The real-time performance and accuracy of traffic flow prediction directly affect the efficiency of traffic flow guidance systems, and traffic flow prediction is a hotspot in the field of intelligent transportation. To further improve the accuracy of short-term traffic flow prediction, a short-term traffic flow prediction model based on traffic flow time series analysis, and an improved long short-term memory network (LSTM) is proposed. First, perform time series analysis on traffic flow data and perform smoothing and standardization processing to obtain a stable time series as model input data, which can improve the accuracy of model training and eliminate the impact of a wide range of feature values. Then, an improved LSTM model based on LSTM and bidirectional LSTM networks are established. Combining the advantages of sequential data and the long-term dependence of forwarding LSTM and reverse LSTM, the bidirectional long-term memory network (BILSTM) is integrated into the prediction model. The first layer of the LSTM network learns and predicts the input time series and further learns and trains through the bidirectional LSTM network to effectively overcome the large prediction errors. Finally, the performance of the proposed method is evaluated by comparing the predicted results with actual traffic data. The model that is proposed in this paper is compared with the long short-term memory network (LSTM) model and the bidirectional long-term memory network (BILSTM) model. The results demonstrate that the proposed method outperforms both compared methods in terms of accuracy and stability.

In order to clearly understand the risky riding behaviors of electric bicycles (e-bikes) and analyze the riding characteristics, we review the research results of the e-bike risky riding behavior from three aspects: the characteristics and causes of e-bike accidents, the characteristics of users’ traffic behavior, and the prevention and intervention of traffic accidents. The analysis results show that the existing research methods on risky riding behavior of e-bikes mainly involve questionnaire survey methods, structural equation models, and binary probability models. The illegal occupation of motor vehicle lanes, over-speed cycling, red-light running, and illegal manned and reverse cycling are the main risky riding behaviors seen with e-bikes. Due to the difference in physiological and psychological characteristics such as gender, age, audiovisual ability, responsiveness, patience when waiting for a red light, congregation, etc., there are differences in risky cycling behaviors of different users. Accident prevention measures, such as uniform registration of licenses, the implementation of quasi-drive systems, improvements of the riding environment, enhancements of safety awareness and training, are considered effective measures for preventing e-bike accidents and protecting the traffic safety of users. Finally, in view of the shortcomings of the current research, the authors point out three research directions that can be further explored in the future. The strong association rules between risky riding behavior and traffic accidents should be explored using big data analysis. The relationships between risk awareness, risky cycling, and traffic accidents should be studied using the scales of risk perception, risk attitude, and risk tolerance. In a variety of complex mixed scenes, the risk degree, coupling characteristics, interventions, and the coupling effects of various combination intervention measures of e-bike riding behaviors should be researched using coupling theory in the future.

Short-term traffic speed prediction is fundamental to intelligent transportation systems (ITS), and the accuracy of the model largely determines the performance of real-time traffic control and management. In this study, a short-term traffic speed prediction method based on the spatial-temporal analysis of traffic flow and a combined deep-learning model, and a hybrid spatial-temporal feature selection algorithm (STFSA) of a convolutional neural network–gated recurrent unit (CNN-GRU)) is initially developed. Specifically, the STFSA is firstly employed to reconstruct the spatial-temporal matrix of traffic speed based on temporal continuity and spatial characteristics, and then this matrix is considered as the input feature of the prediction model. After this, the nonlinear fitting ability of the CNN is adopted to extract deep features from the convolutional and pooling layers for model training. Finally, by combining the timing and long-range dependence of the captured data with the forward GRU and the reverse GRU, the accuracy of the prediction result is further improved. The validity of the proposed model can be verified by comparing the prediction results with the actual traffic data. Accordingly, in the case study, the performance is compared with various benchmark methods under the same prediction scenario, verifying the superiority of the proposed model.

The effect of aggressive driving behavior on driver’s injury severity is analyzed by considering a comprehensive set of variables at highway-rail grade crossings in the US. In doing so, we are able to use a mixed logit modelling approach; the study explores the determinants of driver-injury severity with and without aggressive driving behaviors at highway-rail grade crossings. Significant differences exist between drivers’ injury severity with and without aggressive driving behaviors at highway-rail grade crossings. The level of injury for younger male drivers increases a lot if they are with aggressive driving behavior. In addition, driving during peak-hour is found to be a statistically significant predictor of high level injury severity with aggressive driving behavior. Moreover, environmental factors are also found to be statistically significant. The increased level of injury severity accidents happened for drivers with aggressive driving behavior in the morning peak (6-9 am), and the probability of fatality increases in both snow and fog condition. Driving in open space area is also found to be a significant factor of high level injury severity with aggressive driving behaviors. Bad weather conditions are found to increase the probability of drivers’ high level injury severity for drivers with aggressive driving behaviors.

Electric vehicles (EVs) endow great potentials for future transportation systems, while efficient charge scheduling strategies are crucial for improving profits and mass adoption of EVs. Two critical and open issues concerning EV charging are how to minimize the total charging cost (Objective 1) and how to minimize the peak load (Objective 2). Although extensive efforts have been made to model EV charging problems, little information is available about model properties and efficient algorithms for dynamic charging problems. This paper aims to fill these gaps. For Objective 1, we demonstrate that the greedy-choice property applies, which means that a globally optimal solution can be achieved by making locally optimal greedy choices, whereas it does not apply to Objective 2. We propose a non-myopic charging strategy accounting for future demands to achieve global optimality for Objective 2. The problem is addressed by a heuristic algorithm combining a multi-commodity network flow model with customized bisection search algorithm in a rolling horizon framework. To expedite the solution efficiency, we derive the upper bound and lower bound in the bisection search based on the relationship between charging volume and parking time. We also explore the impact of demand levels and peak arrival ratios on the system performance. Results show that with prediction, the peak load can converge to a globally optimal solution, and that an optimal look-ahead time exists beyond which any prediction is ineffective. The proposed algorithm outperforms the state-of-the-art algorithms, and is robust to the variations of demand and peak arrival ratios.