Attention based parameter estimation and states forecasting of COVID-19 pandemic using modified SIQRD Model
© 2022 Elsevier Ltd. All rights reserved..
In this work, we propose a new mathematical modeling of the spread of COVID-19 infection in an arbitrary population, by modifying the SIQRD model as m-SIQRD model, while taking into consideration the eight governmental interventions such as cancellation of events, closure of public places etc., as well as the influence of the asymptomatic cases on the states of the model. We introduce robustness and improved accuracy in predictions of these models by utilizing a novel deep learning scheme. This scheme comprises of attention based architecture, alongside with Generative Adversarial Network (GAN) based data augmentation, for robust estimation of time varying parameters of m-SIQRD model. In this regard, we also utilized a novel feature extraction methodology by employing noise removal operation by Spline interpolation and Savitzky-Golay filter, followed by Principal Component Analysis (PCA). These parameters are later directed towards two main tasks: forecasting of states to the next 15 days, and estimation of best policy encodings to control the infected and deceased number within the framework of data driven synergetic control theory. We validated the superiority of the forecasting performance of the proposed scheme over countries of South Korea and Germany and compared this performance with 7 benchmark forecasting models. We also showed the potential of this scheme to determine best policy encodings in South Korea for 15 day forecast horizon.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:165 |
|---|---|
| Enthalten in: |
Chaos, solitons, and fractals - 165(2022) vom: 01. Dez., Seite 112818 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Khan, Junaid Iqbal [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
COVID-19 |
|---|
| Anmerkungen: |
Date Revised 21.12.2022 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1016/j.chaos.2022.112818 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM348522436 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM348522436 | ||
| 003 | DE-627 | ||
| 005 | 20231226040439.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.chaos.2022.112818 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1161.xml |
| 035 | |a (DE-627)NLM348522436 | ||
| 035 | |a (NLM)36338376 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Khan, Junaid Iqbal |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Attention based parameter estimation and states forecasting of COVID-19 pandemic using modified SIQRD Model |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 21.12.2022 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © 2022 Elsevier Ltd. All rights reserved. | ||
| 520 | |a In this work, we propose a new mathematical modeling of the spread of COVID-19 infection in an arbitrary population, by modifying the SIQRD model as m-SIQRD model, while taking into consideration the eight governmental interventions such as cancellation of events, closure of public places etc., as well as the influence of the asymptomatic cases on the states of the model. We introduce robustness and improved accuracy in predictions of these models by utilizing a novel deep learning scheme. This scheme comprises of attention based architecture, alongside with Generative Adversarial Network (GAN) based data augmentation, for robust estimation of time varying parameters of m-SIQRD model. In this regard, we also utilized a novel feature extraction methodology by employing noise removal operation by Spline interpolation and Savitzky-Golay filter, followed by Principal Component Analysis (PCA). These parameters are later directed towards two main tasks: forecasting of states to the next 15 days, and estimation of best policy encodings to control the infected and deceased number within the framework of data driven synergetic control theory. We validated the superiority of the forecasting performance of the proposed scheme over countries of South Korea and Germany and compared this performance with 7 benchmark forecasting models. We also showed the potential of this scheme to determine best policy encodings in South Korea for 15 day forecast horizon | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a COVID-19 | |
| 650 | 4 | |a Compartment model | |
| 650 | 4 | |a Control theory | |
| 650 | 4 | |a Deep learning | |
| 700 | 1 | |a Ullah, Farman |e verfasserin |4 aut | |
| 700 | 1 | |a Lee, Sungchang |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Chaos, solitons, and fractals |d 1995 |g 165(2022) vom: 01. Dez., Seite 112818 |w (DE-627)NLM114377014 |x 0960-0779 |7 nnns |
| 773 | 1 | 8 | |g volume:165 |g year:2022 |g day:01 |g month:12 |g pages:112818 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.chaos.2022.112818 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 165 |j 2022 |b 01 |c 12 |h 112818 | ||