Ranking sites and identifying high-crash risk locations based on various safety performance measures (e.g. expected crash frequency) are among the key tasks of the safety management program, enabling an effective allocation of funds for safety improvement projects. While several studies have discussed the issues relating to the hotspot identification process at a micro-level (e.g., intersections or highway segments), less attention is given to the macro-level hotspot identification issue: how to identify areas or regions with the highest risk of crashes. In this research, we introduce a Bayesian multilevel (hierarchical) model for estimating the regional differences while controlling for other important site attributes. The proposed method is illustrated using a case study on railway grade crossings in Canada. While accommodating the spatial dependencies of crash risk, our method allows a fair comparison of different regions by adjusting for the effect of covariates such as traffic exposure. In particular, we compute pairwise probabilities of crash risk for each province in Canada compared to all others. We are therefore able to draw inferences about regional safety performances under similar circumstances. Our findings indicate the need for further investigation to identify the possible reasons for inter-region variations in grade crossing safety across Canada. Our approach could be useful to guide safety policy development and resource allocation.
Winter road maintenance (WRM) has been shown to have significant benefits of improving road safety and reducing traffic delay caused by adverse weather conditions. It has also been suggested that WRM is also beneficial in terms of reducing vehicular air emissions and fuel consumptions because snow and ice on road surface often cause the drivers to reduce their vehicle speeds or to switch to high gears, thus decreasing fuel combustion efficiency. However, there has been very limited information about the underlying relationship, which is important for quantifying this particular benefit of a winter road maintenance program. This research is focused on establishing a quantitative relationship between winter road surface conditions and vehicular air emissions. Speed distribution models are developed for the selected Ontario highways using data from 22 road sites across the province of Ontario, Canada. The vehicular air emissions under different road surface conditions are calculated by coupling the speed models with the engine emission models integrated in the emission estimation model - Motor Vehicle Emission Simulator (MOVES). It was found that, on the average, a 10% improvement in road surface conditions could result in approximately 0.6% to 2% reduction in air emissions. Application of the proposed methodology is demonstrated through a case study to analyse the air emission and energy consumption effects under specific weather events.
Although accident frequencies at railway grade crossings have shown a decreasing trend over the last two decades (partly due to implemented safety improvements and technological advances), safety at grade crossings is still a major concern since crossing accidents are usually associated with devastating consequences. This paper investigates the effect of various site attributes on railway crossing safety outcomes using recent Canada wide data from a 6-year period (2008–2013). The new data sets allow adjusting previous accident models according to latest circumstances (e.g., vehicles’ improved safety features) affecting safety dynamics at crossings. Employing Bayesian hierarchical models including the non-conventional Poisson-Weibull model, different safety performance functions were separately developed for crossings with the following major warning systems: (1) flashing light and bell (FLB), (2) flashing light, bell, and gate (FLBG), (3) standard reflectorized crossing sign (SRCS), and (4) standard reflectorized crossing sign and stop sign (SRCS & STOP). Among other findings, the results indicated that traffic exposure (product of train and vehicle), number of lanes, whistle prohibition, train speed, and road speed were the most important factors affecting accident frequencies at Canadian railway crossings. It should be also noted that safety performance functions vary, in terms of independent variables and their associated coefficients, between the aforementioned warning devices.
This paper presents the results of a new deep learning model for traffic signal control. In this model, a novel state space approach is proposed to capture the main attributes of the control environment and the underlying temporal traffic movement patterns, including time of day, day of the week, signal status, and queue lengths. The performance of the model was examined over nine weeks of simulated data on a single intersection and compared to a semi-actuated and fixed time traffic controller. The simulation analysis shows an average delay reductions of 32% when compared to actuated control and 37% when compared to fixed time control. The results highlight the potential for deep reinforcement learning as a signal control optimization method.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
