返回
Two-Strain COVID-19 Model Using Delayed Dynamic System and Big Data
DOI:10.1109/ACCESS.2021.3104519.png)
摘要
En 中文
The proposed model is based on COVID-19 Big Data Hub. It enables us to predict pandemics development taking into account multiple virus strains and delays of infectiousness. Two-strain dynamic models with distributed delays have been fitted to the time series retrieved from COVID data hub. The data at the national, regional, and county-level which are seamlessly integrated with World Bank Open Data, Google Mobility Reports, Apple Mobility Reports, have been used. The parameter identification has been fulfilled with the help of COBYLA algorithm. The simulations have been implemented with the help of Julia high-performance computing. The effect of the time delays is analyzed. The considered pipeline utilizes the data from the Hub to generate the COVID model and to produce a reliable prediction.
Keyword:
COVID-19
Big Data
Data models
Mathematical model
Delays
Computational modeling
Pipelines
Big data
COVID
delayed dynamic system
distributed delays
epidemiology
high-performance computing
parameter identification
scientific machine learning
virus strain
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Diagnosing Coronavirus Disease 2019 (COVID-19): Efficient Harris Hawks-Inspired Fuzzy K-Nearest Neighbor Prediction Methods
IEEE ACCESS
IF3.6
IEEE ACCESS SPECIAL SECTION EDITORIAL: SMART HEALTH SENSING AND COMPUTATIONAL INTELLIGENCE: FROM BIG DATA TO BIG IMPACTS
IEEE ACCESS
IF3.6
A Novel Bayesian Optimization-Based Machine Learning Framework for COVID-19 Detection From Inpatient Facility Data
IEEE ACCESS
IF3.6
iResponse: An AI and IoT-Enabled Framework for Autonomous COVID-19 Pandemic Management
SUSTAINABILITY
IF3.3

