Transfer Learning for COVID-19 cases and deaths forecast using LSTM network

被引：50

作者：

Gautam, Yogesh ^{[1
]}

机构：

[1] Inst Engn, Dept Mech & Aerosp Engn, Pulchowk Campus, Kathmandu 44700, Nepal

来源：

ISA TRANSACTIONS | 2022年 / 124卷

关键词：

COVID-19; Long Short Term Memory (LSTM); Time-series-forecast; Transfer Learning; Neural network; LOCKDOWN;

D O I：

10.1016/j.isatra.2020.12.057

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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.

引用

页码：41 / 56

页数：16

共 19 条

[1]

[Anonymous], 2020, CORONAVIRUS UPDATE L

[2]

[Anonymous], 2020, Keras: the Python deep learning API

[3]

[Anonymous], 2020, BBC News

[4]

[Anonymous], 2020, WELCOME COLABORATORY