Search

Since 2020, COVID-19 has repeatedly arisen around the world, which has had a significant impact on the global economy and culture. The prediction of the COVID-19 epidemic will help to deal with the current epidemic and similar risks that may arise in the future. So, this paper proposes a hybrid prediction model based on particle swarm optimization variational mode decomposition (PSO-VMD), Long Short-Term Memory Network (LSTM) and AdaBoost algorithm. To address the issue of determining the optimal number of modes K and the penalty factor (α) in the variational mode decomposition (VMD), an adaptive value for particle swarm optimization (PSO) is proposed. Specifically, the weighted average sample entropy of the relevant coefficients is utilized to determine the adaptive value. First, the epidemic data are decomposed into multiple modal components, known as intrinsic mode functions (IMFs), using PSO-VMD. These components, along with policy-based factors, are integrated to form a multivariate forecast dataset. Next, each IMF is predicted using AdaBoost-LSTM. Finally, the prediction results of all the IMF components are reconstructed to obtain the final prediction result. Our proposed method is validated by the cumulative confirmed data of Hubei and Hebei provinces. Specifically, in the case of cumulative confirmation data, the coefficient of determination ( R 2 ) of the mixed model is increased compared to the control model, and the average mean absolute error (MAE) and root mean square error (RMSE) decreased. The experimental results demonstrate that the VMD–AdaBoost–LSTM model achieves the highest prediction accuracy, thereby offering a new approach to COVID-19 epidemic prediction. [ABSTRACT FROM AUTHOR]

Since 2020, COVID-19 has repeatedly arisen around the world, which has had a significant impact on the global economy and culture. The prediction of the COVID-19 epidemic will help to deal with the current epidemic and similar risks that may arise in the future. So, this paper proposes a hybrid prediction model based on particle swarm optimization variational mode decomposition (PSO-VMD), Long Short-Term Memory Network (LSTM) and AdaBoost algorithm. To address the issue of determining the optimal number of modes K and the penalty factor (α) in the variational mode decomposition (VMD), an adaptive value for particle swarm optimization (PSO) is proposed. Specifically, the weighted average sample entropy of the relevant coefficients is utilized to determine the adaptive value. First, the epidemic data are decomposed into multiple modal components, known as intrinsic mode functions (IMFs), using PSO-VMD. These components, along with policy-based factors, are integrated to form a multivariate forecast dataset. Next, each IMF is predicted using AdaBoost-LSTM. Finally, the prediction results of all the IMF components are reconstructed to obtain the final prediction result. Our proposed method is validated by the cumulative confirmed data of Hubei and Hebei provinces. Specifically, in the case of cumulative confirmation data, the coefficient of determination (R2) of the mixed model is increased compared to the control model, and the average mean absolute error (MAE) and root mean square error (RMSE) decreased. The experimental results demonstrate that the VMD–AdaBoost–LSTM model achieves the highest prediction accuracy, thereby offering a new approach to COVID-19 epidemic prediction.

The global outbreak of the COVID-19 epidemic has caused a considerable impact on humans, which expresses the urgency and importance of studying its impacts. Previous studies either frequently use aggregated research methods of statistic data or stay during COVID-19. The afterward impacts of COVID-19 on human behaviors need to be explored further. This article carries out a non-aggregated study methodology in human geography based on big data from social media comments and takes Nanjing, China, as the research case to explore the afterward impact of the COVID-19 epidemic on the spatial behavior of urban tourists. Precisely, we propose the methodology covers two main aspects regarding travel contact trajectory and spatial trajectory. In contact trajectory, we explore three indicators—Connection Strength, Degree Centrality, and Betweenness Centrality—of the collected attractions. Then, in spatial trajectory, we input the results from contact trajectory into ArcGIS by using the Orientation–Destination Model and Standard Deviation Ellipse to explore the influences on the spatial pattern. By setting up comparative groups for the three periods of before, during, and after the COVID-19 in Nanjing, this study found that, in the post-epidemic era, (1) the spatial behavior of urban tourists showed a state of overall contraction; (2) the objects of contraction changed from urban architectural attractions to urban natural attractions; (3) the form of contraction presents concentric circles with the central city (Old City of Nanjing) as the core; (4) the direction of contraction heads to the large-scale natural landscape in the central city, which highlights the importance of green open spaces in the post-epidemic era.

The global outbreak of the COVID-19 epidemic has caused a considerable impact on humans, which expresses the urgency and importance of studying its impacts. Previous studies either frequently use aggregated research methods of statistic data or stay during COVID-19. The afterward impacts of COVID-19 on human behaviors need to be explored further. This article carries out a non-aggregated study methodology in human geography based on big data from social media comments and takes Nanjing, China, as the research case to explore the afterward impact of the COVID-19 epidemic on the spatial behavior of urban tourists. Precisely, we propose the methodology covers two main aspects regarding travel contact trajectory and spatial trajectory. In contact trajectory, we explore three indicators—Connection Strength, Degree Centrality, and Betweenness Centrality—of the collected attractions. Then, in spatial trajectory, we input the results from contact trajectory into ArcGIS by using the Orientation–Destination Model and Standard Deviation Ellipse to explore the influences on the spatial pattern. By setting up comparative groups for the three periods of before, during, and after the COVID-19 in Nanjing, this study found that, in the post-epidemic era, (1) the spatial behavior of urban tourists showed a state of overall contraction; (2) the objects of contraction changed from urban architectural attractions to urban natural attractions; (3) the form of contraction presents concentric circles with the central city (Old City of Nanjing) as the core; (4) the direction of contraction heads to the large-scale natural landscape in the central city, which highlights the importance of green open spaces in the post-epidemic era. [ABSTRACT FROM AUTHOR]