Back

Prediction of COVID-19 Pandemic of Top Ten Countries in the World Establishing a Hybrid AARNN LTM Model

GAHAN, P.; PATTNAIK, M.; Nayak, A.; Roul, M. K.

2021-01-05 epidemiology
10.1101/2020.12.31.20249105 medRxiv
Show abstract

The novel COVID-19 global pandemic has become a public health emergency of international concern affecting 215 countries and territories around the globe. As of 28 November 2020, it has caused a pandemic outbreak with a total of more than 6,171,5119 confirmed infections and more than 1,44,4235 confirmed deaths reported worldwide. The main focus of this paper is to generate LTM real-time out of sample forecasts of the future COVID-19 confirmed and death cases respectively for the top ten profoundly affected countries including for the world. To solve this problem we introduced a novel hybrid approach AARNN model based on ARIMA and ARNN forecasting model that can generate LTM (fifty days ahead) out of sample forecasts of the number of daily confirmed and death COVID-19 cases for the ten countries namely USA, India, Brazil, Russia, France, Spain, UK, Italy, Argentina, Colombia and also for the world respectively. The predictions of the future outbreak for different countries will be useful for the effective allocation of health care resources and will act as early-warning system for health warriors, corporate leaders, economists, government/public-policy makers, and scientific experts.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

1
PLOS ONE
● 5266 papers in training set
Top 15%
12.2%
Similar papers in this journal
2
Infectious Disease Modelling
○ 54 papers in training set
Top 0.1%
10.0%
Similar papers in this journal
3
Chaos, Solitons & Fractals
○ 32 papers in training set
Top 0.1%
5.3%
Similar papers in this journal
4
Frontiers in Public Health
○ 148 papers in training set
Top 1%
4.5%
Similar papers in this journal
5
JMIRx Med
◐ 32 papers in training set
Top 0.2%
4.1%
Similar papers in this journal
6
Scientific Reports
○ 3612 papers in training set
Top 24%
4.1%
7
Nonlinear Dynamics
○ 10 papers in training set
Top 0.1%
4.1%
8
Heliyon
○ 152 papers in training set
Top 1%
3.3%
9
Frontiers in Applied Mathematics and Statistics
○ 11 papers in training set
Top 0.1%
3.2%
50% of probability mass above
10
BioMed Research International
○ 28 papers in training set
Top 0.4%
2.7%
11
Biomedical Signal Processing and Control
○ 22 papers in training set
Top 0.2%
2.4%
12
Mathematical Biosciences and Engineering
● 23 papers in training set
Top 0.4%
2.2%
13
Healthcare
○ 17 papers in training set
Top 0.2%
1.8%
14
Computers in Biology and Medicine
○ 128 papers in training set
Top 2%
1.7%
15
PLOS Computational Biology
● 1863 papers in training set
Top 14%
1.7%
16
PeerJ
◐ 308 papers in training set
Top 6%
1.5%
17
Environmental Research
○ 49 papers in training set
Top 0.7%
1.4%
18
International Journal of Environmental Research and Public Health
○ 128 papers in training set
Top 4%
1.2%
19
Epidemiology and Infection
◐ 89 papers in training set
Top 2%
1.2%
20
Computational Biology and Chemistry
○ 28 papers in training set
Top 0.6%
1.2%
21
Biology Methods and Protocols
◐ 61 papers in training set
Top 2%
1.1%
22
Mathematics
○ 11 papers in training set
Top 0.2%
1.1%
23
BMC Infectious Diseases
○ 133 papers in training set
Top 4%
1.0%
24
Informatics in Medicine Unlocked
○ 22 papers in training set
Top 1%
0.9%
25
Cureus
○ 68 papers in training set
Top 4%
0.9%
26
Frontiers in Genetics
○ 230 papers in training set
Top 5%
0.9%
27
Disaster Medicine and Public Health Preparedness
◐ 16 papers in training set
Top 0.6%
0.9%
28
Royal Society Open Science
● 214 papers in training set
Top 7%
0.6%
29
BMC Research Notes
○ 33 papers in training set
Top 1%
0.6%
30
Biology
○ 45 papers in training set
Top 1%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.