STG-Net: A COVID-19 prediction network based on multivariate spatio-temporal information

Song, Yucheng; Chen, Huaiyi; Song, Xiaomeng; Liao, Zhifang; Zhang, Yan

doi:10.1016/j.bspc.2023.104735

Cited by 5 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The edges are constructed based on geographical similarities and proximity of each region. Song et al [19] developed STG-Net, a model that combines spatiotemporal features in a joint optimization method to make prediction of confirmed cases.…”

Section: Spatiotemporal Features Based Modelsmentioning

confidence: 99%

An Inner-Inter City Graph Neural Network for Predicting the Course of COVID-19 Cases

Ndiaye,

Liu,

Cui

et al. 2024

Preprint

View full text Add to dashboard Cite

Highly infectious diseases, for instance, the recent novel corona virus pandemic (COVID-19) have impacted millions of lives in the globe. From its early stage, it's clear that its transmission is closely related to the crowd mobility. However, research on the predictive power of city level mobility is lacking. To fill this gap, in this paper, we propose the Inner-Inter city Learner (IIL), a method based on the high correlation between human interaction and the new cases, to conduct short and midterm predictions of the COVID-19 cases at a city level. In term of design, IIL is composed of two main components: an inter city transmission learner and an inner city propagation pattern learner. In the first module, we specially generate graphs based on the mobility between cities. Using graph neural networks fed with the city level mobility graphs, the model learns how the transmission pattern in a city is impacted by its neighborhood cities. And in the second part, capitalizing in the highly contagious nature of the virus, we use the human interactions within the cities to capture the invariant features that directly correlate with the spread. In addition, to account for the limited inner mobility data, we employed the model agnostic meta learning to transfer the features common to all cities. We conduct various experiments and compare our methods with the state-of-art baselines. The results show the superiority of our method in various forecast horizons.

show abstract

Section: Spatiotemporal Features Based Modelsmentioning

confidence: 99%

An Inner-Inter City Graph Neural Network for Predicting the Course of COVID-19 Cases

Ndiaye,

Liu,

Cui

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In this paper, we predict the quantitative interval for a certain day in the future and analyze the influence of the attributes of words on the results [11] . Through the time series model to report the number of results to explain [12] , the model is obtained to show a decaying trend. The gray prediction model [10] was used to predict the number of user participation on March 1,2023, obtaining an interval of 19121 to 20218 people.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Wordle Results Based on Ridge Regression Model and K-means Clustering

Zheng¹,

Jiang²,

Fan³

et al. 2023

Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26–28, 2023, N

View full text Add to dashboard Cite

Wordle is a word game that became known in January 2022. In order to innovate the game and improve the participation of the game, this paper analyzes a series of data by using time series model, gray prediction model, ridge regression, K-means clustering and other methods. In this paper, we predict the effects of player number intervals and word attributes on the results of Wordle at a certain stage in the future, and classify the words to find out the characteristics of each class of words, and predict the reported results of a certain word based on the word characteristics. At the same time, our experience can be used as classroom examples of innovative word game strategy algorithms and statistics to demonstrate the research of this paper.

show abstract

An efficient covid-19 prediction using Penguin Pelican optimization-based recurrent dropout-enabled hybrid deep CNN-BILSTM classifier

Dandge,

Harshavardhanan

2023

Multimed Tools Appl

View full text Add to dashboard Cite

STG-Net: A COVID-19 prediction network based on multivariate spatio-temporal information

Cited by 5 publications

References 25 publications

An Inner-Inter City Graph Neural Network for Predicting the Course of COVID-19 Cases

An Inner-Inter City Graph Neural Network for Predicting the Course of COVID-19 Cases

Prediction of Wordle Results Based on Ridge Regression Model and K-means Clustering

An efficient covid-19 prediction using Penguin Pelican optimization-based recurrent dropout-enabled hybrid deep CNN-BILSTM classifier

Contact Info

Product

Resources

About