Skip to main content

Table 1 The MAPEs and RMSEs of the testing set for all methods applied on fs1: time series and fs2: \(53- weeks-before\_52-first-order-differences\) and fs3: \(n-years-before\_m-weeks-around\) feature space

From: A comparative study on predicting influenza outbreaks using different feature spaces: application of influenza-like illness data from Early Warning Alert and Response System in Syria

(a) The MAPEs%
ModelsAverageNaïveSeasonal naïveDriftSTLDHRTBATS
Features:fs111.315.697.95.75.725.124.66
ModelsGLMSVRGBRF3-Layers-LSTM4-Layers-LSTM 
Features:fs26.165.835.945.894.724.9 
ModelsGLMSVRGBRF3-Layers-LSTM4-Layers-LSTM 
Features:fs3
Y0W15.695.686.756.865.665.67 
Y0W25.765.727.16.35.345.38 
Y0W35.735.736.696.295.365.27 
Y0W45.495.616.926.195.445.3 
Y0W55.685.717.295.915.475.39 
Y1W06.486.726.899.274.54.12 
Y2W06.175.856.478.914.674.6 
Y3W05.966.48.379.084.824.69 
Y1W15.125.236.366.943.944.8 
Y1W25.6155.266.484.094.09 
Y1W36.225.276.226.893.973.63 
Y1W46.225.35.77.113.893.52 
Y1W56.085.236.986.184.463.54 
Y2W15.265.325.567.224.444.03 
Y2W26.015.084.245.784.224.3 
Y2W37.435.686.196.174.433.99 
Y2W47.335.46.716.364.814.39 
Y2W57.235.345.536.444.614.71 
Y3W16.015.436.656.94.724.37 
Y3W26.865.495.756.225.54.74 
Y3W37.745.766.186.346.215.42 
Y3W48.245.926.976.246.435.92 
Y3W58.566.146.246.486.786.13 
(b) The RMSEs
ModelsAverageNaïveSeasonal naïveDriftSTLDHRTBATS
Features:fs10.057960.039250.044540.039310.036720.031790.03096
ModelsGLMSVRGBRF3-Layers-LSTM4-Layers-LSTM 
Features:fs20.037430.036430.036870.036990.022940.0237 
ModelsGLMSVRGBRF3-Layers-LSTM4-Layers-LSTM 
Features:fs3
Y0W10.038520.038660.043890.042450.027440.02767 
Y0W20.039330.039230.045250.038680.025980.02593 
Y0W30.037540.038610.042860.039150.026310.02549 
Y0W40.036890.037550.043550.03920.026660.02566 
Y0W50.036860.037980.045280.038250.026110.02565 
Y1W00.037810.038740.041630.049270.021130.01985 
Y2W00.036850.035340.040960.047610.022520.02189 
Y3W00.036290.039650.045260.050060.023120.02323 
Y1W10.033410.033610.038510.03960.019290.02296 
Y1W20.036540.032720.029680.038260.019380.0198 
Y1W30.037420.033090.034340.037680.018730.01763 
Y1W40.037450.032650.033690.038510.018250.01662 
Y1W50.036520.031750.040830.03350.021390.01682 
Y2W10.034720.0340.035150.040290.021080.01984 
Y2W20.038860.033520.02480.033270.019940.02276 
Y2W30.042220.033810.034010.037050.020940.01926 
Y2W40.041590.032490.037870.039090.022880.02122 
Y2W50.042760.032910.035020.039290.021480.02276 
Y3W10.03620.033050.034760.039880.022530.02121 
Y3W20.040380.031560.033820.037290.026590.02319 
Y3W30.043660.033570.035170.038220.03130.02588 
Y3W40.045390.034050.042280.038220.032260.02919 
Y3W50.050980.035920.037470.039280.033880.03064 
  1. Italics number indicate best result