A New Epidemic Disease Predicting Method
LI-Zhen Peng, LI-Xiao Yi, Shi-Yan Hua · 2008
Considering the epidemic data in a long duration as non-stationary time series, we present a novel comprehensive model free infection prediction scheme with combining both wavelet multi-resolution analysis and wavelet neural network. The performance of the new approach is illustrated by an application to predicting the US CDC (03-04) %ILI data, simulation result shows our method is valid and has high prediction accuracy.