To enhance the safety of vulnerable pedestrians, considerable investments of time and effort in pedestrian safety facilities and zones should be made. More certain and severe punishments should be also given for the traffic violations that increase injury severity of pedestrian crashes. Furthermore, central and local governments should play a cooperative role to reduce pedestrian fatalities. Practical applications: Based on our study results, we suggest policy directions to enhance pedestrian safety.

Obtaining the trajectories of all vehicles in congested traffic is essential for analyzing traffic dynamics. To conduct an effective analysis using trajectory data, a framework is needed to efficiently and accurately extract the data. Unfortunately, obtaining accurate trajectories in congested traffic is challenging due to false detections and tracking errors caused by factors in the road environment, such as adjacent vehicles, shadows, road signs, and road facilities. Unmanned aerial vehicles (UAVs), with incorporating machine learning and image processing, can mitigate these difficulties by their ability to hover above the traffic. However, research is lacking regarding the extraction and evaluation of vehicle trajectories in congested traffic. In this study, we propose and compare two learning-based frameworks for detecting vehicles: the aggregated channel feature (ACF), which is based on human-made features, and the faster region-based convolutional neural network (Faster R-CNN), which is based on data-driven features. We extend the detection results to extract vehicle trajectories in congested traffic conditions from UAV images. To remove the errors associated with tracking vehicles, we also develop a postprocessing method based on motion constraints. Then, we conduct detailed performance analyses to confirm the feasibility of the proposed framework on a congested expressway in Korea. The results show that Faster R-CNN outperforms the ACF in images with large objects and in those with small objects if sufficient data are provided. This framework extracts the vehicle trajectories with high precision, making them available for analyzing traffic dynamics based on the training of just a small number of positive samples. The results of this study provide a practical guideline for building a framework to extract vehicles trajectories based on given conditions.

This study analyzes 86,622 commercial motor vehicle (CMV) crashes (large truck, bus and taxi crashes) in South Korea from 2010 to 2014. The analysis recognizes the hierarchical structure of the factors affecting CMV crashes by examining eight factors related to individual crashes and six additional upper level factors organized in two non-nested groups (company level and regional level factors). The study considers four different crash severities (fatal, major, minor, and no injury). The company level factors reflect selected characteristics of 1,875 CMV companies, and the regional level factors reflect selected characteristics of 230 municipalities. The study develops a single-level ordinary ordered logit model, two conventional multilevel ordered logit models, and a cross-classified multilevel ordered logit model (CCMM). As the study develops each of these four models for large trucks, buses and taxis, 12 different statistical models are analyzed. The CCMM outperforms the other models in two important ways: 1) the CCMM avoids the type I statistical errors that tend to occur when analyzing hierarchical data with single-level models; and 2) the CCMM can analyze two non-nested groups simultaneously. Statistically significant factors include taxi company's type of vehicle ownership and municipality's level of transportation infrastructure budget. An improved understanding of CMV related crashes should contribute to the development of safety countermeasures to reduce the number and severity of CMV related crashes.

As the importance of public transportation increases, the management of bus-involved crashes has become a crucial issue for traffic safety. However, there are relatively few studies on crash severity for buses in South Korea. This study investigated factors that influence the severity of injuries that occur in local bus crashes. The study used commercial vehicle crash data from a 5-year period from 2010 through 2014 in South Korea. To determine unobserved regional effects on crash severity, a hierarchical ordered model was applied to the analysis. Individual crash characteristics were set to lower-level variables, and regional characteristics were adopted as upper-level variables. At the lower level, the factors affecting severity of injuries included vehicle speed, vehicle age, road alignment, surface status, road class, and traffic light installation, as found in previous studies. At the upper level, the factors included pavement, emergent medical environment, traffic rate of compliance, and ratio of elderly in the community. There was a 5.1% unobserved variation between regions from the intraclass correlation analysis. The validity of a hierarchical model for local bus crashes was verified by applying the model to other long-distance buses, and it appeared there were no regional effects. This study found a regional effect for local bus crash severity, and thus this factor is important when developing prevention plans to reduce local bus crashes. These results contribute to the study of traffic safety.

Because of the development of scientific technology, drivers now have access to a variety of information to assist their decision making. In particular, an accurate prediction of travel time is valuable to drivers, who can use it to choose a route or decide on departure time. Although many researchers have sought to enhance their accuracy, such predictions are often limited by errors that result from the lagged pattern of predicted travel time, the use of nonrepresentative samples for making predictions, and the use of inefficient and nontransferable models. The proposed model predicts travel times on the basis of the k nearest neighbor method and uses data provided by the vehicle detector system and the automatic toll collection system. By combining these two sets of data, the model minimizes the limitations of each set and enhances the prediction's accuracy. Criteria for traffic conditions allow the direct use of data acquired from the automatic toll collection system as predicted travel time. The proposed model's predictions are compared with the predictions of other models by using actual data to show that the proposed model predicts travel times much more accurately. The proposed model's predictions of travel time are expected to be free from the problems associated with an insufficient number of samples. Further, unlike the widely used artificial neural network and Kalman filter methods, the proposed model does not require long training programs, so the model is easily transferable.

No abstract

This study analyzes a skip-stop strategy considering four types of train choice behavior with smartcard data. The proposed model aims to minimize total travel time with realistic constraints such as facility condition, operational condition, and travel behavior. The travel time from smartcard data is decomposed by two distributions of the express trains and the local trains using a Gaussian mixture model. The utility parameters of the train choice model are estimated with the decomposed distribution using the multinomial logit model. The optimal solution is derived by a genetic algorithm to designate the express stations of the Bundang line in the Seoul metropolitan area. The results indicate the travel times of the transfer-based strategy and the high ridership-based strategy are estimated to be 21.2 and 19.7 min/person, respectively. Compared to the travel time of the current system, the transfer-based strategy has a 5.8% reduction and the high ridership-based strategy has a 12.2% reduction. For the travel behavior-based strategy, the travel time was estimated to be 18.7 minutes, the ratio of the saved travel time is 17.9%, and the energy consumption shows that the travel behavior-based strategy consumes 305,437 (kWh) of electricity, which is about 12.7% lower compared to the current system.

No abstract