An integrated framework for driving risk evaluation that combines lane-changing detection and an attention-based prediction model.

OBJECTIVE: In recent years, the increase in traffic accidents has emerged as a significant social issue that poses a serious threat to public safety. The objective of this study is to predict risky driving scenarios to improve road safety. METHODS: On the basis of data collected from naturalistic driving real-vehicle experiments, a comprehensive framework for identifying and analyzing risky driving scenarios, which combines an integrated lane-changing detection model and an attention-based long short-term memory (LSTM) prediction model, is proposed. The performance of the 4 machine learning methods on the CULane data set is compared in terms of model running time and running speed as evaluation metrics, and the ultrafast network with the best performance is selected as the method for lane line detection. We compared the performance of LSTM and attention-based LSTM on the basis of the prediction accuracy, recall, precision, and F1 value and selected the better model (attention-based LSTM) for risky scenario prediction. Furthermore, Shapley additive explanation analysis (SHAP) is used to understand and interpret the prediction results of the model. RESULTS: In terms of algorithm efficiency, the running time of the ultrafast lane detection network only requires 4.1 ms, and the average detection speed reaches 131 fps. For prediction performance, the accuracy rate of attention-based LSTM reaches 96%, the precision rate is 98%, the recall rate is 96%, and the F1 value is 97%. CONCLUSIONS: The improved attention-based LSTM model is significantly better than the LSTM model in terms of convergence speed and prediction accuracy and can accurately identify risky scenarios that occur during driving. The importance of factors varies by risky scenario. The characteristics of the yaw rate, speed stability, vehicle speed, acceleration, and lane change significantly influence the driving risk, among which lane change has the greatest impact. This study can provide real-time risky scenario prediction, warnings, and scientific decision guidance for drivers.

Evaluation of driver demand for in-vehicle information: An integrated method combining clustering and multivariate ordered probit model.

INTRODUCTION: The proper execution of driving tasks requires information support. While new technologies have increased the convenience of information access, they have also increased the risk of driver distraction and information overload. Meeting drivers' demands and providing them with adequate information are crucial to driving safety. METHODS: Based on a sample of 1,060 questionnaires, research on driving information demands is conducted from the perspective of drivers. A principal component analysis and the entropy method are integrated to quantify the driving information demands and preferences of drivers. The K-means classification algorithm is selected to classify the different types of driving information demands, including dynamic traffic information demands (DTIDs), static traffic information demands (STIDs), automotive driving status information demands (ATIDs), and total driving information demands (TDIDs). Fisher's least significant difference (LSD) is used to compare the differences in the numbers of self-reported crashes among different driving information demand levels. A multivariate ordered probit model is established to explore the potential factors that influence the different types of driving information demand levels. RESULTS: The DTID is the driver's most in-demand information type, and accordingly, gender, driving experience, average driving mileage, driving skills, and driving style significantly affect the driving information demand levels. Moreover, the number of self-reported crashes decreased as the DTID, ATID, and TDID levels decreased. CONCLUSION: Driving information demands are affected by a variety of factors. This study also provides evidence that drivers who have higher driving information demands are more likely to drive more carefully and safely than their counterparts who do not exhibit high driving information demands. PRACTICAL IMPLICATIONS: The results are indicative of the driver-oriented design of in-vehicle information systems and the development of dynamic information services as a way to avoid negative impacts on driving.

Do footbridge and underpass improve pedestrian safety? A Hong Kong case study using three-dimensional digital map of pedestrian network.

Hong Kong is a compact city with high activity and travel intensity. In the past decades, many footbridges and underpasses were installed to reduce the pedestrian-vehicle conflicts on urban roads. However, it is rare that the effects of configuration of pedestrian network on pedestrian crashes are investigated. In Hong Kong, many footbridges and underpasses are connected to major transport hubs and commercial building development and become parts of giant elevated and underground walkway systems. It is challenging to characterize such a complicated pedestrian network. In this study, a three-dimensional digital map is applied to estimate the connectivity and accessibility of pedestrian network, and measure the relationship between pedestrian network characteristics and pedestrian safety at the macroscopic level. Hence, the effects of footbridge and underpass on pedestrian safety are examined. For example, comprehensive built environment, pedestrian network, traffic, and crash data are aggregated to 379 grids (0.5 km × 0.5 km). Then, multivariate Poisson lognormal regression approach is applied to model fatal and severe injury (FSI) and slight injury pedestrian crashes, with which the effects of unobserved heterogeneity, spatial correlation, and correlation between crash counts are accounted. Results indicate that population density, traffic volume, walking trip, footpath density, node density, number of vertices per footpath segment, bus stop, metro exit, residential area, commercial area, and government and utility area are positively associated with pedestrian crashes. In contrast, average gradient, accessibility of footbridge, accessibility of underpass, and number of crossings per road segment are negatively associated with pedestrian crashes. In other word, pedestrian safety would be improved when footbridge and underpass are more accessible. Findings have implications for the design and planning of pedestrian network to promote walkability and improve pedestrian safety.

Investigation of intervention methods based on different leading roles in family regarding child road safety education: An experimental study.

Children are vulnerable to traffic injuries due to their low hazard perception. Previous studies have indicated that both parents and children have potential leading roles in safety education within the family. However, the effects of different leading roles (parents or children) on the hazard perception of children have not yet been revealed, and interactive education with children in the leading roles could also be an important means to enhance children's road safety. To fill this gap, based on constructivism theory and the Feynman learning method, this study proposed two methods of enhancing children's hazard perception based on different leading roles in the family regarding child road safety education and investigated the effectiveness of the above intervention methods. Thirty sets of parents and children participated in this experiment and were divided into three groups. The children received one of three different road safety interventions: a constructivism intervention, a parental guidance intervention or a children's Feynman learning intervention. Compared with the constructivism intervention, the hazard perception of children who received road safety educations within the family were significantly improved; these children were more sensitive to potential traffic hazard factors and presented better visual search patterns. A comparative analysis showed that the two educational interventions based on different leading roles in the family regarding child road safety education were not identical with respect to effectiveness. The children's Feynman learning intervention had a more significant effect than the parental guidance intervention. The findings of this study provide insightful information for safety education researchers, governments, educators and families with children.

Diagnostic analysis of environmental factors affecting the severity of traffic crashes: From the perspective of pedestrian-vehicle and vehicle-vehicle collisions.

OBJECTIVES: Traffic crashes under low-visibility conditions are frequent and serious. The aim of this study was to investigate how the road environment affects the severity of pedestrian-vehicle and vehicle-vehicle collisions under low-visibility conditions. METHODS: The injury severity of pedestrian-vehicle collisions and vehicle-vehicle collisions under low-visibility conditions was set as the dependent variable and divided into 2 categories: "killed or severe injury collision" and "slight injury collision." Ten variables, including environment conditions, road traffic facility status, collision characteristics, and road attributes, were selected as independent factors according to the existing research and the traffic collision data set. Based on 656 valid pedestrian-vehicle collisions and 1,430 valid vehicle-vehicle collisions under low-visibility conditions, 2 random parameter logit models were established to evaluate the impacts of influencing factors on the severity of pedestrian-vehicle collisions and vehicle-vehicle collisions, in which the effect of unobserved heterogeneity was accounted for. RESULTS: The results show that visibility, presence of a roadside protection, road type, road pavement condition, and road alignment were significant factors affecting the severity of pedestrian-vehicle collisions. In addition, the presence of a median divider, location of the collision, road type, road surface condition, road pavement condition, and road alignment were significant factors affecting the severity of vehicle-vehicle collisions. Furthermore, the injury severity of both pedestrian-vehicle collisions and vehicle-vehicle collisions under low-visibility conditions on highways, poor road pavement, and non-straight-line sections was more likely to be fatal or serious. CONCLUSION: These results have implications for the design of more effective strategies to reduce casualties from traffic crashes under low-visibility conditions.

The trade-off between safety and time in the red light running behaviors of pedestrians: A random regret minimization approach.

Pedestrian safety has been a major concern in Hong Kong, where walking is an important access mean to urban transportation services and pedestrian-vehicle conflicts are prevalent. Red light running violation of pedestrians is a leading cause of pedestrian-vehicle crashes at the signal intersections. It is necessary to examine the possible factors including personal characteristics and road environments that affect the propensities of red light running violation of pedestrians. Therefore, effective traffic control and enforcement measures can be implemented to deter against the red light running behaviors of pedestrians. This study attempts to examine the roles of trade-off between safety and time, as well as situational features and personality traits, in the red light running behaviors of pedestrians using a stated preference survey method. Then, a regret-based panel mixed multinomial logit model is established for the association measure between propensities of red light running violation and possible factors, with which the effects of unobserved heterogeneity and correlation in the choices between different scenarios of the same person are considered. Results indicate that the choice decision of pedestrians are more sensitive to a reduction in time loss, as compared to the equivalent increase in safety risk. In addition, the safety versus time trade-off may vary between pedestrian groups. Furthermore, presence and type of another violator also significantly affect the propensities of red light running violation. Such findings are indicative to effective policy interventions that can deter against the red light running behaviors of vulnerable pedestrian groups. Therefore, overall pedestrian safety level can be improved in the long term.

Propensities of red light running of pedestrians at the two-stage crossings with split pedestrian signal phases.

Two-stage crossing with a median refuge island is commonly installed at the busy urban signalized intersections. To accommodate for the high traffic flow in different directions, split phasing is often applied for pedestrians' right of way of the two crossing stages. Previous studies mainly focus on the time delay, capacity and operation efficiency of two-stage crossings. It is rare that safety of two-stage crossings is investigated. Crossing behaviors and propensities of red light running at the two crossing stages (i.e. from the curbside to a central island, and then to another side of the road) are different from that of single stage crossing. Also, there could be interferences in the crossing behaviors and situational features between the two stages. This study aims to identify the personal characteristics, traffic attributes and environmental factors that affect the red light running propensities of pedestrians at the two-stage crossings, based on the video observation surveys at six urban signal intersections in Hong Kong. Random parameter logit regression approach is applied to measure the association between possible factors and propensities of red light running of pedestrians, with which the effect of unobserved heterogeneity is accounted. Results indicate that, other than the pedestrians' characteristics, pedestrian signal of the second stage, maximum waiting time and traffic flow significantly affect the propensity of red light running in the first stage. Also, there are significant interaction effects between pedestrians' characteristics and situational features on the propensity. On the other hand, pedestrians' waiting time before crossing the first stage significantly affects the propensity of red light running in the second stage. Findings are indicative to the design of pedestrian crossing, signal time plan and effective enforcement and education strategies that can deter against the red light running behaviors of pedestrians. Therefore, safety of two-stage signalized crossings can be enhanced.

Investigation of the Contributory Factors to the Guessability of Traffic Signs.

Traffic signs play an important role in traffic management systems. A variety of studies have focused on drivers' comprehension of traffic signs. However, the travel safety of prospective users, which has been rarely mentioned in previous studies, has attracted considerable attention from relevant departments in China. With the growth of international and interregional travel demand, traffic signs should be designed more universally to reduce the potential risks to drivers. To identify key factors that improve prospective users' sign comprehension, this study investigated eight factors that may affect users' performance regarding sign guessing. Two hundred and one Chinese students, all of whom intended to be drivers and none of whom had experience with daily driving after obtaining a license or visits to Germany, guessed the meanings and rated the sign features of 54 signs. We investigated the effects of selected user factors on their sign guessing performance. Additionally, the contributions of four cognitive design features to the guessability of traffic signs were examined. Based on an analysis of the relationships between the cognitive features and the guessability score of signs, the contributions of four sign features to the guessability of traffic signs were examined. Moreover, by exploring Chinese users' differences in guessing performance between Chinese signs and German signs, cultural issues in sign design were identified. The results showed that vehicle ownership and attention to traffic signs exerted a significant influence on guessing performance. As expected, driver's license training and the number of years in college were dominant factors for guessing performance. With regard to design features, semantic distance and confidence in guessing were two dominant factors for the guessability of signs. We suggest improving the design of signs by including vivid, universal symbols. Thus, we provide several suggestions for designing more user-friendly signs.