Transportation最新文献

Recent years have witnessed an increasing number of artificial intelligence (AI) applications in transportation. As a new and emerging technology, AI’s potential to advance transportation goals and the full extent of its impacts on the transportation sector is not yet well understood. As the transportation community explores these topics, it is critical to understand how transportation professionals, the driving force behind AI Transportation applications, perceive AI’s potential efficiency and equity impacts. Toward this goal, we surveyed transportation professionals in the United States and collected a total of 354 responses. Based on the survey responses, we conducted both descriptive analysis and latent class cluster analysis (LCCA). The former provides an overview of prevalent attitudes among transportation professionals, while the latter allows the identification of distinct segments based on their latent attitudes toward AI. We find widespread optimism regarding AI’s potential to improve many aspects of transportation (e.g., efficiency, cost reduction, and traveler experience); however, responses are mixed regarding AI’s potential to advance equity. Moreover, many respondents are concerned that AI ethics are not well understood in the transportation community and that AI use in transportation could exacerbate existing inequalities. Through LCCA, we have identified four latent segments: AI Neutral, AI Optimist, AI Pessimist, and AI Skeptic. The latent class membership is significantly associated with respondents’ age, education level, and AI knowledge level. Overall, the study results shed light on the extent to which the transportation community as a whole is ready to leverage AI systems to transform current practices and inform targeted education to improve the understanding of AI among transportation professionals.

This study relies on the unique revealed choice dataset to investigate the impact of crowding information provision on the route choices of smartphone navigation application users. Extensive processing steps are documented, and data validation is performed to ensure that the dataset is representative of the travel behavior in the Metro Vancouver region, as well as of the crowding conditions on its transit system. A mixed logit model is used for the analysis to account for the panel effect of the dataset. The estimates indicate that information about crowding has a meaningful effect on the travel decisions transit navigation application users make, with the increase in crowding lowering the chances of a route being selected. The identified effects of crowding are also comparable to the estimates that the other sources of revealed preferences on transit (like smart card records) provide. For example, it is found that the time multiplier is 2.23 for a crowded trip (100%+ vehicle occupancy) in a rapid transit vehicle like bus rapid transit or light rail, and that crowded trips on a regular bus are perceived as almost six minutes longer. The findings of this study should be of interest to both the research and the professional community, as it provides more accurate findings than those coming from stated preference surveys and simulations, which are subject to limitations like uncontrolled biases and potential errors. At the same time, it informs transit agencies about the effect of crowding information provision and can potentially facilitate the possibility of expanding that effort (e.g. ensuring higher accuracy and broader availability of the data).

Recent data-driven discrete choice models in travel demand forecasting have achieved improved predictability. However, such prediction improvements come at the cost of black-box models and lost transparency in travel demand forecasting, which makes scenario testing and transportation planning difficult (if not impossible). Furthermore, these predictability gains have often been modest compared to handcrafted parsimonious models, which benefit from enhanced behavioural interpretability and transparency. This paper introduces a novel bi-level model and estimation framework (DUET) to enhance predictability in traditional utility-based discrete choice models. The proposed model improves the specification process by identifying effective variable transformations and interactions in utility functions. Utilising a genetic algorithm, the upper level of our framework selects feasible functional forms from an extensive array, while the lower level applies iterative singular value decomposition and maximum likelihood estimation to optimise model parameters and prevent overfitting. This approach ensures superior predictability through a general utility functional form that considers extensive variable interactions. Case studies on both synthetic data and the Swissmetro dataset highlight the framework’s effectiveness in improving model performance and uncovering critical behavioural patterns and latent trends. Notably, incorporating interactions among variables in Swissmetro data, our model demonstrates a 6.5% improvement in the Brier score (probabilistic prediction accuracy) compared to the state-of-the-art deep neural network-based discrete choice model.Lastly, our results on transport mode choice data align with existing literature, indicating that younger individuals are less sensitive to travel costs. This confirms the need for targeted pricing policies to encourage public transit use among different age groups.

Non-extreme flood disasters caused by urban fluvial flooding can disrupt and impact the operation of urban road traffic systems. This is particularly evident in the influence on the path selection behavior of network users and the resulting changes in the equilibrium state of the road network. Consequently, the network cannot maintain its original performance, leading to disturbances and interruptions. Therefore, this study proposes a novel stochastic traffic assignment model to simulate and analyze such scenarios. The model proposed in this study introduces a path cost expression that incorporates two stochastic terms, effectively capturing the perceived objective costs for different types of users under non-extreme flooding: flood risk and travel time, as well as the subjective cost factors of the users. Additionally, this study introduces a new criterion to classify paths into acceptable and unacceptable categories. Users will abandon unacceptable paths deemed too dangerous and will choose paths only from their set of acceptable paths until the road network reaches an equilibrium state. The corresponding set of acceptable paths will dynamically change based on the risk sensitivity of different types of users and the prevailing flood conditions. The model developed in this study can effectively analyze the impact of non-extreme floods on the path selection behavior of users with different risk sensitivities and simulates the evolution of the road network’s equilibrium state as users instinctively avoid risks. This research provides valuable insights for stakeholders in the operation, management, maintenance, and restoration of road networks under non-extreme flood conditions.

Ride-hailing services, which are offered by companies such as Uber and Lyft, have the potential to produce both benefits and negative externalities. In particular, ride-hailing can help improve mobility and accessibility, but can also contribute to increases in vehicle-miles traveled, congestion, and emissions. Induced ride-hailing trips (i.e., trips that would not have been made if ride-hailing was not available) represent somewhat of a middle ground between benefits and negative externalities. Studies on ride-hailing use have consistently found evidence of induced trips; however, relatively little is known about induced ride-hailing trips. This study uses data from a weeklong smartphone-based travel survey conducted in three metropolitan regions in California to examine the attributes of induced ride-hailing trips and the people who made said trips during the survey period. Descriptive analysis, hypothesis testing, and binary logistic regression are applied to gain insights into the attributes of induced ride-hailing trips and the factors influencing whether a person recorded an induced trip during the survey period. The results suggest that induced trips are more likely to correspond to discretionary and maintenance activities and more likely to be made using pooled ride-hailing services. Additionally, the members of groups that have traditionally experienced transportation disadvantage (including people with disabilities, people from lower-income households, and people from zero-vehicle households) were more likely to record an induced trip. This information can help inform efforts to improve the mobility and accessibility of disadvantaged groups and contribute to improvements in transit and paratransit services.

Anti-congestion policies, such as urban spatial planning, transport infrastructure, and economic incentives, are often regarded as effective structural measures for relieving citywide traffic congestion. However, few studies have empirically investigated and compared the intervention effects of such structural policies on relieving congestion. Using longitudinal AutoNavi’s big-data-based congestion delay index from 96 congested Chinese cities, we developed panel regression models with random effects to estimate the impact of four types of structural determinants on traffic congestion, including fuel price, road construction, public transportation, and urban spatial characteristics. The empirical results demonstrate that (1) the impacts of urban spatial characteristics and public transportation outweigh the impacts of fuel price and road construction on traffic congestion in terms of significance level and quantity; and (2) higher gasoline prices, road length and capacity expansion, a polycentric urban structure, and mixed land use contribute to alleviating traffic congestion. These findings enable a systematic understanding of the determinants of traffic congestion and provide policy implications in the context of developing countries.

In this article, we formulate a hybrid model that allows to identify the triggers of instant utilities using psychophysiological indicators (PPIs). Instant utilities are understood as momentary emotions perceived in every instant of an experience. We build the model using transport and environmental variables associated with the experience to explain instant utilities, which are measured by PPIs and stated emotions. The model is estimated with data from a real-life travel experiment, in which SKT (skin temperature), HR (heart rate), HRV (heart rate variation), and EDA (electrodermal activity) were measured with a wristband. In addition, environmental variables such as CO₂, noise, brightness, and temperature were collected and used to explain instant utility and to control for variation of PPIs. As emotions can be discomposed into at least two dimensions (valence and activation) we capture this multidimensionality estimating two independent models that explain the valence and activation of stated emotions. To analyse what is gained by including physiological data, these models are compared with baseline models without PPIs. Our main findings are: (1) instant utilities are sensible, for instance, to the travel mode; velocity; crowding; brightness; temperature; and humidity; (2) PPIs help to identify the effect of stimuli that cause small variations in the underlying emotions; and (3) instant utility has heterogeneous effects on PPIs across individuals, implying that it is necessary individuals-specific considerations to infer instant utility from PPIs. We discuss the potential applications of this framework in the evaluation of travel satisfaction and demand estimation.

The rapid growth of passengers has led to overcrowding in urban rail transit (URT) systems, especially during holidays, posing significant challenges to the safe management and operation of URT systems. Accurate and real-time short-term passenger inflow and outflow prediction on holidays is essential for operation management and resource allocation to alleviate such overcrowding. However, short-term passenger inflow and outflow prediction on holidays is a challenging task influenced by various factors, including temporal dependencies, spatial dependencies, the temporal evolution of spatial dependencies, the interaction between inflow and outflow, and the limited holiday samples. To address these challenges, we propose a Spatial–Temporal Multi-Task Learning (STMTL) for short-term passenger inflow and outflow prediction on holidays in URT systems. STMTL comprises three parts: (1) Multi-Graph Channel Attention Network (MGCA) extracts both static and dynamic spatial dependencies from inter-station interaction graphs and then adaptively integrates multi-graph features. (2) Time Encoding-Gated Recurrent Unit (TE-GRU), utilizes time encoding gates to capture long-term periodic variations and unique fluctuations caused by holidays. (3) Cross-attention block (CAB) captures complex interactions during holidays and facilitates the sharing of spatiotemporal features between passenger inflow and outflow. The effectiveness and robustness of STMTL are validated on two real-world datasets from the Nanning URT system in China during the New Year’s Day period. Experimental results demonstrate that STMTL consistently outperforms several classic and state-of-the-art models. STMTL achieves a 3.87% and 3.39% average improvement over the best-performing baseline models at 15-min and 30-min granularities, highlighting its potential for practical applications in URT systems during holidays.

The promotion of electric vehicles (EVs) poses challenges to the power grid due to the large-scale and disordered charging behaviors. While previous studies have investigated the charging patterns of EVs, little attention has been paid to electric taxis (ETs). To address this gap, this study proposes a novel combinatorial clustering model to investigate the charging patterns of ETs. This model employs Principle Component Analysis (PCA) for dimensionality reduction, an Canopy + to determine the optimal number of clusters, and concludes with K-means for rapid clustering. It exploits the rich information from the high-dimensional features, such as battery status, time, driving range, and environmental conditions, and enables fast and accurate analysis of large-scale ET charging behavior. The model analyzed a year of charging data from 164 ETs in Hangzhou, identifying six typical patterns. The impact of 20,000 ET charging loads on the power grid was further simulated. The results indicate that increasing the proportion of three types of fast-charging patterns can alleviate the peak and standard deviation of the power load of the grid. This study contributes to a better understanding of the charging behaviors of ETs and provides insights for managing the power demand in the context of urban transportation.

Examining commuting and its connection to wellbeing is a crucial policy concern. Commuting in urban areas is highly stressful and unsafe due to the dearth of transportation supply. Studies examining the cascading phenomenon of commute stress and safety possibly affecting travel wellbeing (TWB) and subsequently impacting quality of life (QOL) are limited. Hence, this study examined the role of trip characteristics, stress and safety perceptions, and residence area characteristics on TWB and how TWB and all these factors further affect the QOL of commuters in a heterogeneous urban region using confirmatory factor analysis and structural equation modeling (SEM). This study further analyzed the equitable distribution of TWB and QOL perceptions across socio-economic groups with the Gini index. A revealed preference survey was conducted in the Mumbai Metropolitan Region, India, and data was collected from 1431 commuters from diverse socio-economic groups. The results indicate that travel time, travel cost, travel discomfort, waiting time, and perceived stress negatively influence TWB, while perceived safety and travel mode are positively associated with TWB. Surprisingly, non-motorized commuters have the lowest TWB levels. Considering direct effects, TWB positively influences QOL, while travel discomfort negatively influences QOL. In indirect effects, perceived stress negatively influences QOL through TWB, whereas perceived safety positively influences QOL through its impact on TWB. The calculated Gini indexes imply equitable distribution of TWB and QOL perceptions among socio-economic groups segmented by income, age, and gender. The policy implications for improving TWB and QOL are discussed accordingly.