A novel ensemble ARIMA‐LSTM approach for evaluating COVID‐19 cases and future outbreak preparedness
Somit Jain, Shobhit Agrawal, Eshaan Mohapatra, Kathiravan Srinivasan · 2024
Read A novel ensemble ARIMA‐LSTM approach for evaluating COVID‐19 cases and future outbreak preparedness by Somit Jain, Shobhit Agrawal, Eshaan Mohapatra, Kathiravan Srinivasan (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11671211.txt.
Description
Somit Jain and co-authors blend two forecasting styles to predict COVID-19 case counts in this 2024 study. Classic statistical models catch trends and seasons but miss sudden curves; neural networks catch curves but can miss structure. The team combined both and tested the hybrid on case data from India, Brazil, Russia, and America.
The hybrid's average forecast error came to 2.4 percent, beating the classic model, two neural rivals, and a popular forecasting tool, whose best score was 2.9 percent. Gains held across the countries studied and across several error measures. The authors say sharper forecasts of this kind help health officials place staff and supplies before surges hit.
Catalog record
| CREATOR | Somit Jain, Shobhit Agrawal, Eshaan Mohapatra, Kathiravan Srinivasan |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |