All Title Author
Keywords Abstract

Publish in OALib Journal
ISSN: 2333-9721
APC: Only $99

ViewsDownloads

Relative Articles

More...

基于双向LSTM模型的COVID-19预测分析
Predictive Analysis of COVID-19 Based on Bidirectional LSTM Model

DOI: 10.12677/HJDM.2023.131005, PP. 46-54

Keywords: 预测,COVID-19,时间序列,神经网络,Forecast, COVID-19, Time Series, Neural Network

Full-Text   Cite this paper   Add to My Lib

Abstract:

2020年初,COVID-19疫情快速爆发,使得多个国家采取很多措施来控制疫情蔓延,疫情的出现对各国的医疗体系和经济造成了较大冲击,因此疫情信息的估计和预测对于政府和企业制定公共卫生防控措施具有重要的参考价值,对于这种快速传播的高致病性传染病来说,信息掌握的滞后会导致较为严重的后果。故提出了将ARIMA模型和LSTM模型等应用到疫情数据中,将无症状感染患者和症状感染患者统计为新增病例,依据2020年至2022年数据,预测短期内美国每日新增确诊病例数量,并提出了在模型中引入双向LSTM,以均方差误差(MSE)和平均绝对误差(MAE)来评价不同参数下模型预测精度,结果显示,提出的模型和参数获得的预测患病数量更接近实际患病数量,得到了较好的预测数据。
At the beginning of 2020, the rapid outbreak of the COVID-19 epidemic caused many countries to take many measures to control the spread of the epidemic. At the same time, the emergence of the epidemic had a great impact on the medical systems and economies of various countries. Therefore, the estimation and prediction of epidemic information has important reference value for the government and enterprises to formulate public health prevention and control measures. For this fast-spreading highly pathogenic infectious disease, the delay in information acquisition will lead to more serious consequences. Therefore, it is proposed to apply the ARIMA model and LSTM model to the epidemic data, and count asymptomatic infected patients and symptomatic infected patients as new cases. Based on the data from 2020 to 2022, we predict the number of new confirmed cases in the United States every day in the short term. A bidirectional LSTM was introduced into the model, and the mean square error (MSE) and mean absolute error (MAE) were used to evaluate the prediction accuracy of the model under different parameters. The results show that the predicted disease number obtained by the proposed model and parameters is closer to the actual disease number, and better prediction data are obtained.

References

[1]  Liu, X.X.., Fong, S.J., Dey, N., et al. (2021) A New SEAIRD Pandemic Prediction Model with Clinical and Epidemio-logical Data Analysis on COVID-19 Outbreak. Applied Intelligence, 51, 4162-4198.
https://doi.org/10.1007/s10489-020-01938-3
[2]  Alizargar, J. (2020) Risk of Reactivation or Reinfection of Novelcoronavirus (COVID-19). Journal of the Formosan Medical Association, 119, 1123.
https://doi.org/10.1016/j.jfma.2020.04.013
[3]  Hernandez-Matamoros, A., Fujita, H., Hayashi, T., et al. (2020) Forecasting of COVID19 per Regions Using ARIMA Models and Polynomial Functions. Applied Soft Computing, 96, Article ID: 106610.
https://doi.org/10.1016/j.asoc.2020.106610
[4]  喻国明, 靳一, 张洪忠, 等. 信息透明化处理的传播效果——SARS事件中的民意调查及分析[J]. 新闻记者, 2003(7): 28-32.
[5]  Bayyurt, L. and Bayyurt, B. (2020) Forecasting of COVID-19 Cases and Deaths Using ARIMA Models. MedRxiv.
https://doi.org/10.1101/2020.04.17.20069237
[6]  Rahman, M.R., Islam, A.H.M.H. and Islam, M.N. (2020) Ge-ospatial Modelling on the Spread and Dynamics of 154 Day Outbreak of the Novel Coronavirus (COVID-19) Pandemic in Bangladesh towards Vulnerability Zoning and Management Approaches. Modeling Earth Systems and Environment, 7, 2059-2087.
https://doi.org/10.1007/s40808-020-00962-z
[7]  Fattah, J., Ezzine, L., Aman, Z., El Moussami, H. and Lachhab, A. (2018) Forecasting of Demand Using ARIMA Model. International Journal of Engineering Business Management, 10.
https://doi.org/10.1177/1847979018808673
[8]  Tuli, S., Tuli, S., Tuli, R. and Gill, S.S. (2020) Predicting the Growth and Trend of COVID-19 Pandemic Using Machine Learning and Cloud Computing. Internet Things, 11, Article ID: 100222.
https://doi.org/10.1016/j.iot.2020.100222
[9]  Ku Kucharski, A.J., et al. (2020) Early Dynamics of Transmission and Control of COVID-19: A Mathematical Modelling Study. Lancet Infectious Diseases, 20, 553-558.
https://doi.org/10.1016/S1473-3099(20)30144-4
[10]  Dey, S.K., Rahman, M.M., Siddiqi, U.R. and Howlader, A. (2020) Analyzing the Epidemiological Outbreak of COVID- 19: A Visual Exploratory Data Analysis Approach. Journal of Medical Virology, 92, 632-638.
https://doi.org/10.1002/jmv.25743
[11]  Tiwari, S., Kumar, S. and Guleria, K. (2020) Outbreak Trends of Corona-virus Disease-2019 in India: A Prediction. Disaster Medicine and Public Health Preparedness, 14, e33-e38.
https://doi.org/10.1017/dmp.2020.115
[12]  Gatto, M., et al. (2020) Spread and Dynamics of the COVID-19 Epi-demic in Italy: Effects of Emergency Containment Measures. Proceedings of the National Academy of Sciences of the USA, 117, 10484-10491.
https://doi.org/10.1073/pnas.2004978117
[13]  Liu, F., Lu, Y. and Cai, M. (2020) A Hybrid Method with Adaptive Sub-Series Clustering and Attention-Based Stacked Residual LSTMs for Multivariate Time Series Forecasting. IEEE Access, 8, 62423-62438.
https://doi.org/10.1109/ACCESS.2020.2981506

Full-Text

comments powered by Disqus

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133

WeChat 1538708413