NORMA eResearch @NCI Library

A study on Influenza Reports: The Impact of Various Influencing Factors and a Predictive Modeling Approach to Forecasting Flu Cases in European Countries

Badami, Vasanthi (2022) A study on Influenza Reports: The Impact of Various Influencing Factors and a Predictive Modeling Approach to Forecasting Flu Cases in European Countries. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

Influenza symptoms are identical to those of COVID 19. As a result, distinguishing between the two disorders might be difficult at times. Similar infections such as influenza should not be ignored in circumstances such as the COVID 19 pandemic. Therefore this study aims to forecast influenza cases in the most regularly visited tourist countries because they are already on high alert to prevent the virus from spreading further. Assisting these countries in their preparation for influenza vaccination campaigns could help to reduce the pandemic’s complexity. Other contributing factors such as weather and the population of different age groups in the respective countries were also taken into account in this study. However, they did not reveal a strong link with the number of influenza cases reported. Conversely, youngsters aged 0 to 14 and those aged 100 and above exhibited an improved correlation. As a result, all of these characteristics were taken into account when forecasting influenza cases. To move forward with the model implementation, stand-alone models such as ARIMA, SVR, RF, and attention LSTM are used, followed by an ARIMA-LSTM hybrid model to see how the hybrid model performs on this problem. The attention LSTM model performed exceptionally well, with a RMSE value of 0.08, however, the RF model had a second-lowest RMSE score (84.991). Other models did not appear to offer much optimism in terms of achieving the best fit model for predictions. As a result of this research, it appears that attention LSTM will be the best fit model.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > R Medicine (General)
R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 18 Jan 2023 14:47
Last Modified: 18 Jan 2023 14:47
URI: https://norma.ncirl.ie/id/eprint/6077

Actions (login required)

View Item View Item