TY - JOUR
T1 - Modeling and prediction of the covid-19 cases with deep assessment methodology and fractional calculus
AU - Karacuha, Ertu Rul
AU - Onal, Nisa Ozge
AU - Ergun, Esra
AU - Tabatadze, Vasil
AU - Alka, Hasan
AU - Karacuha, Kamil
AU - Tontu, Haci Omer
AU - Ngocnu, Nguyen Vinh
N1 - Publisher Copyright:
© 2020 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
PY - 2020
Y1 - 2020
N2 - This study focuses on modeling, prediction, and analysis of confirmed, recovered, and death cases of COVID-19 by using Fractional Calculus in comparison with other models for eight countries including China, France, Italy, Spain, Turkey, the UK, and the US. First, the dataset is modeled using our previously proposed approach Deep Assessment Methodology, next, one step prediction of the future is made using two methods: Deep Assessment Methodology and Long Short-Term Memory. Later, a Gaussian prediction model is proposed to predict the short-Term (30 Days) future of the pandemic, and prediction performance is evaluated. The proposed Gaussian model is compared to a time-dependent susceptibleinfected-recovered (SIR) model. Lastly, an analysis of understanding the effect of history is made on memory vectors using wavelet-based denoising and correlation coefficients. Results prove that Deep Assessment Methodology successfully models the dataset with 0.6671%, 0.6957%, and 0.5756% average errors for confirmed, recovered, and death cases, respectively. We found that using the proposed Gaussian approach underestimates the trend of the pandemic and the fastest increase is observed in the US while the slowest is observed in China and Spain. Analysis of the past showed that, for all countries except Turkey, the current time instant is mainly dependent on the past two weeks where countries like Germany, Italy, and the UK have a shorter average incubation period when compared to the US and France.
AB - This study focuses on modeling, prediction, and analysis of confirmed, recovered, and death cases of COVID-19 by using Fractional Calculus in comparison with other models for eight countries including China, France, Italy, Spain, Turkey, the UK, and the US. First, the dataset is modeled using our previously proposed approach Deep Assessment Methodology, next, one step prediction of the future is made using two methods: Deep Assessment Methodology and Long Short-Term Memory. Later, a Gaussian prediction model is proposed to predict the short-Term (30 Days) future of the pandemic, and prediction performance is evaluated. The proposed Gaussian model is compared to a time-dependent susceptibleinfected-recovered (SIR) model. Lastly, an analysis of understanding the effect of history is made on memory vectors using wavelet-based denoising and correlation coefficients. Results prove that Deep Assessment Methodology successfully models the dataset with 0.6671%, 0.6957%, and 0.5756% average errors for confirmed, recovered, and death cases, respectively. We found that using the proposed Gaussian approach underestimates the trend of the pandemic and the fastest increase is observed in the US while the slowest is observed in China and Spain. Analysis of the past showed that, for all countries except Turkey, the current time instant is mainly dependent on the past two weeks where countries like Germany, Italy, and the UK have a shorter average incubation period when compared to the US and France.
KW - COVID-19
KW - SIR model
KW - deep assessment methodology (DAM)
KW - fractional calculus
KW - least squares
KW - long short-Term memory
KW - modeling
KW - prediction of pandemics
UR - http://www.scopus.com/inward/record.url?scp=85102527432&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.3021952
DO - 10.1109/ACCESS.2020.3021952
M3 - Article
AN - SCOPUS:85102527432
SN - 2169-3536
VL - 8
SP - 164012
EP - 164034
JO - IEEE Access
JF - IEEE Access
ER -