COVID-19 Confirmed Case Prediction after Vaccination Using Deep Learning Models
Bibliographic record
Abstract
The COVID-19 outbreak is wreaking devastation throughout the globe. It has infected millions of people and claimed thousands of lives till now. On the other hand, vaccination has been started in many countries since December 2020. In this study, we have used deep learning models such as long short-term memory (LSTM) and gated recurrent units (GRU) to analyze and forecast the confirmed cases of COVID-19. The datasets of six countries that started vaccination earlier, including Israel, the UK, the USA, Canada, Brazil, and India, were collected from 1 September 2020 to 30 April 2021, containing 242 days and tested on 105 days from 15 January to 30 April 2021, with analysis on how data size and vaccination affect the overall trend. The performance of these models is investigated in terms of error measurements like mean absolute error (MAE) and root mean square error (RMSE). The results show that GRU outperforms LSTM in error terms like MAE and RMSE for most countries. There are many studies on the data before vaccination, and they produced noticeably higher errors. Many researchers have overfitted the forecasting models by using small datasets and creating too many predictor variables. Models constructed in this manner are unlikely to pass a validity and reliability test on a separate sample. Without seeking such validation, the researcher is unaware that overfitting has happened. We have examined these models on data before and after vaccination to verify the time-series prediction and provided a comparative analysis of our models. In addition, our models show promising results and by far outperform in comparison to other studies. For countries such as Canada and Israel, our models produce lower RMSE (1119, 1045) and MAE (752, 727) for both GRU and LSTM models, respectively. These deep learning models can be used for time-series analysis given that datasets are constantly updated with new cases for training and identifying trends and estimation of the upcoming confirmed cases.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".