Prediction model of urban epidemic prevention and control based on multivariate Bi-A-LSTM

The Novel Coronavirus outbreak has since spread rapidly across the globe, seriously affecting the quality of life and economic development of all countries. By predicting the epidemic situation in a certain area, government departments can take corresponding measures to prevent and control the epidemic according to the forecast results. However, with the implementation of various prevention and control measures, vaccination and the impact of virus mutation, the traditional epidemic model and regression model have limitations in the prediction performance, there is a large error in the prediction accuracy. To improve the prediction accuracy, this paper proposes an Attentional mechanism-based LSTM network (A-LSTM), which takes the multiple factors affecting the epidemic trend as the input of the model. Bidirectional A-LSTM is constructed by a-LSTM neural network unit, and the best fitting degree is obtained by training in bidirectional A-LSTM network. Multivariate Bi-A-LSTM epidemic prevention and control prediction model was obtained. In this paper, the actual data as reference, the average absolute error, average absolute percentage error, root mean square error as the evaluation index of the model, and the improved model and other models are compared, experimental results show that the improved model is more accurate than the traditional model in prediction accuracy. © 2022 IEEE.

Short-term passenger volume forecast and model analysis of Beijing public transport

The prediction of bus passenger volume is the fundamental research content of bus transfer optimization. In order to get more accurate passenger volume data and improve the utilization efficiency of urban traffic resources, according to randomness, time-varying and uncertainty of public transport passenger volume in Beijing, combined with the current new coronavirus pneumonia epidemic, this paper collected the relevant data of Beijing in the past 40 years, and predicted and analyzed them from four dimensions of public transport, urban scale and residents' economic level, taxi and sudden health events by BP neural network and regression analysis. The results show that BP neural network has good prediction results, and BP neural network is suitable for large sample size, which needs to fit or predict complex nonlinear relationships. © 2021 SPIE

New COVID-19 variant (B.1.1.7): Forecasting the occasion of virus and the related meteorological factors.

BACKGROUND: World Health Organization has reported fifty countries have now detected the new coronavirus (B.1.1.7 variant) since a couple of months ago. In Indonesia, the B.1.1.7 cases have been found in several provinces since January 2021, although they are still in a lower number than the old variant of COVID-19. Therefore, this study aims to create a forecast analysis regarding the occasions of COVID-19 and B.1.1.7 cases based on data from the 1st January to 18th March 2021, and also analyze the association between meteorological factors with B.1.1.7 incidences in three different provinces of Indonesia such as the West Java, South Sumatra and East Kalimantan. METHODS: We used the Autoregressive Moving Average Models (ARIMA) to forecast the number of cases in the upcoming 14 days and the Spearman correlation analysis to analyze the relationship between B.1.1.7 cases and meteorological variables such as temperature, humidity, rainfall, sunshine, and wind speed. RESULTS: The results of the study showed the fitted ARIMA models forecasted there was an increase in the daily cases in three provinces. The total cases in three provinces would increase by 36% (West Java), 13.5% (South Sumatra), and 30% (East Kalimantan) as compared with actual cases until the end of 14 days later. The temperature, rainfall and sunshine factors were the main contributors for B.1.1.7 cases with each correlation coefficients; r = -0.230; p < 0.05, r = 0.211; p < 0.05 and r = -0.418; p < 0.01, respectively. CONCLUSIONS: We recapitulated that this investigation was the first preliminary study to analyze a short-term forecast regarding COVID-19 and B.1.1.7 cases as well as to determine the associated meteorological factors that become primary contributors to the virus spread.

SUIHTER: a new mathematical model for COVID-19. Application to the analysis of the second epidemic outbreak in Italy.

The COVID-19 epidemic is the latest in a long list of pandemics that have affected humankind in the last century. In this paper, we propose a novel mathematical epidemiological model named SUIHTER from the names of the seven compartments that it comprises: susceptible uninfected individuals (S), undetected (both asymptomatic and symptomatic) infected (U), isolated infected (I), hospitalized (H), threatened (T), extinct (E) and recovered (R). A suitable parameter calibration that is based on the combined use of the least-squares method and the Markov chain Monte Carlo method is proposed with the aim of reproducing the past history of the epidemic in Italy, which surfaced in late February and is still ongoing to date, and of validating SUIHTER in terms of its predicting capabilities. A distinctive feature of the new model is that it allows a one-to-one calibration strategy between the model compartments and the data that are made available daily by the Italian Civil Protection Department. The new model is then applied to the analysis of the Italian epidemic with emphasis on the second outbreak, which emerged in autumn 2020. In particular, we show that the epidemiological model SUIHTER can be suitably used in a predictive manner to perform scenario analysis at a national level.