Investigating driver injury severity patterns in rollover crashes using support vector machine models

Rollover crash is one of the major types of traffic crashes that induce fatal injuries. It is important to investigate the factors that affect rollover crashes and their influence on driver injury severity outcomes. This study employs support vector machine (SVM) models to investigate driver injury severity patterns in rollover crashes based on two-year crash data gathered in New Mexico. The impacts of various explanatory variables are examined in terms of crash and environmental information, vehicle features, and driver demographics and behavior characteristics. A classification and regression tree (CART) model is utilized to identify significant variables and SVM models with polynomial and Gaussian radius basis function (RBF) kernels are used for model performance evaluation. It is shown that the SVM models produce reasonable prediction performance and the polynomial kernel outperforms the Gaussian RBF kernel. Variable impact analysis reveals that factors including comfortable driving environment conditions, driver alcohol or drug involvement, seatbelt use, number of travel lanes, driver demographic features, maximum vehicle damages in crashes, crash time, and crash location are significantly associated with driver incapacitating injuries and fatalities. These findings provide insights for better understanding rollover crash causes and the impacts of various explanatory factors on driver injury severity patterns.     

A framework for and empirical study of algorithms for traffic assignment

Traffic congestion is an issue in most cities worldwide. Transportation engineers and urban planners develop various traffic management projects in order to solve this issue. One way to evaluate such projects is traffic assignment (TA). The goal of TA is to predict the behaviour of road users for a given period of time (morning and evening peaks, for example). Once such a model is created, it can be used to analyse the usage of a road network and to predict the impact of implementing a potential project. The most commonly used TA model is known as user equilibrium, which is based on the assumption that all drivers minimise their travel time or generalised cost. In this study, we consider the static deterministic user equilibrium TA model.The constant growth of road networks and the need of highly precise solutions (required for select link analysis, network design, etc.) motivate researchers to propose numerous methods to solve this problem. Our study aims to provide a recommendation on what methods are more suitable depending on available computational resources, time and requirements on the solution. In order to achieve this goal, we implement a flexible software framework that maximises the usage of common code and, hence, ensures comparison of algorithms on common ground. In order to identify similarities and differences of the methods, we analyse groups of algorithms that are based on common principles. In addition, we implement and compare several different methods for solving sub-problems and discuss issues related to accumulated numerical errors that might occur when highly accurate solutions are required.     

An efficient utilization of intermittent surface–satellite optical links by using mass storage device embedded in satellites

Recently, earth observation system by using satellite network has attracted much attention due to its wide coverage and disaster resistance. Although the system is useful for collecting various data, which have an effect on a natural disaster, ecology and so forth, earth observation satellite hardly send the collected observation data to the ground station. This is because that the earth observation satellite needs to orbit near surface of the earth to get high-precision data, and it limited the time that can be used to send the observed data traffic to the ground station. Additionally, the amount of the observed data drastically increase in these days. Thus, we focus on the data relay satellite using optical communication in this network. By relaying observed data to traffic to the relay satellite, which has geostationary orbit, it is possible to increase the chance of sending data for the observation satellite due to the wide coverage of the relay satellite. In addition, laser light that is used in optical communication in satellite network has high frequency and it can deliver large data compared with radio wave. However, laser light is greatly influenced by atmosphere, and optical link capacity between satellite and ground station drastically changes according to weather condition. Therefore, we propose a new data traffic control method to use the network constructed by satellites which has mass storage device effectively according to the condition of optical downlink between satellite and optical ground station. The effectiveness of the proposed method is evaluated with numerical result.     

A generic approach for examining the effectiveness of traffic control devices in school zones

The effectiveness and performance of traffic control devices in school zones have been impacted significantly by many factors, such as driver behavioral attributes, roadway geometric features, environmental characteristics, weather and visibility conditions, region-wide traffic regulations and policies, control modes, etc. When deploying traffic control devices in school zones, efforts are needed to clarify: (1) whether traffic control device installation is warranted; and (2) whether other device effectively complements this traffic control device and strengthens its effectiveness. In this study, a generic approach is developed to examine and evaluate the effectiveness of various traffic control devices deployed in school zones through driving simulator-based experiments. A Traffic Control Device Selection Model (TCDSM) is developed and two representative school zones are selected as the testbed in Beijing for driving simulation implementation to enhance its applicability. Statistical analyses are conducted to extract the knowledge from test data recorded by a driving simulator. Multiple measures of effectiveness (MOEs) are developed and adopted including average speed, relative speed difference, and standard deviation of acceleration for traffic control device performance quantification. The experimental tests and analysis results reveal that the appropriateness of the installation of certain traffic control devices can be statistically verified by TCDSM. The proposed approach provides a generic framework to assess traffic control device performance in school zones including experiment design, statistical formulation, data analysis, simulation model implementation, data interpretation, and recommendation development.     

Development and application of an integrated traffic simulation and multi-driving simulators

Professional virtual reality experiment tools, including driving simulators and traffic simulators, have their strengths and weaknesses. The integration of the two simulators will enhance the ability of both traffic modeling and driving simulation and present a new area of applications. This paper develops, implements, and validates an experimental platform that integrated a traffic simulator with multiple driving simulators (TSMDS). As a connected multi-user framework that allows multiple drivers who are simultaneously handling many driving simulators, it not only allows driver behavior experiments to be more accurate, controlled, and versatile but also simulates special driving behavior or multi-vehicle interactions under more realistic traffic flow environments. To validate the performance of TSMDS, 27 drivers were recruited to attend the lane changing experiments at a recurring on-ramp bottleneck and left-turn experiments at a two-phase signalized intersection in Shanghai. Both experiments required several drivers to drive the TSMDS and fulfill several complicated lane changing/crossing behaviors through their interaction. The results show that both the participants’ response and lane changing/crossing data that were obtained from the experiment are consistent with the field observation, which confirms the validity of the integrated platform.     

Association between increase in fixed penalties and road safety outcomes: A meta-analysis

Studies that have evaluated the association between increases in traffic fine amounts (fixed penalties) and changes in compliance with road traffic law or the number of accidents are synthesised by means of meta-analysis. The studies were few and different in many respects. Nine studies were included in the meta-analysis of changes in compliance. Four studies were included in the meta-analysis of changes in accidents. Increasing traffic fines was found to be associated with small changes in the rate of violations. The changes were non-linear. For increases up to about 100%, violations were reduced. For larger increases, no reduction in violations was found. A small reduction in fatal accidents was associated with increased fixed penalties, varying between studies from less than 1–12%. The main pattern of changes in violations was similar in the fixed-effects and random-effects models of meta-analysis, meta-regression and when simple (non-weighted) mean values were computed. The main findings are thus robust, although most of the primary studies did not control very well for potentially confounding factors. Summary estimates of changes in violations or accidents should be treated as provisional and do not necessarily reflect causal relationships.     

Are electric self-balancing scooters safe in vehicle crash accidents?

With the pressing demand of environmentally friendly personal transportation vehicles, mobility scooters become more and more popular for the short-distance transportation. Similar to pedestrians and bicyclists, scooter riders are vulnerable road users and are expected to receive severe injuries during traffic accidents. In this research, a MADYMO model of vehicle–scooter crash scenarios is numerically set up. The model of the vehicle with the scenario is validated in pedestrian–vehicle accident investigation with previous literatures in terms of throwing distance and HIC₁₅ value. HIC₁₅ values gained at systematic parametric studies. Injury information from various vehicle crashing speeds (i.e. from 10 m/s to 24 m/s), angles (i.e. from 0 to 360°), scooter's speeds (i.e. from 0 m/s to 4 m/s), contact positions (i.e. left, middle and right bumper positions) are extracted, analyzed and then compared with those from widely studied pedestrian–vehicle and bicycle–vehicle accidents. Results show that the ESS provides better impact protection for the riders. Riding ESS would not increase the risk higher than walking at the same impact conditions in terms of head injury. The responsible reasons should be the smaller friction coefficient between the wheel-road than the heel-road interactions, different body gestures leading to different contact positions, forces and timing. Results may shed lights upon the future research of mobility scooter safety analysis and also the safety design guidance for the scooters.     

Air traffic control: Ocular metrics reflect cognitive complexity

The objective of the study was to evaluate effects of complexity on cognitive workload in a simulated air traffic control conflict detection task by means of eye movements recording. We manipulated two complexity factors, convergence angle and aircrafts minimum distance at closest approach, in a multidimensional workload assessment method based on psychophysiological, performance, and subjective measures. Conflict trials resulted more complex and time-consuming than no conflicts, requiring more frequent fixations and saccades. Moreover, large saccades showed reduced burst power with higher task complexity. A motion-based and a ratio-based strategy were suggested for conflicts and no conflicts on the basis of ocular metrics analysis: aircrafts differential speed and distance to convergence point at trial start were considered determinant for strategy adoption.Relevance to industryEye metrics measurement for online workload assessment enhances better identification of workload-inducing scenarios and adopted strategy for traffic management. System design, as well as air traffic control operators training programs, might benefit from on line workload measurement.     

Ocular movements under taskload manipulations: Influence of geometry on saccades in air traffic control simulated tasks

Traffic geometry is a factor that contributes to cognitive complexity in air traffic control. In conflict‐detection tasks, geometry can affect the attentional effort necessary to correctly perceive and interpret the situation; online measures of situational workload are therefore highly desirable. In this study, we explored whether saccadic movements vary with changes in geometry. We created simple scenarios with two aircraft and simulated a conflict detection task. Independent variables were the conflict angle and the distance to convergence point. We hypothesized lower saccadic peak velocity (and longer duration) for increasing complexity, that is, for increasing conflict angles and for different distances to convergence point. Response times varied accordingly with task complexity. Concerning saccades, there was a decrease of peak velocity (and a related increase of duration) for increased geometry complexity for large saccades (>15°). The data therefore suggest that geometry is able to influence “reaching” saccades and not “fixation” saccades. © 2011 Wiley Periodicals, Inc.     

A combined M5P tree and hazard-based duration model for predicting urban freeway traffic accident durations

The duration of freeway traffic accidents duration is an important factor, which affects traffic congestion, environmental pollution, and secondary accidents. Among previous studies, the M5P algorithm has been shown to be an effective tool for predicting incident duration. M5P builds a tree-based model, like the traditional classification and regression tree (CART) method, but with multiple linear regression models as its leaves. The problem with M5P for accident duration prediction, however, is that whereas linear regression assumes that the conditional distribution of accident durations is normally distributed, the distribution for a “time-to-an-event” is almost certainly nonsymmetrical. A hazard-based duration model (HBDM) is a better choice for this kind of a “time-to-event” modeling scenario, and given this, HBDMs have been previously applied to analyze and predict traffic accidents duration. Previous research, however, has not yet applied HBDMs for accident duration prediction, in association with clustering or classification of the dataset to minimize data heterogeneity. The current paper proposes a novel approach for accident duration prediction, which improves on the original M5P tree algorithm through the construction of a M5P-HBDM model, in which the leaves of the M5P tree model are HBDMs instead of linear regression models. Such a model offers the advantage of minimizing data heterogeneity through dataset classification, and avoids the need for the incorrect assumption of normality for traffic accident durations. The proposed model was then tested on two freeway accident datasets. For each dataset, the first 500 records were used to train the following three models: (1) an M5P tree; (2) a HBDM; and (3) the proposed M5P-HBDM, and the remainder of data were used for testing. The results show that the proposed M5P-HBDM managed to identify more significant and meaningful variables than either M5P or HBDMs. Moreover, the M5P-HBDM had the lowest overall mean absolute percentage error (MAPE).