embeddings from raw GPS data to encode driver behaviors. Experimental results demonstrate the efficacy of the proposed framework in driver profiling.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2023)
Article
Environmental Studies
Shaopeng Zhong, Ao Liu, Yu Jiang, Simon Hu, Feng Xiao, Hai-Jun Huang, Yan Song
Summary: This study analyzes the long-term effects of shared autonomous vehicles (SAVs) from the perspective of land use and transportation integration. Different SAV pricing scenarios are developed to explore the optimal pricing strategy for low carbon-oriented SAVs. Moreover, the study assesses the effect of vehicle electrification on vehicle emissions and energy consumption. The results show a significant reduction in PM2.5 emissions and energy consumption under an appropriate pricing strategy for SAVs, with further improvements achievable through vehicle electrification.
NPJ URBAN SUSTAINABILITY
(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)
