The COVID-19 global pandemic has had a significant impact on mass travel. We examined the risk of transmission of COVID-19 infection between subway commuters using the Susceptible Exposed Infected Recovered (SEIR) model. The model considered factors that may influence virus transmission, namely subway disinfection, ventilation capacity, average commuter spacing, single subway journey time, COVID-19 transmission capacity, and dynamic changes in passenger numbers. Based on these parameters, above a certain threshold (25 min), the risk of infection for susceptible people increased significantly as journey time increased. Average distance between commuters and levels of ventilation and disinfection were also important influencing factors. Meanwhile, the model also indicated that the risk of infection varied at different times of the day. Therefore, this paper recommends strengthening ventilation and disinfection in the carriages and limiting the time of single journeys, with an average distance of at least 1 m between passengers. In this light, subway commuters need to take proactive precautions to reduce their risk of COVID-19 infection. Also, the results show the importance of managing subway stations efficiently during epidemic and post-epidemic eras.

Due to the wide applications of deep learning in the field of urban rail transit passenger flow forecasting, the selection problem of training samples has become increasingly more worthy of researchers' attention, as it is closely related to urban rail transit passenger flow time series. Therefore, it is necessary to study the distribution characteristics of the contribution degree of the training sample to guide sample selection in the deep learning training process. In this study, based on the prediction accuracy and the sample contribution degree, the optimal sample contribution combination algorithm (GWO-SCBP) was ultimately generated by the grey wolf optimizer (GWO) and error back propagation (EBP) algorithms. The contribution of training samples for each station of the Xi'an metro network was calculated and analyzed. The results show that the sample contribution is not only related to the distance between the sample and predicted value, but is also closely related to the station flow characteristics. By classifying the network stations and fitting the contribution degree of the central station of each type of station, linear equations of sample contribution degree were obtained, and the R 2 values attained at least 0.65, indicating a good fitting effect. INDEX TERMS Rail transit, passenger flow forecast, sample selection, grey wolf optimizer algorithm, artificial neural network.

No abstract

No abstract

No abstract