Development of novel hybrid models for the prediction of Covid-19 in Kuwait
The first case of coronavirus 2019 (Covid-19) in Kuwait was reported on February 24, 2020, and then day by day cases of Covid-19 keep on increasing. The decision of the government about the standard citizens to repatriate them back to Kuwait from different epicenters of Covid-19 has created a big ch...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-12-01
|
| Series: | Kuwait Journal of Science |
| Subjects: | |
| Online Access: | https://journalskuwait.org/kjs/index.php/KJS/article/view/10273 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The first case of coronavirus 2019 (Covid-19) in Kuwait was reported on February 24, 2020, and then day by day cases of Covid-19 keep on increasing. The decision of the government about the standard citizens to repatriate them back to Kuwait from different epicenters of Covid-19 has created a big challenge. There is a need to estimate a prediction model for the estimation of this epidemic size. The main objective of the current study is to find an efficient way of prediction of this epidemic situation for coronavirus by using real-time data from 24th February to 12th June 2020. By considering the uncertainty in the current situation and non-stationary real-time data of corona cases, we consider a novel strategy for prediction purposes. By using a multilayer model with different decomposition techniques, we developed a novel hybrid model for decomposition and prediction of corona cases in Kuwait. A Hybrid methodology based on denoising, decomposition, prediction, and ensemble rules are applied to the confirmed corona cases in Kuwait. To evaluate the performance of the novel hybrid model in comparison with other existing models, we use mean relative error, mean absolute error, and mean square error. It is concluded that the proposed framework for the prediction of conformed corona cases indicated better performance as compared to other existing methods. |
|---|---|
| ISSN: | 2307-4108 2307-4116 |