Operational factor analysis of the aggressive taxi speeders using random parameters Bayesian LASSO modeling approach

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.

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.

Research on run-time risk evaluation method based on operating scenario data for autonomous train

Recent years witness the focus of the research of next-generation railways on risk situation awareness and safety decision-making to enhance the autonomy of unmanned trains. However, complex environmental factors make it difficult to assess the risks of train operation. Thus, it is of great necessity to clearly monitor the scenario parameters under which the train control system is designed to work, and to infer real-time risk through the collected scenario data. This paper first clarifies the key scenario parameters that need to be collected during the operation according to the concept of Operational Design Domain (ODD) and operating scenario. The key parameters and their dependencies are used to derive the Dynamic Bayesian Network (DBN) structure. Second, for data probability uncertainty, Fuzzy Set Theory is introduced, within the framework of which a fuzzy dynamic reasoning process is presented by monitoring the scenario data deviation. Finally, a case of real-time risk evaluation and analysis of the accident of Singapore MTR is explicated to demonstrate its contribution to operating data-based runtime risk analysis.

Lane-based Distance-Velocity model for evaluating pedestrian-vehicle interaction at non-signalized locations

Pedestrian vehicle conflicts at non-signalized crosswalks are a world-wide safety concern. Although the "pedestrian priority" policy is applied in some regions to improve pedestrian safety, its effect needs further investigation. This study proposes the Lane-based Distance-Velocity model (LDV) to investigate pedestrian-vehicle interaction at non-signalized crosswalks. Compared with the DV model, the LDV model considers the lateral distance between vehicles and pedestrians. Therefore, the LDV model extends the application of the DV model by allowing it to be applied not only on one-lane streets to multi-lane streets. The conflict severities of pedestrian-vehicle interaction in the LDV model are classified into four categories: safe-passage, mild-interaction, potential-conflict and potential-collision. Based on that, pedestrian crossing decisions are graded as safe-crossing, risky-crossing, and dangerous-crossing. The experimental data are collected at a non-signalized crosswalk through drone footage collected in Xi'an City (China) with a Machine Vision Intelligent Algorithm. The model is tested through a case study to evaluate pedestrian crossing safety when interacting with private cars and taxis. Results from the case study suggest that the proposed model works well in the pedestrian-vehicle interaction analysis. Firstly, 87.9% of drivers are willing to provide right-of-way to pedestrians when they have enough time to react and yield. Then, both the DV model and LDV model have reached consistent conclusions: the deliberate violation rate (DVR) of taxi drivers is 22.64%, which is double that of private car drivers. Last, taxis commit a higher percentage of pedestrians' dangerous or risky crossing situations than private cars. Relevant government departments can utilize the results of this study to manage urban traffic better and improve pedestrian safety.

A Simulation-based Study of the Effect of Brake Light Flashing Frequency on Driver Brake Behavior from the Perspective of Response Time

To prevent vehicle crashes, studies have proposed the use of flashing signals (brake lights or other light indicators) to improve the driver’s response time when the leading vehicle is braking. However, there are no consistent results on the ideal flashing frequency of the brake lights. This study aimed to investigate different brake light flashing frequencies to assess their impact on braking response time. Twenty-four participants aged 25 to 30 were recruited. Two driving speed environments (50 and 80 km/h), three deceleration rates (0.25, 0.6, and 1 g), and four brake light flashing frequencies (0, 2, 4, and 7 Hz) were examined. Braking response time, average braking force, and braking response time ratio were used to evaluate the driving behavior. The results showed that the braking response time and average braking force were affected by the deceleration rate in the 50 km/h driving environment. In the 50 and 80 km/h driving environments, although there were no significant differences among the three deceleration rates, the braking response time decreased by 3–7% under the flashing brake light condition. These findings can be used as a reference for safety designs as well as future studies on driving behavior.

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

Analyzing speed mean and variance is vital to safety management in urban roadway networks. However, modeling speed mean and variance on structured roads could be influenced by the spatial effects, which are rarely addressed in the existing studies. The inadequacy may lead to biased conclusions when considering vehicle speed as a surrogate safety measure. The current study focuses on developing a Bayesian modeling approach with three types of spatial effects, i.e., spatial correlation, spatial heterogeneity, and spillover effect. To capture the spatial correlation, the study employs the intrinsic conditional autoregressive (ICAR) models, spatial lag models (SLM), and spatial error models (SEM). Spatial heterogeneity and spillover effect are considered by the random parameters approach and spatially lagged covariates (SLCs). Speed data are collected from the float cars running on 134 urban arterials in Chengdu, China. The results indicate that the random parameters ICAR model with SLCs (RPICAR-SLC) outperforms others in terms of goodness-of-fit, accuracy, and efficiency for modeling speed mean, while the random parameters ICAR model (RPICAR) is the best for modeling speed variance. Moreover, RPICAR-SLC and RPICAR models are beneficial to address spatial correlation of residuals, explaining the unobserved influence among the observations, and are less likely to cause biased or overestimated parameters. The study also discusses how traffic conditions, road characteristics, traffic management strategies, and facilities on roadway networks influence speed mean and variance. The findings highlight the importance of multi-type spatial effects on modeling speed mean and variance along the structured roadways.

Assessing Factors Associated with Non-Fatal Injuries from Road Traffic Accidents among Malaysian Adults: A Cross-Sectional Analysis of the PURE Malaysia Study

Non-fatal injuries (NFIs) due to road traffic accidents (RTAs) are a public health problem worldwide that significantly impacts the population morbidity and healthcare costs. As the demands for vehicles in developing countries, such as Malaysia, is increasing annually, the present study aims to determine the prevalence and factors associated with NFIs due to RTAs among Malaysia’s adult population. Methods: This was a cross-sectional study involving 15,321 participants from the Prospective Urban and Rural Epidemiological (PURE) study conducted in Malaysia. Participants reported whether they had experienced an NFI that limited their normal activities within the past 12 months. Data on risk factors for NFIs were elicited. Multiple logistic regression models were fitted to identify the associated factors. Results: Overall, 863 participants (5.6% of 15,321) reported at least 1 NFI in the past 12 months, with 303 caused by RTAs (35.1%), 270 caused by falls (31.3%) and 290 attributed to other causes (33.6%). The factors associated with higher odds of sustaining an NFI due to an RTA were being male (adjusted odd ratio (AOR) 2.08; 95% CI 1.33–3.26), having a primary (2.52; 1.40–4.55) or secondary (2.64; 1.55–4.49) level of education, being overweight to obese (1.40; 1.01–1.94), being currently employed (2.03; 1.31–3.13) and not practicing a noon nap/siesta (1.38; 1.01–1.89). Conclusions: The occurrence of NFIs due to RTAs is highly preventable with strategic planning aimed at reducing the risk of RTAs among the Malaysian population. Interventions focusing on protecting road users, especially those who drive two-wheelers, with proactive road safety awareness and literacy campaigns, combined with strict enforcement of the existing traffic laws and behavioural modifications, may reduce the risk of NFIs following RTAs.

Towards Sustainable Road Safety in Saudi Arabia: Exploring Traffic Accident Causes Associated with Driving Behavior Using a Bayesian Belief Network

Understanding the causes and effects of road accidents is critical for developing road and action plans in a country. The causation hypothesis elucidates how accidents occur and may be applied to accident analysis to more precisely anticipate, prevent, and manage road safety programs. Driving behavior is a critical factor to consider when determining the causes of traffic accidents. Inappropriate driving behaviors are a set of acts taken on the roadway that can result in aberrant conditions that may result in road accidents. In this study, using Al-Ahsa city in Saudi Arabia’s Eastern Province as a case study, a Bayesian belief network (BBN) model was established by incorporating an expectation–maximization algorithm. The model examines the relationships between indicator variables with a special focus on driving behavior to measure the uncertainty associated with accident outcomes. The BBN was devised to analyze intentional and unintentional driving behaviors that cause different types of accidents and accident severities. The results showed when considering speeding alone, there is a 26% likelihood that collision will occur; this is a 63% increase over the initial estimate. When brake failure was considered in addition to speeding, the likelihood of a collision jumps from 26% to 33%, more than doubling the chance of a collision when compared to the initial value. These findings demonstrated that the BBN model was capable of efficiently investigating the complex linkages between driver behavior and the accident causes that are inherent in road accidents.

Investigating the Effect of Social and Cultural Factors on Drivers in Malaysia: A Naturalistic Driving Study

Road accidents are increasing every year in Malaysia, and it is always challenging to collect reliable pre-crash data in the transportation community. Existing studies relied on simulators, police crash reports, questionnaires, and surveys to study Malaysia’s drivers’ behavior. Researchers previously criticized such methods for being biased and unreliable. To fill in the literature gap, this study presents the first naturalistic driving study in Malaysia. Thirty drivers were recruited to drive an instrumented vehicle for 750 km while collecting continuous driving data. The data acquisition system consists of various sensors such as OBDII, lidar, ultrasonic sensors, IMU, and GPS. Irrelevant data were filtered, and experts helped identify safety criteria regarding multiple driving metrics such as maximum acceptable speed limits, safe accelerations, safe decelerations, acceptable distances to vehicles ahead, and safe steering behavior. These thresholds were used to investigate the influence of social and cultural factors on driving in Malaysia. The findings show statistically significant differences between drivers based on gender, age, and cultural background. There are also significant differences in the results for those who drove on weekends rather than weekdays. The study presents several recommendations to various public and governmental sectors to help prevent future accidents and improve traffic safety.

Pediatric Traffic Injuries on Halloween in the United Kingdom: Prevalence and Injury Severity

The study results serve as a reminder for parents, children, and drivers to be alert to the danger of traffic crashes on Halloween. The aim of this study was to examine whether Halloween is associated with a higher incidence of traffic injuries and whether traffic injuries sustained on Halloween are more severe than those sustained on other days. The U.K. STATS19 database, including the data of all road traffic crashes occurring from 1990 to 2017, was employed. A total of 73,587 pediatric traffic casualties (involving pedestrians, cyclists, and moped riders) were included. Between 17:00 and 19:00 (17:00~18:59) on Halloween, the number of casualties was higher than that on other public holidays and usual days. The logistic regression model revealed that, between 17:00 and 18:00 (17:00~17:59), the risk of being killed or seriously injured on Halloween was 34.2% higher (odds ratio = 1.342; 95% CI = 1.065–1.692) than that on other days. Pediatric crashes occurring on Halloween are associated with a higher number of injuries and increased injury severity.

Exploring the Impact of Driver Adherence to Speed Limits and the Interdependence of Roadside Collisions in an Urban Environment: An Agent-Based Modelling Approach

Roadside collisions are a significant problem faced by all countries. Urbanisation has led to an increase in traffic congestion and roadside vehicle collisions. According to the UK Government’s Department for Transport, most vehicle collisions occur on urban roads, with empirical evidence showing drivers are more likely to break local and fixed speed limits in urban environments. Analysis conducted by the Department for Transport found that the UK’s accident prevention measure’s cost is estimated to be £33bn per year. Therefore, there is a strong motivation to investigate the causes of roadside collisions in urban environments to better prepare traffic management, support local council policies, and ultimately reduce collision rates. This study utilises agent-based modelling as a tool to plan, experiment and investigate the relationship between speeding and vehicle density with collisions. The study found that higher traffic density results in more vehicles travelling at a slower speed, regardless of the degree to which drivers comply with speed restrictions. Secondly, collisions increase linearly as speed compliance is reduced for all densities. Collisions are lowest when all vehicles comply with speed limits for all densities. Lastly, higher global traffic densities result in higher local traffic densities near-collision sites across all adherence levels, increasing the likelihood of congestion around these sites. This work, when extended to real-world applications using empirical data, can support effective road safety policies.