Research Output

@article{LIU2024103997,

title = {Electrification pathways for public transport systems},

author = {Kai Liu and Tao Feng and Toshiyuki Yamamoto and Ziqi Song},

url = {https://www.sciencedirect.com/science/article/pii/S1361920923003942},

doi = {https://doi.org/10.1016/j.trd.2023.103997},

issn = {1361-9209},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Transportation Research Part D: Transport and Environment},

volume = {126},

pages = {103997},

keywords = {Editorial note, Electric mobility},

pubstate = {published},

tppubtype = {article}

}

@article{LIU2024102078,

title = {RT-GCN: Gaussian-based spatiotemporal graph convolutional network for robust traffic prediction},

author = {Yutian Liu and Soora Rasouli and Melvin Wong and Tao Feng and Tianjin Huang},

url = {https://www.sciencedirect.com/science/article/pii/S1566253523003949},

doi = {https://doi.org/10.1016/j.inffus.2023.102078},

issn = {1566-2535},

year  = {2024},

date = {2024-01-01},

journal = {Information Fusion},

volume = {102},

pages = {102078},

abstract = {Traffic forecasting plays a critical role in intelligent transportation systems (ITS) in smart cities. Travelers as well as urban managers rely on reliable traffic information to make their decisions for route choice and traffic management. However, noisy or missing traffic data poses a problem for accurate and robust traffic forecasting. While data-driven models such as deep neural networks can achieve high prediction accuracy with complete datasets, sensor malfunctions, and environmental effects degrade the performance of such models, as these models rely heavily on precise traffic measurements for model training and estimation. Consequently, incomplete traffic data poses a challenge for robust model design that can make accurate traffic forecasts with noisy/missing data. This research proposes the Robust Spatiotemporal Graph Convolutional Network (RT-GCN), a traffic prediction model that handles noise perturbations and missing data using a Gaussian distributed node representation and a variance based attention mechanism. Through experiments conducted on four real-world traffic datasets using diverse noisy and missing scenarios, the proposed RT-GCN model has demonstrated its ability to handle noise perturbations and missing values and provide high accuracy prediction.},

keywords = {Gaussian distribution, Graph convolutional network, Missing data, Robustness, Traffic prediction},

pubstate = {published},

tppubtype = {article}

}

@article{WANG2024129667,

title = {Modelling the dual dynamic traffic flow evolution with information perception differences between human-driven vehicles and connected autonomous vehicles},

author = {Guanfeng Wang and Hongfei Jia and Tao Feng and Jingjing Tian and Ruiyi Wu and Heyao Gao and Chao Liu},

url = {https://www.sciencedirect.com/science/article/pii/S0378437124001766},

doi = {https://doi.org/10.1016/j.physa.2024.129667},

issn = {0378-4371},

year  = {2024},

date = {2024-01-01},

journal = {Physica A: Statistical Mechanics and its Applications},

volume = {640},

pages = {129667},

abstract = {The introduction of connected autonomous vehicles (CAVs) potentially improves the link capacity and backward wave speed of traffic flow, while the advanced communication technology could well make it possible to allow CAV users to share their travel information. To bridge the knowledge gaps in the network evolution under mixed environment of human-driven vehicles (HVs) and CAVs, it is essential to explore multi-dimensional dynamic traffic assignment. An inertia-based multi-class dual dynamic traffic assignment (IMDDTA) model is proposed to capture the intraday and diurnal variations of the mixed traffic flow under the disequilibrium state simultaneously. Specifically, in this study we consider the inertia of HV users as well the information-sharing behaviour of CAV users respectively, characterized by different extensions of the multinomial logit (MNL) model. To demonstrate the properties of the model, two numerical case studies are conducted based on the Braess network and the Sioux Falls network. The results indicate an acceptable validity and applicability of the model and provide valuable insights on the evolution of traffic flow under mixed environment.},

keywords = {Connected autonomous vehicles, Dual dynamic traffic assignment, Inertial route choice behaviour, Information-sharing, Mixed traffic flow},

pubstate = {published},

tppubtype = {article}

}

@article{GU2024129666,

title = {A novel regional traffic control strategy for mixed traffic system with the construction of congestion warning communities},

author = {Xiaoning Gu and Chao Chen and Tao Feng and Baozhen Yao},

url = {https://www.sciencedirect.com/science/article/pii/S0378437124001754},

doi = {https://doi.org/10.1016/j.physa.2024.129666},

issn = {0378-4371},

year  = {2024},

date = {2024-01-01},

journal = {Physica A: Statistical Mechanics and its Applications},

volume = {639},

pages = {129666},

abstract = {Large-scale congestion can lead to traffic paralysis, which severely hampers the flow of vehicles and disrupts the normal functioning of urban traffic. Traffic optimization strategies can effectively improve the performance of road networks, but often ignore the impact of regional traffic conditions and equity. This paper presents a novel traffic strategy to solve regional traffic congestion in large cities, particularly focusing on mixed traffic scenarios of connected and non-connected vehicles. The proposed method involves monitoring the traffic condition of the congestion warning community and adjusting the internal access flow within each region. The problem is formulated as a Stackelberg game, with traffic policymakers and road users as the key players. The upper layer aims to control traffic access by issuing a community warning index, with the objective of minimizing congestion warning conditions within the community. This information is then disseminated to connected vehicles which utilize it to generate personalized route guidance, while non-connected vehicles remain unaffected. The lower-level objective is to allocate vehicles in the transportation network in a user-optimal manner. To solve the bi-level programming model, the paper introduces a variable neighborhood search approach based on graph theory. The Frank-Wolfe algorithm is used to solve the lower-level model, with a penalty function introduced to transform the constrained traffic assignment problem (TAP) into an unconstrained TAP. The proposed method is applied using the data of Beijing urban road network and a sensitivity analysis is conducted to examine the impacts of critical parameters, such as regional partitioning and mixed traffic proportion. The results show that the method exhibits improved optimization performance across different parameter settings, effectively utilizing idle links and contributing to a reduction in the occurrence of traffic warning regions.},

keywords = {Bi-level programming model, Congestion warning, Stackelberg game, Traffic access restriction, Urban traffic control},

pubstate = {published},

tppubtype = {article}

}

@article{land13040519,

title = {Effects of Urban Parks on Housing Prices in the Post-COVID-19 Pandemic Era in China},

author = {Xinxing Yang and Qiang Ye and You Peng and Shaobo Liu and Tao Feng},

url = {https://www.mdpi.com/2073-445X/13/4/519},

doi = {10.3390/land13040519},

issn = {2073-445X},

year  = {2024},

date = {2024-01-01},

journal = {Land},

volume = {13},

number = {4},

abstract = {Urban parks are important for improving the quality of living environments. Although the impact of parks on housing prices has been well documented, the effects of the COVID-19 pandemic remain vague. This paper analyzes the housing prices of neighborhoods around Meixi Lake park in Changsha, at the initial stage of the COVID-19 pandemic in June 2020 and the stable stage of the recovery period in June 2023, which demonstrates the impacts of urban parks on property pricing and housing choice based on residential transaction data. The results indicate that urban parks are given a high priority in determining people’s choices. In June 2020, the risk of epidemic transmission and noise interference lowered the price of property that is close to public parks and recreational facilities. However, good management and social services in residential areas increase housing prices. However, when the pandemic ended, the strong demand for outdoor activities led to a price rise in the properties near Meixi Lake park. People are most likely to choose houses in a neighborhood characterized by good educational facilities and a high-quality living environment. More specially, the houses with a short distance to parks and where residents can enjoy the view of a lake or mountains are preferable to any others. A residential area adjacent to a super large park paired with a small park is the most valuable consideration for property developers and housing consumers.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{HAN2024142192,

title = {Study on window-opening behavior of suburban sustainable life-pattern in residential buildings at Donglu town of Hezhou, China},

author = {Jie Han and Nan Mo and Jingyi Cai and Xinyue Li and Fuhao Xie and You Peng and Tao Feng},

url = {https://www.sciencedirect.com/science/article/pii/S0959652624016408},

doi = {https://doi.org/10.1016/j.jclepro.2024.142192},

issn = {0959-6526},

year  = {2024},

date = {2024-01-01},

journal = {Journal of Cleaner Production},

volume = {452},

pages = {142192},

abstract = {Window opening behavior is a crucial determinant of indoor thermal comfort and air quality. It plays an important role in accurate building performance simulations when it comes to regional contexts of climate. Few studies on window opening behavior have been carried out in suburban regions where window opening, as an adaptative adjustment, is more prevalent than in urban areas. To bridge this gap, this study based on questionnaire surveys and on-site measurements investigates the window opening behavior of suburban residents in bedrooms during the transitional season in Donglu town, China. The results indicate the duration of window opening exhibits a strong correlation with suburban residents' habits and occupations. The suburban residents tend to close their bedrooms' windows when leaving home, while they prefer opening them before going to sleep. A logistic regression model was developed for suburban household to predict the probability of window opening behavior. It has been evidenced that outdoor and indoor humidity, outdoor temperature, time periods and solar radiation intensity are strongly influencing on suburban residents' window opening and closing behaviors. In addition, due to the influence of continuous humid weather in transitional seasons, outdoor humidity is the principal factor that prompts residents to close their windows. Our findings contribute to further achieving novel knowledge on occupants’ interaction with suburban residential buildings.},

keywords = {Logistic regression, Suburban residential buildings, Transition season, Window opening behavior},

pubstate = {published},

tppubtype = {article}

}

@article{WU2024103876,

title = {Spatial allocation of heavy commercial vehicles parking areas through geo-fencing},

author = {Jishi Wu and Tao Feng and Peng Jia and Gen Li},

url = {https://www.sciencedirect.com/science/article/pii/S0966692324000851},

doi = {https://doi.org/10.1016/j.jtrangeo.2024.103876},

issn = {0966-6923},

year  = {2024},

date = {2024-01-01},

journal = {Journal of Transport Geography},

volume = {117},

pages = {103876},

abstract = {Inadequate parking planning for heavy commercial vehicles (HCV) exacerbates urban road congestion. As an effective means of parking management, geofencing that identifies the virtual boundary for geographic areas is essential to ensure these vehicles do not impede traffic and urban spaces. However, geofenced areas must be rationally designed to prevent mismatches between parking areas and real parking needs. This paper presents a data-driven approach that integrates the Spatial-temporal Density-Based Spatial Clustering of Applications with Noise (ST-DBSCAN) methods and a Gaussian mixture model for identifying and predicting potential parking areas for HCVs. Leveraging the HCV trajectory data and land use data in Shanghai, China, we characterize the spatial distribution of parking demand and create a probabilistic model to predict active HCV traffic patterns and the spatial confidence regions under varying land use conditions. The results show that clusters of HCV parking demand tend to congregate near ports, comprehensive transportation hubs, logistics centers, and commercial hubs. These clusters correspond to five distinct parking demand patterns (i.e., day-long HCV stops, morning peak time HCV stops, daytime HCV stops, afternoon peak time HCV stops, and nighttime HCV stops), each reflecting specific spatiotemporal characteristics. The geofenced spatial domain was found to be very sensitive to the timing of parking, emphasizing the importance of using advanced geofencing technologies. The methodological framework introduced in this study holds significant value for policymakers and HCV operators as it aids in determining parking at strategic levels, offering valuable insights and tools to enhance the effectiveness of parking management.},

keywords = {Commercial vehicles parking management, Gaussian mixture model, Geo-fenced parking area, ST-DBSCAN clustering},

pubstate = {published},

tppubtype = {article}

}

@article{Liu2023,

title = {The Effect of Crowdsourced Police Enforcement Data on Traffic Speed: A Case Study of The Netherlands},

author = {Yutian Liu and Tao Feng},

doi = {10.3390/app132111822},

issn = {2076-3417},

year  = {2023},

date = {2023-10-29},

journal = {Applied Sciences},

volume = {13},

number = {21},

publisher = {MDPI AG},

abstract = {<jats:p>The proliferation of smartphones and internet connectivity has provided the opportunity to use crowdsourced data in traffic management. Nowadays, many people use navigation apps such as Google Maps, Waze, and Flitsmeister to obtain real-time travel information and provide feedback on road conditions, such as reporting police speed checks. As an accurate traffic speed prediction is of great significance for road users and traffic managers, different models have been proposed and widely used to predict traffic speed considering the spatio-temporal dependence of traffic data and external factors such as the weather, accidents and points of interest. This study investigates the impact of crowdsourced data about police enforcement from navigation apps on traffic speed. In addition, we examine whether the police enforcement report affects the accuracy of the deep learning prediction model. The authors extract crowdsourced police enforcement information from navigation apps, collect the corresponding historical traffic speed data, and predict traffic speed in several corridors in The Netherlands using a GCN-GRU traffic speed prediction model. The results show that the crowdsourced data for police enforcement cause the average vehicle speed to drop between 1 [km/h] and 3 [km/h] when passing the road segments marked with police activity. Moreover, the prediction performance of the GCN-GRU model during the periods without police enforcement is better than the periods with reported police activity, showing that police speed check reports can decrease the accuracy of speed prediction models.</jats:p>},

keywords = {Computer Science Applications, Fluid Flow and Transfer Processes, General Engineering, General Materials Science, Instrumentation, Process Chemistry and Technology},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {New Classification Scheme and Evolution Characteristics Analysis of High-Speed Railway Stations Using Large-Scale Mobile Phone Data: A Case Study in Jiangsu, China},

author = {Yue, Yifan and Chen, Jun and Feng, Tao and Wang, Wei and Wang, Chunyang and Ma, Xinwei},

url = {https://ascelibrary.org/doi/abs/10.1061/JTEPBS.TEENG-7855},

doi = {https://doi.org/10.1061/JTEPBS.TEENG-7855},

year  = {2023},

date = {2023-09-06},

urldate = {2023-09-06},

journal = {Journal of Transportation Engineering, Part A: Systems},

volume = {149},

issue = {11},

abstract = {Effective management of the high-speed railways (HSR) system requires an in-depth understanding of the HSR stations in the network, e.g., the time-dependent volume distribution. The classification of HSR stations is the scientific basis for transport policymaking and land-use planning. Existing classification methods cannot meet the needs of temporal variation of passenger flow or the refined design and operation of HSR stations. This study adopts the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to classify HSR stations in different years. Using the data of Jiangsu Province, China, as an example, the time series of arrival and departure passenger flow at HSR stations are clustered via the DBSCAN algorithm, and the HSR stations are clustered into three classes. To determine the hierarchical structure of HSR stations representing the evolution of HSR networks, we use large-scale panel data obtained from mobile phone cellular data across years (July 1–14 from each of the years 2018, 2020, and 2021) to capture and analyze the spatial-temporal evolution characteristics of massive passenger flow at HSR stations. It is indicated that both HSR station hierarchy and passenger flow have the characteristics of spatial-temporal evolution across years, and the classification results are influenced by the geographical positions of cities and HSR layout. Accurate clustering of HSR stations via large-scale actual passenger flow data enables railway authorities and operators to identify critical nodes for efficient HSR network performance. The resulting classification would contribute to an in-depth understanding of the evolution characteristics of passenger flow in different years.},

keywords = {Big data, classification algorithm, High-Speed Rail Station},

pubstate = {published},

tppubtype = {article}

}

@article{PCOVID19202301,

title = {Assessing the Impacts of Stay-in-Place Policy of COVID-19 Pandemic during the Chinese Spring Festival: A Stated Preference Approach},

author = {Xiaofeng Pan and Tao Feng and Yanyi Chen},

url = {https://downloads.hindawi.com/journals/jat/2023/9662990.pdf},

doi = {https://doi.org/10.1155/2023/9662990},

year  = {2023},

date = {2023-01-17},

urldate = {2023-01-17},

journal = {Journal of Advanced Transportation},

volume = {2023},

number = {9662990},

abstract = {This paper aims to investigate Chinese people’s willingness to stay in the city where they work when the Spring Festival meets the COVID-19 pandemic. Specifically, a stated choice experiment about intercity travel including three homecoming trips (i.e., trips carried by conventional railway, high-speed railways, and private car) and the option “stay in place” was designed. Respondents were requested to choose the most preferred alternative in the context of the current situation of the COVID-19 pandemic and relevant policies. Based on the data collected from 800 respondents, a latent class mixed logit model was developed and estimated to capture the potential correlations within alternatives and respondents and the preference heterogeneity between respondents. Two latent classes were identified, one of which paid more attention to epidemic prevention policies while the other cared more about the characteristics of homecoming trips. Results show that people’s willingness to stay in the city of work is largely dependent on epidemic prevention policies in their hometowns and decisions of social network members.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ZHU2023,

title = {An information model for highway operational risk management based on the IFC-Brick schema},

author = {Bencheng Zhu and Fujin Hou and Tao Feng and Tao Li and Cancan Song},

url = {https://www.sciencedirect.com/science/article/pii/S2046043022001046},

doi = {https://doi.org/10.1016/j.ijtst.2022.12.004},

issn = {2046-0430},

year  = {2023},

date = {2023-01-01},

journal = {International Journal of Transportation Science and Technology},

abstract = {With the development of highways, new technologies should be continuously introduced to improve highway traffic safety. Digital twin (DT) has been an emerging field of research in recent years. To develop a digital twin management system, a data model is essential. In the field of highway operational risk management (HORM), however, the development of data models is still in its infancy. Motivated by the concept of linked data, in this paper, we attempt to propose an information model for HORM. The main achievements of this paper include data architecture, identification and classification code methods, data interaction method, and the developed system. Based on data needs analysis, the highway information model architecture for risk management is defined as five layers: basic highway products, traffic sensors and equipment, traffic rules, traffic flow, and weather. Furthermore, according to the concepts of semantic data, these five layers can be classified into three categories: highway product data, topology data, and sensor data. Although the Industry Foundation Classes (IFC) standard and Brick schema were first proposed and applied in the building domain, some of their entities and relationships can also be applied to highways. To this end, we defined some new classes, a specific ontology, and an integrated framework for HORM. Finally, a case study was carried out. Applying such information model to highways has broad potential. It changes the file-based exchange method to the data-based one, which can promote highway data exchange and applications. The proposed information model could be of great significance for HORM.},

keywords = {Digital Twin, Highway, IFC-Brick, Information Model, Operational Risk Management},

pubstate = {published},

tppubtype = {article}

}

@article{YAN2023103585,

title = {A model of household shared parking decisions incorporating equity-seeking household dynamics and leadership personality traits},

author = {Qianqian Yan and Tao Feng and Harry Timmermans},

url = {https://www.sciencedirect.com/science/article/pii/S0965856423000058},

doi = {https://doi.org/10.1016/j.tra.2023.103585},

issn = {0965-8564},

year  = {2023},

date = {2023-01-01},

journal = {Transportation Research Part A: Policy and Practice},

volume = {169},

pages = {103585},

abstract = {Shared parking is viewed increasingly important as a way to alleviate parking problems in urban areas. To maximize the effect of shared parking initiatives, it is critical to understand the decision of households to share private parking spaces. Current models of household decision-making fail to adequately address equity seeking/avoiding household dynamics, which may negatively affect model validity. In this study, a model, which overcomes this theoretical concern, is introduced and estimated to understand the household shared parking participation decision. Specifically, the concept of leadership personality is used, jointly with individual and household characteristics, to specify the decision weight of each spouse of a couple. A choice experiment, in which individual members of couples first answer the choice questions individually and independently, and then jointly complete the choice questions, is designed to estimate the model. Estimation results, based on data collected in Qingdao, China, support the proposed model. Results show that intra-household interactions influence the households’ shared parking participation decision and that households favor alternatives that provide higher equality. Age, leadership personality, household structure, and household financial management are significantly related to household member decision weights.},

keywords = {Household decision-making, Intra-household interaction, Leadership personality, Shared parking},

pubstate = {published},

tppubtype = {article}

}

@article{Zhang2023,

title = {Association rules and prediction of transportation mode choice: Application to national travel survey data},

author = {Jiajia Zhang and Tao Feng and Harry J. P. Timmermans and Zhengkui Lin},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85149871014&doi=10.1016%2fj.trc.2023.104086&partnerID=40&md5=eb1a8d77d53861b16c1a4c1b421b0ef9},

doi = {10.1016/j.trc.2023.104086},

issn = {0968090X},

year  = {2023},

date = {2023-01-01},

journal = {Transportation Research Part C: Emerging Technologies},

volume = {150},

publisher = {Elsevier Ltd},

abstract = {Predicting transportation mode choice is a classic challenge of travel behavior research. Over the years, different theoretical concepts and modeling approaches have been applied. This paper elaborates the application of class association rules (CARs) and examines their predictive performance using data extracted from the 2015 National Dutch Travel Survey. To solve the problem how to activate rules that have high confidence but low support, the information gain (IG) concept is introduced in the model building process. The modeling process in this study first involves extracting frequent items from the data using the FP-Growth algorithm and deriving CARs from these frequent items. Next, the IG statistic is used to construct a novel model (named CARIG), which consists of a set of decision rules that formally represent behavioral scripts, for predicting individuals’ transportation mode choice. The performance of CARIG is compared with the performance of conventional class-based association rules (CBA), decision trees (DT), a convolutional neural network (CNN) and a logistic regression (LR) model. In addition, a 10-fold cross validation test using a grid search parameter optimization method is conducted to validate the proposed approach. The results show that the proposed method is promising in predicting transportation mode choices observed in the national travel survey data. © 2023 Elsevier Ltd},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Wu2023,

title = {Uncovering the spatiotemporal impacts of built environment on traffic carbon emissions using multi-source big data},

author = {Jishi Wu and Peng Jia and Tao Feng and Haijiang Li and Haibo Kuang and Junyi Zhang},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85149753704&doi=10.1016%2fj.landusepol.2023.106621&partnerID=40&md5=7e2bd842748fc814c1130a305a79b385},

doi = {10.1016/j.landusepol.2023.106621},

issn = {02648377},

year  = {2023},

date = {2023-01-01},

journal = {Land Use Policy},

volume = {129},

publisher = {Elsevier Ltd},

abstract = {Understanding and predicting urban traffic carbon emissions constitute an urgent agenda in research and policy decision-making. Since the exhausted emissions vary in time and different urban settings, assessing the spatiotemporal distribution of carbon emissions is fundamentally important for land use planning. This paper attempts to identify the spatial and temporal heterogeneity of the impacts of land use and built environment on urban traffic carbon emissions. A spatial standard deviational ellipse (SDE) model and a geographically and temporally weighted regression (GTWR) model were developed to explore the spatiotemporal dependency of traffic carbon emissions on land use and built environment factors and applied to the core urban zones of Dalian, China. Results show the center of gravity of traffic carbon emissions have a footprint characterized by a shift to the southeast first and then to the northwest, with weekday and weekend performance being consistent. Compared to other periods, emissions are spatially agglomerated during internal hours (9:00–15:59), especially during weekdays. Land use and built environment factors affect carbon emissions differently across space and time whereas the effects of residential population density, employment density, medical, road network density on weekdays are larger than that on weekends. Furthermore, we found that increasing land use mix leads to a greater negative impact on weekday emissions. This supplements the important role of mixed land use planning in decarbonization. Based on the findings, we propose various policy interventions to support the development of carbon neutral cities. © 2023 Elsevier Ltd},

note = {Cited by: 0},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rs15082075,

title = {Driving Mechanism of Differentiation in Urban Thermal Environment during Rapid Urbanization},

author = {Yifeng Ji and You Peng and Zhitao Li and Jiang Li and Shaobo Liu and Xiaoxi Cai and Yicheng Yin and Tao Feng},

url = {https://www.mdpi.com/2072-4292/15/8/2075},

doi = {10.3390/rs15082075},

issn = {2072-4292},

year  = {2023},

date = {2023-01-01},

journal = {Remote Sensing},

volume = {15},

number = {8},

abstract = {To achieve sustainable urban development, it is essential to gain insight into the spatial and temporal differentiation characteristics and the driving mechanisms of the urban thermal environment (UTE). As urbanization continues to accelerate, human activity and landscape configuration and composition interact to complicate the UTE. However, the differences in UTE-driven mechanisms at different stages of urbanization remain unclear. In this study, the UTE of Shenyang was measured quantitatively by using the land surface temperature (LST). The spatial and temporal differentiation characteristics were chronologically studied using the standard deviation ellipse (SDE) and hotspot analysis (Getis-Ord Gi*). Then, the relationship between human activities, landscape composition and landscape configuration and LST was explored in a hierarchical manner by applying the geographical detector. The results show that the UTE in Shenyang continues to deteriorate with rapid urbanization, with significant spatial and temporal differentiation characteristics. The class-level landscape configuration is more important than that at the landscape level when studying UTE-driven mechanisms. At the class level, the increased area and abundance of cropland can effectively reduce LST, while those of impervious surfaces can increase LST. At the landscape level, LST is mainly influenced by landscape composition and human activities. Due to rapid urbanization, the nonlinear relationship between most drivers and LST shifts to near-linear. In the later stage of urbanization, more attention needs to be paid to the effect of the interaction of drivers on LST. At the class level, the interaction between landscape configuration indices for impervious surfaces, cropland and water significantly influenced LST. At the landscape level, the interactions among the normalized difference building index (NDBI) and other selected factors are significant. The findings of this study can contribute to the development of urban planning strategies to optimize the UTE for different stages of urbanization.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{HAN2023113035,

title = {Research on the influence of courtyard space layout on building microclimate and its optimal design},

author = {Jie Han and Xinyue Li and Beiyu Li and Wei Yang and Wei Yin and You Peng and Tao Feng},

url = {https://www.sciencedirect.com/science/article/pii/S0378778823002657},

doi = {https://doi.org/10.1016/j.enbuild.2023.113035},

issn = {0378-7788},

year  = {2023},

date = {2023-01-01},

journal = {Energy and Buildings},

volume = {289},

pages = {113035},

abstract = {The inner courtyard is an important transition space for mass exchange and heat transfer between the internal space of courtyard buildings and the external environment. A good layout of courtyard space is conducive to building energy efficiency and human thermal comfort. In the paper, we analyze the impacts of different design schemes of the spatial layout on the microclimate of inner courtyard space using field measurements and numerical simulation methods. The analysis of the measured data presents the main meteorological factors affecting the thermal comfort of the courtyard. The magnitude of the effects is ranked as air temperature, total solar radiation intensity, near-surface air flow rate, and relative humidity. Results of the ENVI-met simulation show that changing the cover of different underlying surface types leads to different microclimate regulation effects in the sense that the temperature and relative humidity in summer drops up to 3.53 °C and 15.59%, respectively and in winter increase up to 3.97 °C and 37.21%, respectively. This paper proposes that lawn ground, marble ground, water surface and landscape tree coverage of 25%, 25%, 50% and 75%, respectively, are suitable design schemes for the inner courtyard space of library.},

keywords = {Adaptive thermal comfort, Courtyard space, ENVI-met, Patio microclimate},

pubstate = {published},

tppubtype = {article}

}

@article{XIA2023109284,

title = {Research on safety and efficiency warranted vessel scheduling in unidirectional multi-junction waterways of port waters},

author = {Zicheng Xia and Tao Feng and Zijian Guo and Ying Jiang and Wenyuan Wang},

url = {https://www.sciencedirect.com/science/article/pii/S036083522300308X},

doi = {https://doi.org/10.1016/j.cie.2023.109284},

issn = {0360-8352},

year  = {2023},

date = {2023-01-01},

journal = {Computers & Industrial Engineering},

pages = {109284},

abstract = {Traffic management in port waters is a complicated task considering vessels with various characteristics and the specific layout of waterways. Optimal management is needed to reduce vessel waiting time and guarantee adequate safety, which in turn could enhance port competitiveness, and is conducive to port development. In this paper, a key collision avoidance point precomputation model is proposed to assess the safety level of each vessel scheduling plan and the consequent efficiency in unidirectional multi-junction waterways of port waters. An integrated vessel scheduling approach (IVSA) is proposed and developed to obtain the safety-enabled optimal vessel scheduling with the purpose to minimize the total delay under the premise of adequate safety. A series of experiments has been conducted by employing data of an empirical port in northern China. It is found that, in addition to improving traffic environment and reducing unnecessary behavior of vessels, IVSA could substantially reduce the total delay, from 6.04% to 27.75%. Result of this research can provide a guidance for port seaside management under complex situations and provide the decision-making support for the assessment of vessel traffic on future port waterway expansion.},

keywords = {Diversity speed, Traffic scheduling, Unidirectional multi-junction waterway, Vessel safety},

pubstate = {published},

tppubtype = {article}

}

@article{YUE2023104640,

title = {Classification and Determinants of High-Speed Rail Stations Using Multi-Source Data: A Case Study in Jiangsu Province, China},

author = {Yifan Yue and Jun Chen and Tao Feng and Xinwei Ma and Wei Wang and Hua Bai},

url = {https://www.sciencedirect.com/science/article/pii/S2210670723002512},

doi = {https://doi.org/10.1016/j.scs.2023.104640},

issn = {2210-6707},

year  = {2023},

date = {2023-01-01},

journal = {Sustainable Cities and Society},

pages = {104640},

abstract = {High-speed rail (HSR) stations play a vital role in the HSR system. HSR stations not only facilitate the accessibility of interregional transportation but also stimulate population movements across various cities in China. HSR stations in different cities can vary greatly, and an efficient HSR system requires an in-depth understanding of the interrelations between the related influential factors and spatiotemporal passenger flow patterns of different HSR stations. This study adopts a new scheme for clustering HSR stations based on passengers' arrival and departure time series using mobile phone data in Jiangsu, China. To this end, 71 HSR stations are clustered into 3 classes and the spatiotemporal characteristics of passenger flow at different stations are compared. Finally, a geographically weighted multinomial logit model (GWMNL) is built to explore the influence of the built environment, socioeconomic indicators, and HSR station attributes on the classification results of HSR stations related to the time-varying characteristics of passenger flow. The model results show that the number of entertainment POIs, population, population density, area, GDP and building area are significantly associated with the classification results of HSR stations. Additionally, for HSR stations under the same classification result, these variables also have different effects on them in the geographical dimension. According to these findings, quantitative analysis of the linkages between the passenger flow patterns at different HSR stations and the impacting factors would offer implications for planners and policymakers in HSR station planning and associated urban development.},

keywords = {Built environment, Geographically Weighted Multinomial Logit Model, High-Speed Rail Station, Influential factors, Mobile Phone Data},

pubstate = {published},

tppubtype = {article}

}

@article{TIAN2023103763,

title = {Where to park an autonomous vehicle? Results of a stated choice experiment},

author = {Zhihui Tian and Tao Feng and Baozhen Yao and Yan Hu and Jing Zhang},

url = {https://www.sciencedirect.com/science/article/pii/S0965856423001830},

doi = {https://doi.org/10.1016/j.tra.2023.103763},

issn = {0965-8564},

year  = {2023},

date = {2023-01-01},

journal = {Transportation Research Part A: Policy and Practice},

volume = {175},

pages = {103763},

abstract = {The future innovation and growing popularity of autonomous vehicles have the potential to significantly impact the spatiotemporal distribution of parking demand. However, little knowledge is gained on how people will choose to park their autonomous cars. In principle, an autonomous vehicle is not necessarily parked close by like traditional vehicles leveraging the automated driving and parking capability, still, the decision made by people is important for policymakers in urban and transportation planning. This study attempts to gain useful insights to understand people’s parking location choices for autonomous vehicles. A stated choice experiment was designed, allowing people to choose a parking location for autonomous vehicles in varied contexts, including time windows, picking-up times, and the requirement for on-time arrival at the next activity. We found that similar to conventional cars people generally prefer cheaper and/or closer parking lots for autonomous vehicles. However, the distance between a parking lot and the activity location is relatively longer in the case of autonomous vehicles. The amount of time an autonomous vehicle spends in congestion while picking up the users influences the choice of parking locations. Moreover, substantial preference heterogeneity between individual people was found in the parking choice behavior. The maximum value of access time for autonomous cars is 34 $/h which is higher than the empirical value of walking time for conventional cars. Results of elasticity indicate that the influence of parking fees is larger than that of access time and congestion time.},

keywords = {Autonomous vehicles, Context effects, Parking location choice},

pubstate = {published},

tppubtype = {article}

}

@article{WU2023103839,

title = {Spatiotemporal analysis of built environment restrained traffic carbon emissions and policy implications},

author = {Jishi Wu and Peng Jia and Tao Feng and Haijiang Li and Haibo Kuang},

url = {https://www.sciencedirect.com/science/article/pii/S1361920923002365},

doi = {https://doi.org/10.1016/j.trd.2023.103839},

issn = {1361-9209},

year  = {2023},

date = {2023-01-01},

journal = {Transportation Research Part D: Transport and Environment},

volume = {121},

pages = {103839},

abstract = {Urban environmental policies need to be rectified considering the spatioemporal variations of traffic emissions. However, knowledge to support such a decision-making process is insufficient. This study analyzes the spatiotemporal distributions of traffic emissions in the built environment and their potential nonlinear associations. Considering the recent innovations in machine learning, a tree-boosting algorithm combined with Gaussian process and random effects models (GPBoost) is applied using the big GPS taxi data from Dalian, China. The nonlinear relationships between built environment variables and traffic carbon (CO2) emissions are interpreted using the SHapley Additive ExPlanation (SHAP). It is found that the proposed GPBoost model that considers spatial heterogeneity enhances the overall predictive power compared to traditional machine learning models. Most of the built environment variables have a nonlinear relationship with traffic carbon emissions and the threshold effects vary over time, indicating the necessity of dynamic urban management.},

keywords = {Built environment, GPBoost, Machine learning, Nonlinear effects, SHapley Additive ExPlanation, Traffic carbon emissions},

pubstate = {published},

tppubtype = {article}

}

@article{WANG2023138077,

title = {An acceptability-based multi-objective traffic flow adjustment method for environmental sustainability and equity},

author = {Guanfeng Wang and Hongfei Jia and Tao Feng and Jingjing Tian and Mengxia Li and Luyao Wang},

url = {https://www.sciencedirect.com/science/article/pii/S0959652623022357},

doi = {https://doi.org/10.1016/j.jclepro.2023.138077},

issn = {0959-6526},

year  = {2023},

date = {2023-01-01},

journal = {Journal of Cleaner Production},

volume = {418},

pages = {138077},

abstract = {As a product of digital development, connected autonomous vehicles (CAVs) offer a unique prospective solution to alleviate the possible performance deterioration of road networks under the mixed environment of human-driven vehicles (HVs) and CAVs. In this paper, we propose a traffic flow adjustment method (TFAM) that treats CAVs as mobile regulators with the purpose to reshape traffic flow distribution on road networks by guiding rather than controlling CAVs. More specifically, we deploy subsidy nodes to briefly outline travel routes and achieve higher acceptability than traditional route-based control schemes. The TFAM is a multi-objective bi-level programming problem where the upper-level problem optimizes the network performance through regulating location and subsidy on the subsidy nodes. The lower-level problem is a dual dynamic traffic assignment (DDTA) model. Apart from the total travel time cost (TTTC), total emission cost (TEC) and network equity (NE) are also introduced as optimization objectives to highlight environmental sustainability and acceptability. To obtain the Pareto solution frontier, a meta-heuristic algorithm with an improved encoding process is proposed. Results of two numerical case studies demonstrate the effects of TFAM on traffic flow distribution and network performance, which yields valuable insights on the optimization of urban traffic systems.},

keywords = {Connected autonomous vehicles, Digital product, Emission reduction, Multi-objective bi-level programming, Subsidy nodes deploying scheme, Traffic flow adjustment method},

pubstate = {published},

tppubtype = {article}

}

@article{LYU2023103718,

title = {A multiscale spatial analysis of taxi ridership},

author = {Tao Lyu and Yuanqing Wang and Shujuan Ji and Tao Feng and Zhouhao Wu},

url = {https://www.sciencedirect.com/science/article/pii/S0966692323001904},

doi = {https://doi.org/10.1016/j.jtrangeo.2023.103718},

issn = {0966-6923},

year  = {2023},

date = {2023-01-01},

journal = {Journal of Transport Geography},

volume = {113},

pages = {103718},

abstract = {Taxi plays a supplement role in sustainable development of urban public transport systems. However, the extent to which the built environment affects taxi ridership at various spatial scales deserves further exploration because understanding the true spatial heterogeneity across a varying scale could be valuable for both global and localized policy decision-makings. In this study, we attempt to analyze and discuss the spatial predictors of taxi ridership by utilizing an multiscale geographically weighted regression (MGWR) model and comparing the model's performance to that of ordinary least square (OLS) and geographically weighted regression (GWR) models. Using the taxi data of Xi'an city, we found that the MGWR model could explain 81.8% of the total taxi ridership fluctuations and allows localized and targeted policy makings to help taxi drivers search for passengers and to improve passengers' taxi-hailing experiences in specific districts.},

keywords = {Influencing factors, Multiscale geographically weighted regression, Scale effect, spatial heterogeneity, Taxi ridership},

pubstate = {published},

tppubtype = {article}

}

@article{ZHOU2023103936,

title = {Assessing the effects of the built environment and microclimate on cycling volume},

author = {Ting Zhou and Tao Feng and Astrid Kemperman},

url = {https://www.sciencedirect.com/science/article/pii/S1361920923003334},

doi = {https://doi.org/10.1016/j.trd.2023.103936},

issn = {1361-9209},

year  = {2023},

date = {2023-01-01},

journal = {Transportation Research Part D: Transport and Environment},

volume = {124},

pages = {103936},

abstract = {Cycling benefits human health and helps to mitigate environmental issues. However, limited evidence exists regarding how the built environment influences cycling volume under different time and weather conditions. In this paper, we employed a Gradient Boosting Decision tree method to analyze the non-linear and threshold effects of the multiscale built environment and microclimate on cycling volume. Results based on the multisource data of The Netherlands show that 27 out of the 28 variables have a non-linear and threshold effect on cycling volume. Temperature is found to be a dominant factor among all variables. At street level, slope is the most important factor, followed by the green view and sky view indexes. At neighborhood level, population density is the most important factor, followed by residential density, and the density of bus stops. These findings offer useful insights for planning a cycling-friendly urban built environment at different scales.},

keywords = {Cycling volume, Gradient Boosting Decision Tree, Multi-scale urban built environment},

pubstate = {published},

tppubtype = {article}

}

@article{LI2023103338,

title = {A decomposition-based optimization method for integrated vehicle charging and operation scheduling in automated container terminals under fast charging technology},

author = {Xiangda Li and Yun Peng and Qi Tian and Tao Feng and Wenyuan Wang and Zhen Cao and Xiangqun Song},

url = {https://www.sciencedirect.com/science/article/pii/S1366554523003265},

doi = {https://doi.org/10.1016/j.tre.2023.103338},

issn = {1366-5545},

year  = {2023},

date = {2023-01-01},

journal = {Transportation Research Part E: Logistics and Transportation Review},

volume = {180},

pages = {103338},

abstract = {The increasing utilization of battery-powered automated guided vehicles in automated container terminals, has an important consequence on terminal cost and efficiency. How to tackle integrated vehicle charging and operation scheduling problem to maintain high terminal performance is prominent for sustainable port operation. In this paper, fast charging technology is investigated, and a mixed integer programming model for this complicated scheduling problem is constructed, which aims to reduce charging cost and penalty cost related to makespan, and includes sequence-related constraints, time-related constraints and energy-related constraints. A decomposition-iteration algorithm is proposed to solve this problem, and furthermore it is combined with a simulation-based optimization method to address practical-sized instances. Numerical experiments on real-world cases are conducted to verify the efficiency and effectiveness of the proposed solution algorithm. Insightful managerial implications are derived by comparative analysis on charging rules and charging facility locations, and sensitivity analysis on charging power, charging facility configuration and vehicle configuration. Experimental results provide valuable references for terminal managers to make configuration and scheduling decisions for battery-powered vehicle transporting systems.},

keywords = {Automated container terminal, Automated guided vehicles, Charging scheduling, Decomposition algorithm, Simulation-based optimization},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Demand Prediction and Optimal Allocation of Shared Bikes Around Urban Rail Transit Stations},

author = {Liang Yu and Tao Feng and Tie Li and Lei Cheng},

url = {https://link.springer.com/content/pdf/10.1007/s40864-022-00183-w.pdf?pdf=button},

doi = {https://doi.org/10.1007/s40864-022-00183-w},

year  = {2022},

date = {2022-12-13},

journal = {Urban Transit Rail},

abstract = {The imbalance between the supply and demand of shared bikes is prominent in many urban rail transit stations, which urgently requires an efficient vehicle deployment strategy. In this paper, we propose an integrated model to optimize the deployment of shared bikes around urban rail transit stations, incorporating a seasonal autoregressive integrated moving average with long short-term memory (SARIMA-LSTM) hybrid model that is used to predict the heterogeneous demand for shared bikes in space and time. The shared bike deployment strategy was formulated based on the actual deployment process and under the principle of cost minimization involving labor and transportation. The model is applied using the big data of shared bikes in Xicheng District, Beijing. Results show that the SARIMA-LSTM hybrid model has great advantages in predicting the demand for shared bikes. The proposed allocation strategy provides a new way to solve the imbalance challenge between the supply and demand of shared bikes and contributes to the development of a sustainable transportation system.},

keywords = {Big data, Bike sharing, Machine learning, Transit},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {A novel reliable path planning approach for multimodal networks based on a two-factor bound convergence algorithm},

author = {Wentao Yu and Huijun Sun and Tao Feng and Ying Lv and Xin Guo and Guangyu Xin},

url = {https://www.worldscientific.com/doi/epdf/10.1142/S0217984922500075},

doi = {https://doi.org/10.1142/S0217984922500075},

year  = {2022},

date = {2022-08-22},

journal = {Modern Physics Letters B},

abstract = {Due to the influence of diverse factors, travel time is highly uncertain. Travelers are eager to find the most reliable path in multimodal networks to reduce the penalty caused by late arrival. However, the research considering the traveler preferences in multimodal transportation networks to solve the reliable path problem with given budgets is limited. Thus, we propose two multimodal reliable path models to find personalized and reliable paths. First, we build a multimodal network based on smart card data to incorporate the multimodal transfers between public and private transportation and solve corresponding parking issues effectively. Next, we build a multimodal time-reliable path model to find time-reliable paths. Further, considering traveler preferences, we design a multimodal utility-reliable path model to find personalized and reliable paths. A novel two-factor reliability bound convergence algorithm is developed to solve the proposed models and proved for its theoretical feasibility. Finally, a real-world case study is used to verify the effectiveness and efficiency of the proposed models and algorithm.},

keywords = {Bound convergence algorithm, Multimodal network, Path planning},

pubstate = {published},

tppubtype = {article}

}

@article{@FrontiersPublicHealthPengFeng,

title = {Analysis of students' positive emotions around the green space in the university campus during the COVID-19 pandemic in China},

author = {Shaobo Liu and Yifeng Ji and Jiang Li and You Peng and Zhitao Li and Wenbo Lai and Tao Feng},

url = {https://doi.org/10.3389/fpubh.2022.888295},

doi = {doi.org/10.3389/fpubh.2022.888295},

year  = {2022},

date = {2022-08-09},

urldate = {2022-08-09},

journal = {Frontiers in Public Health},

abstract = {Green space around the university campus is of paramount importance for emotional and psychological restorations in students. Positive emotions in students can be aroused when immersed in green space and naturalness. However, to what extent can perceived naturalness influence students' positive emotion remains unclear, especially in the context of COVID-19 countermeasures. This study, therefore, attempts to investigate in-depth the nature and strength of the relationships between students' positive emotion and their perceived naturalness, place attachment, and landscape preference, which are potentially varying across universities in different social and environmental contexts and different restrictions policies regarding the COVID-19 pandemic. A course of questionnaire-based surveys was administered on two university campuses in Heilongjiang and Hunan Provinces, China, resulting in 474 effective samples. Structural equation modeling was used to explore the hypothetical conceptual framework of latent variables and the indicators. The findings indicate that the higher students' perceived naturalness results in greater positive emotion. Students' perceived naturalness in green spaces of campus has a positive effect on their place attachment and landscape preference. Moreover, the difference between mediate effects of place attachment and landscape preference were addressed, which verifies the contextual influences.},

keywords = {COVID-19, Health},

pubstate = {published},

tppubtype = {article}

}

@article{Chen2022,

title = {Examine the Prediction Error of Ride-Hailing Travel Demands with Various Ignored Sparse Demand Effects},

author = {Zhiju Chen and Kai Liu and Tao Feng},

url = {https://www.hindawi.com/journals/jat/2022/7690309/},

doi = {https://doi.org/10.1155/2022/7690309},

year  = {2022},

date = {2022-04-12},

journal = {Journal of Advanced Transportation},

volume = {2022},

abstract = {The accurate short-term travel demand predictions of ride-hailing orders can promote the optimal dispatching of vehicles in space and time, which is the crucial issue to achieve sustainable development of such dynamic demand-responsive service. The sparse demands are always ignored in the previous models, and the uncertainties in the spatiotemporal distribution of the predictions induced by setting subjective thresholds are rarely explored. This paper attempts to fill this gap and examine the spatiotemporal sparsity effect on ride-hailing travel demand prediction by using Didi Chuxing order data recorded in Chengdu, China. To obtain the spatiotemporal characteristics of the travel demand, three hexagon-based deep learning models (H-CNN-LSTM, H-CNN-GRU, and H-ConvLSTM) are compared by setting various threshold values. The results show that the H-ConvLSTM model has better prediction performance than the others due to its ability to simultaneously capture spatiotemporal features, especially in areas with a high proportion of sparse demands. We found that increasing the minimum demand threshold to delete more sparse data improves the overall prediction accuracy to a certain extent, but the spatiotemporal coverage of the data is also significantly reduced. Results of this study could guide traffic operations in providing better travel services for different regions.},

keywords = {Ride hailing, Travel demand},

pubstate = {published},

tppubtype = {article}

}

@article{40c9feae3bd0408b805b8e9538654c6e,

title = {Role of latent factors and public policies in travel decisions under COVID-19 pandemic: Findings of a hybrid choice model},

author = {Chao Chen and Tao Feng and Xiaoning Gu},

url = {https://www.sciencedirect.com/science/article/pii/S2210670721008660},

doi = {10.1016/j.scs.2021.103601},

issn = {2210-6707},

year  = {2022},

date = {2022-03-01},

urldate = {2022-03-01},

journal = {Sustainable Cities and Society},

volume = {78},

publisher = {Elsevier},

abstract = {Policy measures to control the spread of COVID-19 imposed by different countries have a devastating impact on people's travel behaviors. Differing from the normal situation where general concerns on travel time and cost determine the travel choices, the uncertainty underlying behavior change in the case of a pandemic might be largely attributed to the latent aspects, i.e., social responsibility, risk perception, attitudes, which could diminish the effects of main attributes on travel decisions. Therefore, this paper examines the effects of COVID-19 related policies on individuals' travel choices influenced by the latent aspects. A stated choice experiment was designed to collect people's responses under policy measures to various transportation modes. Results of a hybrid choice model show that COVID-19 related policies significantly affect individuals' transportation mode choice decisions during pandemic situations. The attributes, like travel time and travel cost, which significantly impact travel behavior in normal situations, become less relevant. Moreover, the travel preferences during the pandemic are significantly associated with latent factors of social responsibility, fear of infection, perceived risk, and travel anxiety. In general, public transportation is identified as an insecure alternative compared with other private modes, and people who are more socially responsible tend to travel less during the pandemic. Outcomes of this study could be of value to policymakers and public health emergencies, e.g., government authorities to utilize such knowledge in providing social support for these COVID-19 countermeasures and designing customized policies for specific population groups.},

keywords = {COVID-19 pandemic, Latent factors, Public transport},

pubstate = {published},

tppubtype = {article}

}

@article{cd8c66995497429ba47116d41341c4f0,

title = {Investigating the effectiveness of COVID-19 pandemic countermeasures on the use of public transport: A case study of The Netherlands},

author = {Chao Chen and Tao Feng and Xiaoning Gu and Baozhen Yao},

url = {https://www.sciencedirect.com/science/article/pii/S0967070X22000051},

doi = {10.1016/j.tranpol.2022.01.005},

issn = {0967-070X},

year  = {2022},

date = {2022-03-01},

urldate = {2022-03-01},

journal = {Transport Policy},

volume = {117},

pages = {98--107},

publisher = {Elsevier},

abstract = {During the COVID-19 pandemic, public transport in many cities faces dramatic reduction of passenger demand. Various countermeasures such as social distancing and in-vehicle disinfection have been implemented to reduce the potential risks concerning infection, the effectiveness in promoting the use of public transport however remains unclear. Unlike the usual situation where time and cost are the main factors affecting travel decisions, the uncertainty hiding behind the behavior change of public transport users in a pandemic might be greatly affected by the control measures and the perception of people. This paper therefore aims to examine the effects of COVID-19 related countermeasures implemented in public transport on individuals' travel decisions. We explore the extent to which do policy countermeasures influence different groups of people on the use of public transport. An error component latent class choice model was estimated using the data collected in the Netherlands. Results show that the restrictions policy lifted by the Dutch central government have significant effect on individuals' transportation mode choice decision during the pandemic. The related measures adopted by the public transport sector, by contrast, present different effects on different people. The older and highly educated people are more susceptible to enforcement measures, whereas young and single Dutch citizens are more accessible to non-compulsory measures. Moreover, compared with other private modes, public transport is generally identified as a riskier option, and the average willingness to travel descends. Findings of this study are helpful for the authorities in designing and promoting effective policies in the context of pandemics.},

keywords = {COVID-19 pandemic, Error component latent class choice model, Public transport, Taste variation, Travel behavior},

pubstate = {published},

tppubtype = {article}

}

@article{LIU2022108,

title = {A route analysis of metro-bikeshare users using smart card data},

author = {Yang Liu and Yanjie Ji and Tao Feng and Zhuangbin Shi},

url = {https://www.sciencedirect.com/science/article/pii/S2214367X21000880},

doi = {https://doi.org/10.1016/j.tbs.2021.09.006},

issn = {2214-367X},

year  = {2022},

date = {2022-01-01},

journal = {Travel Behaviour and Society},

volume = {26},

pages = {108-120},

abstract = {Few studies have analyzed individuals’ travel route characteristics in the integrated metro and bikeshare network. Taking Nanjing, China, as a case study, this paper analyzes the combined travel route of metro-bikeshare users based on three-week metro- and shared bike smart card data. The smart card data provides both boarding/borrowing and alighting/returning location and time, which makes it possible to trace each combined mode user’s actual metro routes. By assuming that the bike routes are the shortest paths between a specific OD pair from smart card records, we extract the combined metro-bikeshare travel routes of each user by using a metro route reconstruction method. The results show that over 60% of the metro-bikeshare users, most of whom are youth adults (18–35 years old), only occasionally use this mode. Further, the spatial and temporal characteristics of the combined metro-bikeshare travel routes are analyzed visually across different age groups. We find that most of the combined metro-bikeshare routes concentrated on Metro Line 2 with different cycling access/egress routes; however, the routes mostly travelled by different age groups are significantly different. Young adults are mainly distributed in suburban and exurban areas. Adults are more likely to be metro-bikeshare commuters, with travel routes usually passing through the central area of the city. Besides, the routes mostly travelled by the elderly are longer than those by other groups, and highly coincide with the routes mostly travelled by adults during the rush hours. Finally, relevant policy implementations are proposed in conjunction with metro-bikeshare users’ travel route characteristics.},

keywords = {Metro-bikeshare integration, Smart card data, Spatiotemporal patterns, Travel route},

pubstate = {published},

tppubtype = {article}

}

@article{LIU2022103215,

title = {Robust charging strategies for electric bus fleets under energy consumption uncertainty},

author = {Kai Liu and Hong Gao and Yang Wang and Tao Feng and Cheng Li},

url = {https://www.sciencedirect.com/science/article/pii/S1361920922000451},

doi = {https://doi.org/10.1016/j.trd.2022.103215},

issn = {1361-9209},

year  = {2022},

date = {2022-01-01},

journal = {Transportation Research Part D: Transport and Environment},

volume = {104},

pages = {103215},

abstract = {Charging management has a profound impact on the reliability and safety of electric bus (EB) services. However, the actual charging operation of EB fleets is a critical challenge due to uncertain energy consumption, limited charging resources and other factors. A deterministic model and a robust model with a probability-free uncertainty set are proposed and compared. The power is optimized via rational allocation of charging resources, where the uncertainty of energy consumption is addressed to achieve the dual goals of reducing charging expenses and improving system robustness. A column generation algorithm is designed to solve the optimization issue. The experimental results show that the obtained robust charging strategies can achieve up to 97.88% utilization of charging resources at low electricity prices. Moreover, the robust model can effectively prevent low electric quantity and delayed departure issues for EBs caused by the uncertainty of energy consumption.},

keywords = {Battery performance, Column generation, Damage prevention, Energy consumption uncertainty, Robust optimization},

pubstate = {published},

tppubtype = {article}

}

@article{GU2022108409,

title = {The prediction of potential risk path in railway traffic events},

author = {Shuang Gu and Keping Li and Tao Feng and Dongyang Yan and Yanyan Liu},

url = {https://www.sciencedirect.com/science/article/pii/S0951832022000813},

doi = {https://doi.org/10.1016/j.ress.2022.108409},

issn = {0951-8320},

year  = {2022},

date = {2022-01-01},

journal = {Reliability Engineering & System Safety},

volume = {222},

pages = {108409},

abstract = {In railway traffic operation, the prediction of risk path is one of the important issues because it can ensure the potential consequences are effectively mitigated and controlled to prevent the domino effect. However, it is quite difficult to mine the potential information and investigate the complex dependency in failure text data, which makes the prediction of potential risk path challenging. In this paper, we propose a new network-based risk prediction model to investigate the propagation path of potential risk and reduce the risk of cascade failures. Three kinds of information hidden in network connections are considered: local structural information, global structural information and attribute information. The model uses the keyword extraction method of text data for data preprocessing. The breadth-first search-based algorithm is improved to identify the meta-paths. The co-occurrence matrix and the association matrix are considered to play a role in the model. In order to verify the feasibility and advantages of the model, we use a dataset consisting of traffic events in Beijing subway as a case study. Results of the comparative analysis show that the proposed model not only can effectively predict the potential risk path, but also provides the best results in terms of ROC, AUC and Precision.},

keywords = {Network-based model, Potential path, Railway traffic event, Risk prediction},

pubstate = {published},

tppubtype = {article}

}

@article{10.3389/fpubh.2022.861456,

title = {Analysis of Urban Built Environment Impacts on Outdoor Physical Activities—A Case Study in China},

author = {Bo Li and Qiuhong Liu and Tong Wang and He He and You Peng and Tao Feng},

url = {https://www.frontiersin.org/article/10.3389/fpubh.2022.861456},

doi = {10.3389/fpubh.2022.861456},

issn = {2296-2565},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

journal = {Frontiers in Public Health},

volume = {10},

abstract = {Outdoor physical activities can promote public health and they are largely influenced by the built environment in different urban settings. Understanding the association between outdoor physical activities and the built environment is important for promoting a high quality of life. Existing studies typically focus on one type of outdoor activity using interview-based small samples and are often lack of systematic understanding of the activities' intensity and frequency. In this study, we intend to gain deeper insight into how the built environment influences physical activities using the data extracted from individual's wearables and other open data sources for integrated analysis. Multi-linear regression with logarithm transformation is applied to perform the analysis using the data from Changsha, China. We found that built environment impacts on outdoor physical activities in Changsha are not always consistent with similar studies' results in other cities. The most effective measures to promote outdoor physical activities are the provision of good arterial and secondary road networks, community parks, among others in Changsha. The results shed light on future urban planning practices in terms of promoting public health."},

keywords = {Built environment, Health, Physical Activity},

pubstate = {published},

tppubtype = {article}

}

@article{ZHANG2022103385,

title = {Customizing the promotion strategies of integrated air-bus service based on passenger satisfaction},

author = {Jiyang Zhang and Min Yang and Junyi Ji and Tao Feng and Yalong Yuan and Enhui Chen and Lichao Wang},

url = {https://www.sciencedirect.com/science/article/pii/S1361920922002139},

doi = {https://doi.org/10.1016/j.trd.2022.103385},

issn = {1361-9209},

year  = {2022},

date = {2022-01-01},

journal = {Transportation Research Part D: Transport and Environment},

volume = {109},

pages = {103385},

abstract = {The integrated air-bus service expands the catchment area and alleviates congestion of regional airports. To gain further insights into the unexplored potential attributes of the integrated service that generate passenger satisfaction, this paper utilizes a two-stage analysis approach to identify the key promotion factors for passengers from different constituents. Based on the survey data collected in Nanjing Lukou International Airport, this paper 1) uses k-means clustering to categorize respondents into four groups. 2) Combines the gradient boosting decision tree and impact asymmetry analysis to identify the attributes that have nonlinear influences on the overall service satisfaction for each group respectively. Results suggest that the timetable of the airport bus is critical for all passenger groups. Interestingly, there are noticeable differences in passenger satisfaction with the accessibility, cost affordability, comfort, reliability, and integration of the integrated service, providing the basis for customizing service promotion strategies among different passenger groups and airports.},

keywords = {Clustering analysis, Gradient Boosting Decision Tree, Impact-asymmetry analysis, Integrated air-bus services, Passenger satisfaction, Service promotion},

pubstate = {published},

tppubtype = {article}

}

@article{YAN2022,

title = {Private owners’ propensity to engage in shared parking schemes under uncertainty: comparison of alternate hybrid expected utility-regret-rejoice choice models},

author = {Qianqian Yan and Tao Feng and Harry Timmermans},

url = {https://www.sciencedirect.com/science/article/pii/S1942786722005094},

doi = {https://doi.org/10.1080/19427867.2022.2088568},

issn = {1942-7867},

year  = {2022},

date = {2022-01-01},

journal = {Transportation Letters},

abstract = {ABSTRACT 

To develop effective strategies for the supply of shared parking and study various theoretical choice models under uncertainty, this paper investigates private parking space owners’ propensity to engage in shared parking schemes using a stated choice experiment that involves an uncertain key attribute. A hybrid expected utility-regret model incorporating rejoice is specified to explore the participation behavior. Equivalent models considering the perception of attribute differences are also estimated. Results show that socio-demographic characteristics, social influence, government’s role, media attention, platform fee, and revenues are all important factors explaining private parking owners’ propensity to engage in shared parking schemes. Besides, the model incorporating all these components, including the emotions of regret and rejoice and the perception of attribute differences, yields the best results. These findings could help promote the policy development toward increasing people’s engagement in shared parking.},

keywords = {hybrid expected utility-regret-rejoice models, owners, perception, propensity, Shared parking},

pubstate = {published},

tppubtype = {article}

}

@article{YUAN2022533,

title = {Heterogeneity in the transfer time of air-rail intermodal passengers based on ticket booking data},

author = {Yalong Yuan and Min Yang and Tao Feng and Yafeng Ma and Yifeng Ren and Xinpei Ruan},

url = {https://www.sciencedirect.com/science/article/pii/S0965856422002580},

doi = {https://doi.org/10.1016/j.tra.2022.09.022},

issn = {0965-8564},

year  = {2022},

date = {2022-01-01},

journal = {Transportation Research Part A: Policy and Practice},

volume = {165},

pages = {533-552},

abstract = {Transfer constitutes the weakest link in air-rail integrated services (ARISs). Air-rail passengers face problems such as long transfer times, complex transfer processes and poor transfer experiences, which seriously reduces ARIS competitiveness. The transfer time, as the most direct and objective measurement of transfer behavior, is important in ARIS planning, construction and operation. This paper aims to analyze the influence of transfer time on the use of ARIS using ticket booking data. The air-rail intermodal passengers are classified into three groups according to the social demographical attributes and trip characteristics using a latent class clustering model, namely passengers departing on weekdays for medium- or long-distance trips, passengers departing on weekdays for medium- or short-distance trips and passengers departing during weekends for medium- or long-distance trips. After that, a generalized ordered logistic regression (GOL) model is employed to identify the key factors influencing the transfer behavior of these three passenger groups. The results indicate that ticket-related attributes have the greatest impact on passenger transfer behavior, followed by transfer-related attributes, and operation-related attributes have the least impact. The effects of operation- and transfer-related attributes on transfer behavior among the different passenger groups are similar, but the ticket price, travel distance and travel time impose distinct effects on transfer behavior in the different passenger groups. Finally, some relevant recommendations to improve the ARIS are discussed.},

keywords = {Air-rail integrated service (ARIS), Air-rail passenger, Passenger heterogeneity, Ticket booking data, Transfer time},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1080/23249935.2022.2138628,

title = {Attitudes, personality traits and private parking space owners’ willingness to engage in shared parking schemes: a hybrid prospect theoretic model},

author = {Qianqian Yan and Tao Feng and Harry Timmermans},

url = {https://doi.org/10.1080/23249935.2022.2138628},

doi = {10.1080/23249935.2022.2138628},

year  = {2022},

date = {2022-01-01},

journal = {Transportmetrica A: Transport Science},

volume = {0},

number = {0},

pages = {1-29},

publisher = {Taylor & Francis},

abstract = {ABSTRACTTo develop effective strategies for the supply of shared parking, the present study investigates factors influencing the willingness of private parking space owners to engage in shared parking. Apart from the attributes of shared parking options, unobserved latent variables measuring attitudes and personality traits, are assumed to play a role in the decision-making process. This study estimates a hybrid prospect theoretic model to investigate the willingness of parking space owners to share their parking space. The latent variables include personality traits and attitudes that are incorporated into a prospect theoretic choice model. Non-linear effects of the latent variables and the interaction effects between personality traits and attitudes are examined. Results indicate that non-linear effects and interactions significantly improve the overall explanatory power of the model. The research findings may help in developing shared parking policies and informing companies and governments how to promote shared parking schemes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{LIU2022460,

title = {Understanding the route choice behaviour of metro-bikeshare users},

author = {Yang Liu and Tao Feng and Zhuangbin Shi and Mingwei He},

url = {https://www.sciencedirect.com/science/article/pii/S0965856422002890},

doi = {https://doi.org/10.1016/j.tra.2022.11.006},

issn = {0965-8564},

year  = {2022},

date = {2022-01-01},

journal = {Transportation Research Part A: Policy and Practice},

volume = {166},

pages = {460-475},

abstract = {Understanding the determinants of the route choice behaviour on a multi-modal transit network of metro and shared bike is important to improve personalized multimodal travel services. This paper attempts to analyse the route choice behaviour of metro-bikeshare users considering passengers’ socio-economic attributes and perceived congestion which is approximated by load status. An abstract integrated metro-bikeshare network (IMBN) is built with virtual nodes by aggregating shared bike stations within the walkable distance and abstract routes by aggregating optional paths for each OD pair. Using the metro- and shared bike smart- card data from Nanjing, China, the route sets of metro-bikeshare users were extracted from the IMBN. A multinomial Logit model (MNL) was then applied to investigate the determinants of route choice behaviour for two types of users, namely “return-enter” and “exit-lease”, respectively. The results show that the models with the load status attributes have a better performance than the models without these attributes. We found the sensitivity of “exit-lease” users to the train crowding is significantly greater than that of the “return-enter” users. “Return-enter” users have a higher perception of out-of-vehicle travel time (OVTT) than that of in-vehicle travel time (IVT), while the “exit-lease” users have the opposite perception. Besides, the change rate of shared bike inventory, departure time and whether he or she is a regular user also have a significant impact on route choice behaviour. The findings can help policymakers and system operators to improve the services and the efficiency of the multimodal transportation system.},

keywords = {Metro-bikeshare integration, Multinomial logit model, Route choice, Smart card data},

pubstate = {published},

tppubtype = {article}

}

@article{c8074a50b1504dc9bbb68a3a8a592d14,

title = {Improved imputation of rule sets in class association rule modeling: application to transportation mode choice},

author = {Jiajia Zhang and Tao Feng and Harry Timmermans and Zhengkui Lin},

doi = {10.1007/s11116-021-10238-9},

issn = {0049-4488},

year  = {2021},

date = {2021-11-26},

journal = {Transportation},

volume = {XX},

number = {X},

publisher = {Springer},

abstract = {Predicting transportation mode choice is a critical component of forecasting travel demand. Recently, machine learning methods have become increasingly more popular in predicting transportation mode choice. Class association rules (CARs) have been applied to transportation mode choice, but the application of the imputed rules for prediction remains a long-standing challenge. Based on CARs, this paper proposes a new rule merging approach, called CARM, to improve predictive accuracy. In the suggested approach, first, CARs are imputed from the frequent pattern tree (FP-tree) based on the frequent pattern growth (FP-growth) algorithm. Next, the rules are pruned based on the concept of pessimistic error rate. Finally, the rules are merged to form new rules without increasing predictive error. Using the 2015 Dutch National Travel Survey, the performance of suggested model is compared with the performance of CARIG that uses the information gain statistic to generate new rules, class-based association rules (CBA), decision trees (DT) and the multinomial logit (MNL) model. In addition, the proposed model is assessed using a ten-fold cross validation test. The results show that the accuracy of the proposed model is 91.1%, which outperforms CARIG, CBA, DT and the MNL model.},

note = {Funding Information: This work was supported by China Scholarship Council.},

keywords = {Class association rules, FP-tree, Rule merging, Transportation mode choice},

pubstate = {published},

tppubtype = {article}

}