In this work, to clarify the impact of electric bicycle drivers’ risky driving behavior on driving safety, we used multiple regression analysis methods combined with a questionnaire survey of residents of the city of Guilin, China. We studied the impact of the two dimensions of safety knowledge and safety attitude on risky driving behavior, and identified the differences in the impact of these two dimensions from the perspective of personal characteristics. Through modeling analysis, we found that “responsible attitude” and “group behavior attitude” explain 62.4% of the variation in aggressive behavior; 48.5% of the variation in negligent behavior is caused by “age”, “safety knowledge” and “responsible attitude”; and 52% of the variation in violations is caused by “age”, “violation attitude” and “group behavior attitude”. The results show that “group behavior attitude” affects the occurrence of aggression; that safety knowledge has a significant negative impact on unintentional negligence but has no significant effect on deliberate violations and aggression; and that the difference in risky driving behavior is mainly manifested in “age”, “gender”, “violation” and “accident experience”.

To objectively evaluate the influence of the subsidence area of a manhole cover on the riding behavior of two-wheeler riders in urban bicycle lanes, a probability model of riding behavior of two-wheeler riders was established. The main factors influencing the probability of riding behaviors under the condition of the subsidence area of a manhole cover are investigated. Based on the field data of 10 survey sections in Guilin, the regression models between the selected probability of independent riding behavior, combined riding behavior and the main influencing factors are respectively established by using the multiple regression analysis method. The results show that the selected probabilities of deceleration riding behavior and original-speed riding behavior have a linear regression relationship with the subsidence depth of the manhole cover and the lane integrity. The subsidence depth of manhole covers is positively correlated with the probability of deceleration riding behavior and negatively correlated with the probability of original-speed riding behavior; lane integrity is positively correlated with both the probability of deceleration riding behavior and the probability of original-speed riding behavior. The data goodness-of-fit value for the relevant influence factors in the two models is 0.941 and 0.900, respectively. The probability of acceleration riding behavior has a linear regression relationship with the lane integrity and section flow. Lane integrity is negatively correlated with the probability of acceleration riding behavior and positively correlated with section flow. The data goodness-of-fit value for the relevant influence factors is 0.821. The probabilities of straight riding behavior and detour riding behavior have a linear regression relationship with the subsidence depth of manhole covers and the minor width of the flat part. The subsidence depth of a manhole cover is negatively correlated with the probability of straight riding behavior and positively correlated with the probability of detour riding behavior. The minor width of flat part is negatively correlated with the probability of straight riding behavior and positively correlated with the probability of detour riding behavior. The data goodness-of-fit value for the relevant influence factors in the two models is 0.601 and 0.603, respectively. The results provide the theoretical basis for the evaluation of the severity and optimization design of the subsidence of manhole covers in urban bicycle lanes.

In order to quickly and accurately identify the lane changing intention of vehicles, and to deeply consider the time series characteristics of vehicle driving processes and the interactive effects between vehicles, a lane changing intention recognition model, namely, Model_TA, was constructed by combining the time series feature extraction ability of the encoder in the Transformer model, the bidirectional gating mechanism of the bidirectional gated recurrent unit, and the additive attention mechanism. The performance of the Model_TA model was trained and validated on the I-80 dataset in NGSIM. The experimental results showed that the accuracy of model intent recognition was 97.01%, which was 20.3%, 4.73%, and 1.73% higher than that of SVM, LSTM, and Transformer models, respectively; the prediction accuracy at 2.0 s, 2.5 s, and 3.0 s is 90.15%, 84.58%, and 83.13%, respectively, which is better than similar models. It is proved that the model can better predict the lane changing intention of vehicles.

This paper focuses on predicting road passenger probability and optimizing taxi driving routes based on trajectory big data. By utilizing clustering algorithms to identify key passenger points, a method for calculating and predicting road passenger probability is proposed. This method calculates the passenger probability for each road segment during different time periods and uses a BiLSTM neural network for prediction. A passenger-seeking recommendation model is then constructed with the goal of maximizing passenger probability, and it is solved using the NSGA-II algorithm. Experiments are conducted on the Chengdu taxi trajectory dataset, using MSE as the metric for model prediction accuracy. The results show that the BiLSTM prediction model improves prediction accuracy by 9.67% compared to the BP neural network and by 6.45% compared to the LSTM neural network. The proposed taxi driver passenger-seeking route selection method increases the average passenger probability by 18.95% compared to common methods. The proposed passenger-seeking recommendation framework, which includes passenger probability prediction and route optimization, maximizes road passenger efficiency and holds significant academic and practical value.