Identifying the latent relationships between factors associated with traffic crashes through graphical models.

Traffic safety field has been oriented toward finding the relationships between crash outcomes and predictor variables to understand crash phenomena and/or predict future crashes. In the literature, the main framework established for this purpose is based on constructing a modelling equation in which crash outcome (e.g., frequencies) is examined in relation to explanatory variables chosen based on the problem at hand. Despite the importance and success of this approach, there are two issues that are generally not discussed: 1) the latent relationships between factors associated with crashes are oftentimes not the focus of analysis or not observed; and 2) there are not many tools to make informed decisions on which variables might have an impact on the crash outcome and should be included in a safety model, particularly when observations are limited. To address these issues, this paper proposes the use of graphical models, namely a Markov random field (MRF) modelling, Bayesian network modelling, and a graphical XGBoost approach, to disclose relationship topologies of explanatory variables leading to fatal and incapacitating injury pedestrian crashes. The application of graph learning models in traffic safety has a high potential because they are not only useful to understand the mechanism behind the crash occurrence but also can assist in devising accurate and reliable prevention measures by identifying the true variable structure and essential factors jointly acting towards crash occurrence, similar to a pathological examination.

Location selection of field hospitals amid COVID-19 considering effectiveness and fairness: A case study of Florida.

The world has experienced an unprecedented global health crisis since 2020, the COVID-19 pandemic, which inflicted massive burdens on countries' healthcare systems. During the peaks of the pandemic, the shortages of intensive care unit (ICU) beds illustrated a critical vulnerability in the fight. Many individuals suffering the effects of COVID-19 had difficulty accessing ICU beds due to insufficient capacity. Unfortunately, it has been observed that many hospitals do not have enough ICU beds, and the ones with ICU capacity might not be accessible to all population strata. To remedy this going forward, field hospitals could be established to provide additional capacity in helping emergency health situations such as pandemics; however, location selection is a crucial decision ultimately for this purpose. As such, we consider finding new field hospital locations to serve the demand within certain travel-time thresholds, while accounting for the presence of vulnerable populations. A multi-objective mathematical model is proposed in this paper that maximizes the minimum accessibility and minimizes the travel time by integrating the Enhanced 2-Step Floating Catchment Area (E2SFCA) method and travel-time-constrained capacitated p-median model. This is performed to decide on the locations of field hospitals, while a sensitivity analysis addresses hospital capacity, demand level, and the number of field hospital locations. Four counties in Florida are selected to implement the proposed approach. Findings can be used to identify the ideal location(s) of capacity expansions concerning the fair distribution of field hospitals in terms of accessibility with a specific focus on vulnerable strata of the population.

A comprehensive analysis of the relationships between the built environment and traffic safety in the Dutch urban areas.

Built-environment factors potentially alleviate or aggravate traffic safety problems in urban areas. This paper aims to investigate the relationships of these factors with vehicle-bicycle and vehicle-vehicle property damage only (PDO) and killed and severe injury (KSI) crashes in urban areas. For this purpose, an area-level analysis using 100x100m2 cells, along with a Spatial Hurdle Negative Binomial regression model were employed. The study area is composed of a selection of municipalities in the Netherlands-Randstad Area where major land-use developments have occurred since the 1970s. The study was conducted by developing a rich dataset composed of various national and local databases. The findings reveal that built-environment factors and land-use policies have substantial impacts on safety, which cannot be neglected. The factors explaining the land-use density and diversity in the area (e.g., urbanity and function mixing levels), as well as the land-use design characteristics (indicated by average age of the neighborhoods), traffic and road network characteristics, and proximity to different destinations influence the probability, frequency, and severity of crashes in urban areas. Furthermore, low socioeconomic levels are associated with a higher frequency of traffic crashes.

Multivariate random parameter Tobit modeling of crashes involving aging drivers, passengers, bicyclists, and pedestrians: Spatiotemporal variations.

The increase in 65 years and older population in the United States compels the investigation of the crashes involving all aging (65+) roadway users (drivers, passengers, bicyclists, and pedestrians) in order to ensure their safety. As such, the objective of this research is to provide a spatiotemporal comparative investigation of the crashes involving these aging roadway users in Florida via concurrently using the same set of predictors in order to obtain comparable findings among them. First, a new metric, namely Crash Rate Difference (CRD) approach is developed, which enables one to capture potential spatial and temporal (e.g., weekend and weekday) variations in crash rates of aging user-involved crashes. Second, a multivariate random parameter Tobit model is utilized to determine the factors that drive both the crash occurrence probability and the crash rate of 65+ roadway users, accounting for the unobserved heterogeneity. Findings show that there are statistically significant heterogeneous effects of predictors on the crash rates of different roadway users, which evidences the unobserved heterogeneity across observations. Results also indicate that the presence of facilities such as hospitals, religious facilities, or supermarkets is very influential on crash rates of 65+ roadway users, advocating that roadways around these facilities should be particularly scrutinized by road safety stakeholders. Interestingly, the effect of these facilities on crashes also differs significantly between weekdays and weekends. Moreover, the roadway segments with high crash rates vary temporally depending on whether it is a weekday or a weekend. These findings regarding the spatiotemporal variations clearly indicate the need to develop and design better traffic safety measures and plans addressing these specific roadway segments, which can be tailored to alleviate traffic safety problems for 65+ roadway users.