Bayesian spatial correlation, heterogeneity and spillover effect modeling for speed mean and variance on urban road networks

Analyzing the heterogenous effects of factors on high-range speeding likelihood of taxi speeders: Does explainable deep learning provides more insights than random parameter approach?

The random parameters Generalized Linear Model (GLM) is frequently used to model speeding characteristics and capture the heterogenous effects of factors. However, this statistical approach is seldom employed for prediction and generalization due to the challenge of transferring its predefined errors. Recently, the emergence of explainable AI techniques has illuminated a new path for analyzing factors associated with risky driving behaviors. Despite this, there remains a gap that comparing results from machine and deep learning (ML/DL) approaches with those from random parameters GLM. This study aims to apply the random parameter GLM and explainable deep learning to evaluate the heterogenous effects of factors on the taxis' high-range speeding likelihood. Initially, a Beta GLM with random parameters (BGLM-RP) is developed to model the high-range speeding likelihood among taxi drivers. Additionally, XGBoost, a simple convolutional neural network (Simple-CNN), a deeper CNN (DCNN), and a deeper CNN with self-attention (DCNN-SA) are developed. The quantified explanations and illustrations of the factors' heterogenous effects from ML/DL models are derived from pseudo coefficients by decomposing factors' SHapley Additive exPlanations (SHAP) values. All the developed statistical, ML, and DL models are compared in terms of mean absolute errors and mean square errors on testing and full data. Results show that DCNN-SA excels in prediction on testing data, indicating its superior generalization capabilities, while BGLM-RP outperforms other models on full data. The DCNN-SA can reveal the heterogenous effects of factors for both in-sample and out-of-sample data, which is not possible for the random parameter GLM. However, BGLM-RP can reveal larger magnitudes of the factors' heterogenous effects for in-sample data. The signs and significances are identical between the varying coefficients from BGLM-RP and the pseudo coefficients from the ML/DL models, demonstrating the validity and rationale of using the proposed explanation framework to quantify the factors' effects in ML/DL models. The study also discusses the contributions of various factors to the high-range speeding likelihood of taxi drivers.

A spatial autocorrelation analysis of road traffic crash by severity using Moran's I spatial statistics: A comparative study of Addis Ababa and Berlin cities

Methodological advancements in road safety research reveal an increasing inclination toward integrating spatial approaches in hot spot identification, spatial pattern analysis, and developing spatially lagged models. Previous studies on hot spot identification and spatial pattern analysis have overlooked crash severities and the spatial autocorrelation of crashes by severity, missing valuable insights into crash patterns and underlying factors. This study investigates the spatial autocorrelation of crash severity by taking two capital cities, Addis Ababa and Berlin, as a case study and compares patterns in low and high-income countries. The study used three-year crash data from each city. It employed the average nearest neighbor distance (ANND) method to determine the significance of spatial clustering of crash data by severity, Global Moran's I to examine the statistical significance of spatial autocorrelation, and Local Moran's I to identify significant cluster locations with High-High (HH) and Low-Low (LL) crash severity values. The ANND analysis reveals a significant clustering of crashes by severity in both cities, except in Berlin's fatal crashes. However, different Global Moran's I results were obtained for the two cities, with a strong and statistically significant value for Addis Ababa compared to Berlin. The Local Moran's I result indicates that the central business district and residential areas have LL values, while the city's outskirts exhibit HH values in Addis Ababa. With some persistent HH value locations, Berlin's HH and LL grid clusters are intermingled on the city's periphery. Socio-economic factors, road user behavior and roadway factors contribute to the difference in the result. Nevertheless, it is interesting to note the similarity of significant HH value locations on the outskirts of both cities. Finally, the results are consistent with previous studies and indicate the need for further investigation in other locations.

Who might encounter hard-braking while speeding? Analysis for regular speeders using low-frequency taxi trajectories on arterial roads and explainable AI

Regular speeders are those who commit speeding recidivism during a period. Among their speeding behaviors, some occurring in specific scenarios may cause more hazards to road users. Therefore, there is a need to evaluate the driving risks if the regular speeders have different speeding propensities. This study considers speeding-related hard-braking events (SHEs) as a safety surrogate measure and recognizes the regular speeders who encounter at least one SHEs during the study period as risky individuals. To identify speeding behaviors and hard-braking events from low-frequency GPS trajectories, we compare the average travel speed between pairwise adjacent GPS points to the posted speed limit and examine the speed curve and the corresponding travel distance between these GPS points, respectively. Thereafter, a logistic model, XGBoost, and three 1D Convolutional Neural Networks (CNNs) including AlexNet CNN, Mini-AlexNet CNN, and Simple CNN are respectively developed to recognize the regular speeders who encountered SHEs based on their speeding propensities. The proposed Mini-AlexNet CNN achieves a global F1-score of 91% and recall of 90% on the testing data, which are superior to other models. Further, the study uses the Shapley Additive exPlanation (SHAP) framework to visually interpret the contribution of speeding propensities on SHE likelihood. It is found that speeding by 50% or greater for no more than 285 m is the most dangerous kind among all the speeding behaviors. Speeding on roads without bicycle lanes or on roads with roadside parking and excessive accesses increases the probability of encountering SHEs. Based on the analyses, we put forward tailored recommendations that aim to restrict hazard-related speeding behaviors rather than speeding behaviors of all kinds.

Exploring the impact of trip patterns on spatially aggregated crashes using floating vehicle trajectory data and graph Convolutional Networks

In recent years, increased attention has been given to understanding the spatial pattern of crashes in urban areas. Accurately capturing the spatial relationship between crash counts and variables requires extracting hidden information from multiple data sources. In this study, we propose a machine learning model to explore the spatial impact of activity patterns on spatially aggregated crash counts. Our paper introduces a two-step framework: (a) the Latent Dirichlet Allocation (LDA) model, an unsupervised method for mining hidden activity patterns from floating vehicle trajectory data, and (b) the Graph Convolutional Network (GCN) model, which builds the spatial relationship between multi-source data. The data and hidden activity patterns were aggregated into 175 Traffic Analysis Zones (TAZs) in San Francisco using spatial partitioning. The GCN model provided higher prediction accuracy than commonly used machine learning algorithms that did not consider combined spatial relationships and those that only considered traditional vehicle counts data. Furthermore, we used attribution algorithms to obtain the respective weight scores of each factor. Our results reveal that daily vehicle kilometers traveled, road density, population density, commercial activity during weekends, and residential activity during morning peak hours on weekdays are factors associated with crashes.

Biomimetic method of emergency life channel urban planning in Wuhan using slime mold networks

This study investigated a bio-inspired approach to planning optimal routes for urban hospital life channels to enable better responses to urban public security incidents. An experimental slime mold network and an origin-destination (OD) network model in which the nodes were tertiary hospitals in Wuhan were constructed. Correlation metrics of the two network models were used for network analysis and visualization. The experimental results showed that the slime mold network was better than the OD network in terms of global optimization. Furthermore, significant polarization of the influence value of urban hospital nodes resulted in a power-law distribution. This paper presents an urban planning method in which the biological mechanism of slime mold foraging is applied to construct shortest path networks in an emergency life channels. The results can be used to examine the relationship between urban roads and hospital nodes and the rational of global optimization distribution when planning the locations of new hospitals. A set of replicable and sustainable methods for conducting a biomimetic slime mold experiment to model real environments are presented. This approach provides a novel perspective for modeling emergency life channels.

Analysis of the injury severity of motor vehicle-pedestrian crashes at urban intersections using spatiotemporal logistic regression models

This paper conducted a comprehensive study on the injury severity of motor vehicle-pedestrian crashes at 489 urban intersections across a dense road network based on high-resolution accident data recorded by the police from 2010 to 2019 in Hong Kong. Given that accounting for the spatial and temporal correlations simultaneously among crash data can contribute to unbiased parameter estimations for exogenous variables and improved model performance, we developed spatiotemporal logistic regression models with various spatial formulations and temporal configurations. The results indicated that the model with the Leroux conditional autoregressive prior and random walk structure outperformed other alternatives in terms of goodness-of-fit and classification accuracy. According to the parameter estimates, pedestrian age, head injury, pedestrian location, pedestrian actions, driver maneuvers, vehicle type, first point of collision, and traffic congestion status significantly affected the severity of pedestrian injuries. On the basis of our analysis, a range of targeted countermeasures integrating safety education, traffic enforcement, road design, and intelligent traffic technologies were proposed to improve the safe mobility of pedestrians at urban intersections. The present study provides a rich and sound toolkit for safety analysts to deal with spatiotemporal correlations when modeling crashes aggregated at contiguous spatial units within multiple years.

The difference in quasi-induced exposure to crashes involving various hazardous driving actions

In quasi-induced exposure (QIE) theory, the presence of hazardous driving action is the typical determinant of the driver's responsibility for a crash. However, there is a lack of effort available to analyze the impacts of hazardous actions on the QIE estimate, which may result in estimation bias. Thus, the study aims to explore the difference in QIE to crashes involving various hazardous driving actions. Chi-square test is conducted to examine the consistency of non-responsible party distributions among the crashes involving various hazardous actions. Multinomial logit model and nested logit model are employed to identify the disparities of contributing factors to the actions. Results indicate that: 1) the estimated exposures appear to be inconsistent among the crashes with different hazardous actions, 2) driving cohorts have differential propensities of performing various hazardous actions, and 3) factors such as driver-vehicle characteristics, time, area, and environmental condition significantly affect the occurrence of hazardous actions while the directions and magnitude of the effects show great disparities for various actions. It can be concluded that the QIE estimates are significantly different for crashes involving various hazardous actions, which serves to highlight the importance of clarifying the specific hazardous actions for responsibility assignment in QIE theory.

Investigating speed-safety association: Considering the unobserved heterogeneity and human factors mediation effects

The relationship between mean speed and crash likelihood is unclear in the literature. The contradictory findings can be attributed to the masking effects of the confounding variables in this association. Moreover, the unobserved heterogeneity has almost been criticized as a reason behind the current inconclusive results. This research provides an effort to develop a model that analyzes the mean speed-crash frequency relationship by crash severity and type. Also, the confounding and mediation effects of the environment, driver, and traffic-related attributes have been considered. To this end, the loop detector and crash data were aggregated daily for rural multilane highways of Tehran province, Iran, covering two years, 2020-2021. The partial least squares path modeling (PLS-PM) was employed for crash causal analysis along with the finite mixture partial least squares (FIMIX-PLS) segmentation to account for potential unobserved heterogeneity between observations. The mean speed was negatively and positively associated with the frequency of property damage-only (PDO) and severe accidents, respectively. Moreover, driver-related variables, including tailgating, distracted driving, and speeding, played key mediation roles in associating traffic and environmental factors with the crash risk. The higher the mean speed and the lower the traffic volume, the higher odds of distracted driving. Distracted driving was, in turn, associated with the higher vulnerable road users (VRU) accidents and single-vehicle accidents, triggering a higher frequency of severe accidents. Moreover, lower mean speed and higher traffic volume were positively correlated with the percentage of tailgating violations, which, in turn, predicted multi-vehicle accidents as the main predictor of PDO crash frequency. In conclusion, the mean speed effects on the crash risk are entirely different for each crash type through distinct crash mechanisms. Hence, the distinct distribution of crash types in different datasets might have led to current inconsistent results in the literature.