Interpretable travel distance on the county-wise COVID-19 by sequence to sequence with attention

@article{Tian2022InterpretableTD,
  title={Interpretable travel distance on the county-wise COVID-19 by sequence to sequence with attention},
  author={Ting Tian and Yukang Jiang and Huajun Xie and Xueqin Wang and Hailiang Guo},
  journal={ArXiv},
  year={2022},
  volume={abs/2206.02536}
}
Background: Travel restrictions as a means of intervention in the COVID-19 epidemic have reduced the spread of outbreaks using epidemiological models. We introduce the attention module in the sequencing model to assess the effects of the different classes of travel distances. Objective: To establish a direct relationship between the number of travelers for various travel distances and the COVID-19 trajectories. To improve the prediction performance of sequencing model. Setting: Counties from… 
View PDF on arXiv

Figures and Tables from this paper

References

SHOWING 1-10 OF 26 REFERENCES

Population flow drives spatio-temporal distribution of COVID-19 in China

Modelling of population flows in China enables the forecasting of the distribution of confirmed cases of COVID-19 and the identification of areas at high risk of SARS-CoV-2 transmission at an early stage.

Modelling and predicting the spatio-temporal spread of cOVID-19 in Italy

A strong evidence is found that strict control measures implemented in some provinces efficiently break contagions and limit the spread to nearby areas.

The effect of travel restrictions on the spread of the 2019 novel coronavirus (COVID-19) outbreak

The results suggest that early detection, hand washing, self-isolation, and household quarantine will likely be more effective than travel restrictions at mitigating this pandemic, and sustained 90% travel restrictions to and from mainland China only modestly affect the epidemic trajectory unless combined with a 50% or higher reduction of transmission in the community.

Estimating the effects of non-pharmaceutical interventions on COVID-19 in Europe

The results show that major non-pharmaceutical interventions and lockdown in particular have had a large effect on reducing transmission and continued intervention should be considered to keep transmission of SARS-CoV-2 under control.

Human mobility in response to COVID-19 in France, Italy and UK

A framework to quantify the substantial impact of the mobility restrictions is provided and a percolation model mimicking mobility network disruption is introduced, finding that node persistence in the percolations process is significantly correlated with the economic and demographic characteristics of countries.

A seq2seq model to forecast the COVID-19 cases, deaths and reproductive R numbers in US counties

A forecasting model using deep learning (DL) to predict the spread of the virus within US counties and an autoencoder-based Seq2Seq model with gated recurrent units (GRUs) in the deep recurrent layers is implemented.

Analysis and Prediction of COVID-19 Confirmed Cases Using Deep Learning Models: A Comparative Study

Predictions of the number of coronavirus confirmed cases for the five topmost affected countries across the world have been made and it was inferred that the LSTM model outperformed the ANN model.

Collaborative City Digital Twin For Covid-19 Pandemic: A Federated Learning Solution

A collaborative city digital twin based on FL, a novel paradigm that allowing multiple city DT to share the local strategy and status in a timely manner, and eventually establish a `global view' for city crisis management is proposed.

Deep learning via LSTM models for COVID-19 infection forecasting in India

This paper applies recurrent neural networks such as long short term memory (LSTM), bidirectional LSTM, and encoder-decoder L STM models for multi-step COVID-19 infection forecasting and predicts that the likelihood of another wave of infections in October and November 2021 is low.

Long Short-Term Memory

A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.