No abstract

The transmission of pollutants in buses has an important impact on personal exposure to airborne particles and spread of the COVID-19 epidemic in enclosed spaces. We conducted the following real-time field measurements inside buses: CO2, airborne particle concentration, temperature, and relative humidity data during peak and off-peak hours in spring and autumn. Correlation analysis was adopted to evaluate the dominant factors influencing CO2and particle mass concentrations in the vehicle. The cumulative personal exposure dose to particulate matter and reproduction number were calculated for passengers on a one-way trip. The results showed the in-cabin CO2concentrations, with 22.11% and 21.27% of the total time exceeding 1,000 ppm in spring and autumn respectively. In-cabin PM2.5 mass concentration exceeded 35 μm/m3 by 57.35% and 86.42% in spring and autumn, respectively. CO2 concentration and the cumulative number of passengers were approximately linearly correlated in both seasons, with R value up to 0.896. The cumulative number of passengers had the most impact on PM2.5 mass concentration among tested parameters. The cumulative personal exposure dose to PM2.5 during a one-way trip in autumn was up to 43.13 μg. The average reproductive number throughout the one-way trip was 0.26; it was 0.57 under the assumed extreme environment. The results of this study provide an important basic theoretical guidance for the optimization of ventilation system design and operation strategies aimed at reducing multi-pollutant integrated health exposure and airborne particle infection (such as SARS-CoV-2) risks.

No abstract

Improving the accuracy of box office revenue forecasts is conducive to stimulating the creation, market investment, infrastructure construction, and rational allocation of public resources in the film market, as well as promoting social welfare and cultural prosperity. Since the existing box office revenue prediction algorithm does not consider film industry structure, the prediction accuracy is not satisfying. This paper firstly builds a two-stage human-machine collaborative feature processing framework. In the first stage, based on the box office data, the regression decision tree algorithm is used to process all the box office features preliminarily and delete the unimportant features automatically. In the second stage, feature processing is coupled with the built Artificial Neural Network (ANN). In this stage, the features processed by the machine are manually classified, and multiple, incompatible feature sets are divided. After designing the incompatible set network pruning algorithm, the neural network is pruned. We construct the data set with a total of 7098 movies crawled online on four platforms. Numerical experimental results show that the Mean Absolute Error (MAE) of the two-stage algorithm is significantly better than the baseline model, which can effectively reduce the noise caused by encoding between incompatible features directly, improve the prediction accuracy of ANN, accelerate the forward inference speed of ANN and reduce the consumption of computing resources.

Among most public transport modes, the frequent start-stop urban bus has the most complex micro-environment. Indoor environment quality, airflow patterns, etc. has not been fully understood yet inside buses. In addition, under COVID-19 pandemic, it had been proved aerosol transmission risk might be enhanced inside the buses. Usually, carbon dioxide (CO2) could be considered the index of ventilation effect in enclosed environment, airborne particles are viral carriers. Thus, accurate forecasting of the two abovementioned key pollutants become important. The study analysed the CO2 and airborne particle dispersion inside a bus at the downtown areas of Dalian, China by employing field measurement at spring and autumn, 2021. Temperature, relative humidity, CO2 and airborne particle concentrations were logged by sensors at sampling points respectively, passengers onboard were counted manually. Correlation analysis was conducted and two empirical models for evaluating CO2 and airborne particle were concluded based on the measurement data. From preliminary results, transient concentration of pollutant is almost linearly correlated with cumulative and instant numbers of passenger respectively, with Pearson correlation coefficient larger than 0.8336 for CO2 and 0.8424 for PM2.5. The purpose of the study is to reflect environmental quality inside the bus and provide inspiration into pollution control strategies in buses.