Sequential Data Modeling of Influenza A via Traditional, DWT-GPR Hybrid, and Deep Learning Architectures

Author

Edmund Fosu Agyemang, The University of Texas Rio Grande ValleyFollow

Date of Award

7-2025

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Applied Statistics and Data Science

First Advisor

Hansapani Rodrigo

Second Advisor

Tamer F. Oraby

Third Advisor

George P. Yanev

Abstract

Influenza A is responsible for 290,000 to 650,000 respiratory deaths a year, though this estimate is an improvement from years past due to improved sanitation, healthcare practices, and vaccination programs. In this study, we perform a comparative analysis of traditional, deep-learning and discrete wavelet (DWT)-Gaussian Process (GP) hybrid models to predict Influenza A outbreaks. Using historical data from January 2009 to December 2023, we compared the performance of traditional ARIMA and ETS models, four variants of DWT-GPR models and six distinct deep learning architectures: Simple RNN, LSTM, GRU, BiLSTM, BiGRU and Transformer. The results reveal a clear superiority of all the deep learning models, especially the state-of-the-art Transformer with respective average testing MSE and MAE of 0.0433±0.0020 and 0.1126±0.0016 for capturing the temporal complexities associated with Influenza A data, outperforming the well-known traditional ARIMA, ETS and DWT-GPR models. The findings of this study provide evidence that state-of-the-art deep learning architectures can enhance predictive modelling for infectious diseases and indicate a more general trend toward using deep learning methods to strengthen public health forecasting and intervention planning strategies. By shifting to more complex forecasting techniques, public health strategies could be significantly impacted, ultimately leading to timely intervention resulting in a decrease in Influenza A morbidity and mortality. Future work should focus on how these models can be incorporated into real-time forecasting and preparedness systems at an epidemic level and integrated into existing surveillance systems.

Comments

Copyright 2025 Edmund Fosu Agyemang. All Rights Reserved. https://proquest.com/docview/3253950491

Recommended Citation

Agyemang, E. F. (2025). Sequential data modeling of influenza A via traditional, DWT-GPR hybrid, and deep learning architectures [Master's thesis, The University of Texas Rio Grande Valley]. ScholarWorks @ UTRGV. https://scholarworks.utrgv.edu/etd/1770