Advances in International Applied Mathematics
Advances in International Applied Mathematics. 2023; 5: (2) ; 10.12208/j.aam.20230005 .
总浏览量: 1023
北方民族大学
*通讯作者： 李虎飞,单位：北方民族大学；
在各类传染病交替爆发的背景下，利用深度学习和统计相关理论对传染病的传播机制和流行趋势进行研究和探索是非常重要的. 首先，文章通过对SEAIRD模型与LSTM模型的预测结果进行线性回归，提出SEAIRD-LSTM混合预测模型. 然后，对俄罗斯地区COVID-19传染病感染人数与死亡人数进行预测，并将SEAIRD-LSTM混合预测模型与多项式回归、逻辑回归、SEIR以及LSTM模型对比，结果表明SEAIRD-LSTM混合预测模型在RMSE、MAE、MAPE和R2评价指标下都取得了较好的预测效果. 最后，对德国和英国地区新冠数据进行预测，通过真值与预测值的误差率对比，验证了SEAIRD模型的可适性以及SEAIRD-LSTM混合预测模型的预测准确度.
In the context of the outbreak of various infectious diseases, it is very important to use deep learning and statistical theories to study and explore the transmission mechanism and epidemic trend of infectious diseases. Firstly, the SEAIRD-LSTM hybrid prediction model is proposed by linear regression of SEAIRD model and LSTM model. Then, the number of COVID-19 infections and deaths in Russia was predicted, and the hybrid prediction model of SEAIRD-LSTM was compared with polynomial regression, logistic regression, SEIR and LSTM models. The results show that the SEAIRD-LSTM hybrid prediction model achieves good prediction effect under RMSE, MAE, MAPE and R2 evaluation indexes. Finally, the COVID-19 data in Germany and the UK were predicted, and the adaptability of the SEAIRD model and the prediction accuracy of the SEAIRD-LSTM hybrid prediction model were verified by comparing the error rate between the true value and the predicted value.
[1] Ciotti M, Ciccozzi M, Terrinoni A, et al. The COVID-19 pandemic[J]. Critical reviews in clinical laboratory sciences, 2020, 57(6): 365-388.
[2] Lipsitch M, Swerdlow D L, Finelli L. Defining the epidemiology of Covid-19—studies needed[J]. New England journal of medicine, 2020, 382(13): 1194-1196.
[3] Bulut C, Kato Y. Epidemiology of COVID-19[J]. Turkish journal of medical sciences, 2020, 50(9): 563-570.
[4] Jiao J, Liu Z, Cai S. Dynamics of an SEIR model with infectivity in incubation period and homestead-isolation on the susceptible[J]. Applied Mathematics Letters, 2020, 107: 106442.
[5] Fu B, Yang Y, Ma Y, et al. Attention-based recurrent multi-channel neural network for influenza epidemic prediction[C]. IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2018: 1245-1248.
[6] Doni A R, Sasipraba T. LSTM-RNN Based Approach for Prediction of Dengue Cases in India[J]. Ingénierie des Systèmes d'Information, 2020, 25(3).
[7] Derr T, Ma Y, Fan W, et al. Epidemic graph convolutional network[C]. Proceedings of the 13th International Conference on Web Search and Data Mining, 2020: 160-168.
[8] 谢黎颖. 基于时空序列的传染病发展趋势预测[D]. 东华大学, 2021.
[9] da Silva T T, Francisquini R, Nascimento M C V. Meteorological and human mobility data on predicting COVID-19 cases by a novel hybrid decomposition method with anomaly detection analysis: A case study in the capitals of Brazil[J]. Expert Systems with Applications, 2021, 182: 115190.
[10] 何振欢, 肖建华. 基于EEMD-LSTM模型的禽霍乱预测研究[J]. 动物医学进展, 2022, 43(11):34-38.
[11] 赖晓蓥, 钱俊. ARIMA-LSTM-XGBoost加权组合模型在肺结核发病趋势预测的研究[J]. 现代预防医学, 2021, 48(01):5-9.
[12] 冯晨, 陈志德. 基于XGBoost 和LSTM 加权组合模型在销售预测的应用[J]. 计算机系统应用, 2019, 28(10): 226-232.