期刊
ISA TRANSACTIONS
卷 124, 期 -, 页码 41-56出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.isatra.2020.12.057
关键词
COVID-19; Long Short Term Memory (LSTM); Time-series-forecast; Transfer Learning; Neural network
Transfer learning is utilized in LSTM networks to forecast new COVID cases and deaths, showing promising results that can be valuable for policymakers in combating COVID-19.
In this paper, Transfer Learning is used in LSTM networks to forecast new COVID cases and deaths. Models trained in data from early COVID infected countries like Italy and the United States are used to forecast the spread in other countries. Single and multistep forecasting is performed from these models. The results from these models are tested with data from Germany, France, Brazil, India, and Nepal to check the validity of the method. The obtained forecasts are promising and can be helpful for policymakers coping with the threats of COVID-19. (C) 2020 ISA. Published by Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据