基于LSTM-SIR-EAKF的流感样病例预测
Influenza-like Illness Prediction Based on LSTM-SIR-EAKF
李进 1魏艳龙 1薛红新 2梁海坚2
作者信息
- 1. 太原师范学院计算机科学与技术学院,山西 晋中 030619
- 2. 中北大学计算机科学与技术学院,山西 太原 030051
- 折叠
摘要
探索基于机器学习模型与传染病模型的组合方法来预测流感趋势,为医疗机构提供意见方便做好预防措施.为了准确捕获流感样病例的时序特征,提出一种基于长短期记忆(LSTM)神经网络、易感-感染-康复(SIR)模型和集合调整卡尔曼滤波(EAKF)的组合预测模型(LSTM-SIR-EAKF).首先,使用LSTM学习流感样病例的时序关系.其次,利用SIR模型模拟流感的传播过程.最后,EAKF对SIR模型生成的流感样病例预测值进行修正,得到最终流感预测值.实验结果表明,通过对3个时间段流感样病例的预测,LSTM-SIR-EAKF模型的拟合优度R2分别是0.996、0.991、0.995,且预测结果的评价指标均优于对比模型.LSTM-SIR-EAKF模型通过长短期记忆网络在时间方面对流感做了长期预测,以及传染病模型在空间中模拟了流感人群的变化,有效提高了预测效果.
Abstract
The paper explores the combination method based on machine learning model and infectious disease model to predict influenza trend,and provides advice for medical institutions to take preventive measures.To precisely capture the temporal fea-tures of influenza-like illness(ILI),this paper proposes a combined prediction model(LSTM-SIR-EAKF)based on long and short-term memory(LSTM)neural networks,Suceptible-Infected-Recovered(SIR)model,and Ensemble Adjustment Kalman Filter(EAKF).Firstly,the model of LSTM is employed to learn the temporal relationship between ILI.Then,SIR model is used to simulate the transmission process of ILI.Finally,EAKF correctes the anticipated values of ILI from SIR model to obtain the fi-nal prediction values of ILI.The experimental results show that through the prediction of ILI in three time periods,the goodness of fit(R2)proposed by the LSTM-SIR-EAKF model are 0.996,0.991 and 0.995,respectively,and the evaluation indicators of the prediction results are better than the comparison model.LSTM-SIR-EAKF model makes long-term prediction of influenza in time through long and short term memory network,and the infectious disease model simulates the changes of influenza population in space,effectively improving the prediction effect.
关键词
流感预测/长短期记忆网络/易感-感染-康复模型/集合调整卡尔曼滤波/时间序列Key words
ILI prediction/LSTM/SIR/ensemble adjustment Kalman filter/time series引用本文复制引用
基金项目
国家自然科学基金资助项目(62106238)
山西省基础研究计划项目(202203021212185)
山西省高等学校科技创新项目(2020L0283)
出版年
2024
国家科技期刊平台
NSTL
万方数据