ILI forecasting (one week) results for six geolocations.

Models: AdaBoost, SVM with a linear kernel, and LSTM. Metrics: RMSPE (%), MAPE (%), and RMSE (% ILI). The best performing models within each data type are highlighted in bold.

模型：自适应提升算法（AdaBoost）、搭载线性核的支持向量机（Support Vector Machine，SVM）以及长短期记忆网络（Long Short-Term Memory，LSTM）。评估指标：均方根百分比误差（Root Mean Squared Percentage Error，RMSPE，%）、平均绝对百分比误差（Mean Absolute Percentage Error，MAPE，%）以及均方根误差（Root Mean Squared Error，RMSE，% ILI）。每种数据类型中表现最优的模型将以粗体突出显示。