With the increasing demand of hazardous material (Hazmat), traffic accidents occurred frequently during Hazmat transportation, which had caused widespread concern in communities. Therefore, a good understanding of Hazmat transportation accident characteristics and contributing factors is of practical importance. In this study, 1721 Hazmat accidents that have occurred during road transportation for the period 2014–2017 in China were examined, and a random-parameters ordered probit model was established to explore the influence of contributing factors on the severity of accidents by accounting for unobserved heterogeneity in the data. Both the injuries and the number of people evacuated were considered as the indicator of accident severity and investigated, respectively. Results show that higher injury severity is likely to be associated with type of Hazmat (compressed gas, explosive, and poison), misoperation, driver fatigue, speeding, tunnel, slope, county road, dry road surface, winter, dark, more than two vehicles, rear end crash, and explosion. As for the correlation between risk factors and the severity of evacuation, type of Hazmat (compressed gas, explosive, and poison), quantity of Hazmat (10–39 t), misoperation, county road, dry road surface, weekdays, dusk, explosion significantly contribute to increasing the severity of evacuation of Hazmat accidents.

In many related works, nominal classification algorithms ignore the order between injury severity levels and make sub-optimal predictions. Existing ordinal classification methods suffer rank inconsistency and rank non-monotonicity. The aim of this paper is to propose an ordinal classification approach to predict traffic crash injury severity and to test its performance over existing machine learning classification methods. First, we compare the performance of the neural network, XGBoost, and SVM classifiers in injury severity prediction. Second, we utilize a severity category-combination method with oversampling to relieve the class-imbalance problem prevalent in crash data. Third, we take advantage of probability calibration and the optimal probability threshold moving to improve the prediction ability of ordinal classification. The proposed approach can satisfy the rank consistency and rank monotonicity requirement and is proved to be superior to other ordinal classification methods and nominal classification machine learning by statistical significance test. Important factors relating to injury severity are selected based on their permutation feature importance scores. We find that converting severity levels into three classes, minor injury, moderate injury, and serious injury, can substantially improve the prediction precision.

Escalator-related injuries have become an important issue in daily metro operation. To reduce the probability and severity of escalator-related injuries, this study conducted a probability and severity analysis of escalator-related injuries by using a Bayesian network to identify the risk factors that affect the escalator safety in metro stations. The Bayesian network structure was constructed based on expert knowledge and Dempster–Shafer evidence theory, and further modified based on conditional-independence test. Then, 950 escalator-related injuries were used to estimate the posterior probabilities of the Bayesian network with expectation–maximization (EM) algorithm. The results of probability analysis indicate that the most influential factor in four passenger behaviors is failing to stand firm (p = 0.48), followed by carrying out other tasks (p = 0.32), not holding the handrail (p = 0.23), and another passenger’s movement (p = 0.20). Women (p = 0.64) and elderly people (aged 66 years and above, p = 0.48) are more likely to be involved in escalator-related injuries. Riding an escalator with company (p = 0.63) has a relatively high likelihood of resulting in escalator-related injuries. The results from the severity analysis show that head and neck injuries seem to be more serious and are more likely to require an ambulance for treatment. Passengers who suffer from entrapment injury tend to claim for compensation. Severe injuries, as expected, significantly increase the probability of a claim for compensation. These findings could provide valuable references for metro operation corporations to understand the characteristics of escalator-related injuries and develop effective injury prevention measures.

The safety situation of hazardous materials (hazmat) accidents during road transportation in China is severe and very serious accidents occurred frequently. Such accidents not only have a huge impact on the environment but also have serious consequences for people and the economy, such as fires and explosions. Therefore, it is necessary to understand the characteristics and laws of road transport accidents of hazmat systematically. This paper investigated 2777 hazmat transportation accidents in China from 2013 to 2019 to identify the characteristics, consequences, and causes of the accident. The results show that August (10.05%) and December (9.76%) are the peak periods of hazmat transportation accidents, while most hazmat transportation accidents occurred in the early morning (6:00–9:00 a.m.) and at noon (9:00 a.m.–12:00 p.m.) hours. For the geographical location, the accidents mainly occurred in the east China (34.35%) and the northwest China areas (14.87%). The main types of hazmat transportation accidents were rollover (35.36%), rear-end (22.58%), and collision (14.87%), where the probability of a major leak was high. The most common hazmat transportation accidents involve gas (17.79%), flammable liquid (56.07%), and corrosive substance (12.28%). The most common consequences of the hazmat transportation accidents were leakage (80.34%), followed by fire release (8.32%) and explosion release (2.34%). Human factor (26.74%) is the main cause of hazmat transportation accidents. These findings could help hazmat transportation managers and planners develop appropriate measures for improving hazmat transportation safety.

Crash injuries not only result in huge property damages, physical distress, and loss of lives, but arouse a reduction in roadway capacity and delay the recovery progress of traffic to normality. To assess the resilience of post-crash tunnel traffic, two novel concepts, i.e., surrogate resilience measure (SRM) and injury-based resilience (IR), were proposed in this study. As a special kind of semi-closed infrastructure, urban tunnels are more vulnerable to traffic crashes and injuries than regular roadways. To assess the IR of the post-crash roadway tunnel traffic system, an over-one-year accident dataset comprising 8621 crashes in urban roadway tunnels in Shanghai, China was utilized. A total of 34 variables from 11 factors were selected to establish the IR assessment indicator system. Methodologically, to tackle the skewness issue in the dataset, a binary skewed logit (Scobit) model was found to be superior to a conventional logistic model and subsequently adopted for further analysis. The estimated results showed that 15 variables were identified to be significant in assessing the IR of the roadway tunnels in Shanghai. Finally, the formula for calculating the IR levels of post-crash traffic systems in tunnels was given and would be a helpful tool to mitigate potential trends in crash-related resilience deterioration. The findings of this study have implications for bridging the gap between conventional traffic safety research and system resilience modeling.

It is of great significance to identify dangerous driving behavior by extracting vehicle trajectory through video monitoring to ensure highway traffic safety. At present, there is no suitable method to identify dangerous driving vehicles accurately based on trajectory data. This paper aims to develop a detection algorithm for identifying dangerous driving behavior based on the road scene, which is mainly composed of imbalanced dangerous driver detection and labeling, extraction of driving behavior characteristics and the establishment of a recognition model about dangerous driving behavior. Firstly, this paper defines the risk index of the vehicle related to five types of dangerous driving behavior: dangerous following, lateral deviation, frequent acceleration and deceleration, frequent lane change, and forced insertion. Then, a variety of methods, including K-means clustering, local factor anomaly algorithm, isolation forest and OneClassSVM, are used to carry out anomaly detection on the risk indicators of drivers, and the optimal method is proposed to identify dangerous drivers. Then, the speed and acceleration of each vehicle are Fourier transformed to obtain the characteristics of the driver’s driving behavior. Finally, considering the imbalanced characteristic of the analyzed dataset with a very small proportion of dangerous drivers, this paper compares a variety of imbalanced classification algorithms to optimize the recognition performance of dangerous driving behavior. The results show that the OneClassSVM detection algorithm can be effectively applied to the identification of dangerous driving behavior. The improved Xgboost algorithm performs best for the extremely imbalanced data of dangerous drivers.