Presentation Information
[C10-01]Machine Learning and Wavelet-Based Prediction of Norovirus Detection Rates in South Korea
*Giphil Cho1 (1. Kangwon National University (Korea))
Keywords:
Norovirus,Machine Learning,Wavelet analysis
Norovirus is a primary agent of acute gastroenteritis in all age groups, with young children under five being particularly vulnerable. Due to the virus’s pronounced seasonal behavior, forecasting its detection rate based on climatic factors is essential. To account for the seasonal variability in both weather patterns and norovirus prevalence, wavelet coherence analysis was applied. The phase shift in the one-year cycle was examined to identify changes in periodic behavior over time. In the preprocessing stage, the model was trained on data from January 2007 to June 2019 and tested on data from June 2019 to December 2020, with wavelet-derived features reflecting temporal changes in seasonality. Weekly detection rates were predicted using four machine learning models, and the inclusion of wavelet analysis resulted in a 10–15% improvement in prediction accuracy compared to models without it.