Search

The rapid expansion of urban rail transit necessitates accurate short-term passenger flow forecasts (STPFF) to optimize operation plans and enhance service quality. However, the existing STPFF methods do not fully consider the effect of built environment on passenger flow. In this regard, a convolutional long short-term memory neural network (CNN-LSTM) model incorporating built environment indicators has been proposed for accurately short-term passenger flow predictions. First, a system of built environment indicators (including 11 indicators), anchored in the 5Ds framework, is introduced to depict the characteristics of the built environments surrounding rail transit stations. Then, the random forest model (RF) is utilized to measure and rank the indicator importance. Finally, using historical passenger flow and key built environment indicators as input variables, a CNN-LSTM model for short-term passenger flow forecast is built. Taking Beijing city, China as an example for empirical research, the results show that CNN-LSTM model considering built environment can improve the accuracy of STPFF. Utilizing the top four key built environment indicators (the ratio of commercial land area, density of point of interest (POI) categories, and bus station density) as input variables can effectively reduce model computational complexity while concurrently enhancing predictive accuracy. The highest forecasting accuracy of the model is achieved at a time granularity of 5 min. This study can effectively support the operation and management of urban rail transit. [ABSTRACT FROM AUTHOR]

The occurrence of accidents in expressway weaving areas is significantly influenced by frequent lane change maneuvers. Acquiring the lane change behavior pattern characteristics of vehicles in this area can provide prior knowledge for autonomous vehicles when performing lane change maneuvers, which helps ensure the safety of autonomous vehicles. This study aims to extract lane change behavior patterns of vehicles in weaving areas, to analyze the distribution differences of patterns across different lane change maneuvers, and to explore risk characteristics during the lane change process. First, a lane-changing sequence segmentation method was designed based on the hierarchical Dirichlet process hidden semi-Markov model (HDP-HSMM) algorithm, taking into account the interaction with surrounding vehicles and risk factors. Second, the Gaussian mixture model latent Dirichlet allocation (GMM-LDA) algorithm was employed to cluster the segments and derive patterns of lane-changing behavior that include risk attributes. The trajectory data from the UCF SST dataset were used to validate the method framework and make an in-depth analysis. The results show that the behavior patterns obtained by this method are able to better describe the operational and risk states of the vehicle. Variations exist in the behavioral patterns of different types of lane change maneuvers throughout the entire process. Spatial distribution disparities exist in the behavior patterns of lane change maneuvers across various sections of weaving areas. The findings of this study provide behavioral characteristics of different types of lane change maneuvers in weaving areas, which might contribute to enhancing the accurate recognition of lane change behaviors by autonomous vehicles. [ABSTRACT FROM AUTHOR]

Rational allocation of healthcare facilities is a key component of planning strategies in promoting public health and wellbeing worldwide. Many Chinese cities have been experiencing population loss, making it challenging to match the supply and demand of healthcare facilities accurately. How to plan healthcare facilities to improve spatial accessibility in shrinking cities is still an underresearched topic. Taking Lufeng in China as the case, we used residential electricity consumption rate as proxy data to rectify the actual population distribution and used Gaussian two-step floating catchment area (G2SFCA) to evaluate the spatial accessibility of hierarchical healthcare facilities for making recommendations to improve the planning of healthcare facilities in shrinking cities to achieve better spatial accessibility. Our findings indicated that: (1) the supply and demand of healthcare facilities were generally not well matched, especially in the fringe area; (2) the sudden influx population during festival periods placed additional burden on medical resources in the fringe area and its spatial accessibility, especially on township hospitals and community healthcare services; and (3) to promote the spatial accessibility of healthcare facilities in shrinking cities, we proposed related planning strategies regarding the targeted allocation of three-level healthcare facilities to match the hierarchical diagnosis and treatment, and flexible setting of mobile healthcare facilities and telemedicine to echo the temporal population changes. These findings can provide references for improving livelihood health in cities experiencing population loss. [ABSTRACT FROM AUTHOR]

With population aging becoming increasingly prominent, it has been recognized as a critical issue for urban planners whether older adults can access fair, high-quality medical services. Yet, few studies have investigated urban medical accessibility at a departmental level for older adults. Taking Beijing as a case study, this study puts forth a novel framework augmented by multisource data to analyze subdistrict-scale accessibility to urban medical departments, with a particular emphasis on older adults' common diseases. Online registration data were collected to indicate the supply capacity of medical services, with the influence of department reputation taken into account when determining the facilities' service range. A hierarchical two-step floating catchment area method was employed to examine accessibility for older adults to the cardiovascular, orthopedic, endocrinology, respiratory, and neurology departments. Subsequently, Gini indices were calculated to evaluate medical accessibility equity across urban spaces. Additionally, multiple linear regression was used to explore the correlations between medical accessibility and potential influencing factors. Results showed that medical accessibility is typically higher in downtown areas and decreases from the urban center to the peripheral areas in Beijing. Cardiovascular, respiratory, and orthopedic patients face relatively greater difficulty in accessing appropriate medical resources. Furthermore, significant inequity in medical accessibility was observed among the subdistricts at different locations, with accessibility inequity in the ecological conservation area being particularly concerning. Additionally, seven factors were found to significantly affect accessibility, including distance to the urban center, density of arterial and collector roads, proportion of residential land use, proportion of public service land use, proportion of transportation land use, and proportion of vehicle ownership. The proposed framework could identify subdistricts with low accessibility for older adult patients to access different medical departments. Therefore, it could potentially support the policy-making process by offering guidelines to adjust the construction plan of the medical system in metropolises and optimize the direction for resource input. [ABSTRACT FROM AUTHOR]

High pressure and high temperature (HPHT) oil and gas pipelines, the burial depths of which are determined by the mitigation requirement of upheaval buckling deformation or legislation requirement, are commonly buried below the ground surface. Uplift resistance of soils surrounding the buried pipeline should be considered into the design of upheaval buckling behavior. Conventional design guidelines and current analytical models based on either dry soil or fully saturated soil are generally applied to predict the soil uplift resistance behavior. Therefore, the HPHT pipelines are mostly buried in unsaturated onshore soils. This paper presents a series of small pipe–soil interaction experiments for measuring the reaction that is acted on the buried pipelines in unsaturated backfill soils, and its purpose is studied to evaluate the impacts of soil moisture content, pipeline burial depths, and tension loading levels on the soil uplift resistance behavior. A new simplified formula based on the uplift experiment results is specially established to predict the uplift resistance of soils. Further, the uplift failure mechanism and pipe–soil interaction behavior are effectively applied to predict the upheaval buckling behavior of the pipelines buried in unsaturated soils. [ABSTRACT FROM AUTHOR]

Traditionally, urban land use planning belongs to urban planning and transportation infrastructure construction belongs to transportation planning. However, it is widely recognized that the integrated optimization of urban and transportation planning is the development trend in the future. This paper will develop a methodology to model the integrated transportation and land use planning problem that will consider the stochastic characteristic of link capacity and travel demand. The integrated planning problem will be formulated as a bilevel programming model. In this programming, the upper-level decision makers are urban planners and transportation engineers that aim to maximize network performance by making integrated planning schemes. Specifically, the planners should determine how to allocate limited resources between the development of residential and working locations, and improvement of the traffic network. The lower-level decision maker is the heterogenous traveler that makes residential and working location decisions, and the choice of travel path. The land use pattern is indicated by the spatial distribution of residential and working locations. Finally, the particle swarm optimization (PSO) algorithm will be used to solve the bilevel model. A set of numerical experiments will be carried out to illustrate the application of this model. [ABSTRACT FROM AUTHOR]