Page 73 - Çevre Şehir İklim İngilizce - Sayı 4

Hacı Abdullah Uçan - Tayfun Dede - Sinan Nacar

Table 10. The relative importance of the independent variables used for the estimation
of the number of licenses variable obtained from the MARS andTreeNet methods

MARS TreeNet
N 100 |||||||||||||||||||||||||||||||||||||||||||||||| G 100 ||||||||||||||||||||||||||||||||||||||||||
Y 35.24 |||||||||||||||| E 97.3 |||||||||||||||||||||||||||||||||||||||||
G 15.28 ||||||| F 96.8 |||||||||||||||||||||||||||||||||||||||||
N 83.5 |||||||||||||||||||||||||||||||||||
Y 66.96 ||||||||||||||||||||||||||||

Table 10 shows that population, period during the year and gross domestic
product were effective among the independent variables in the equations
obtained for the MARS method, while all variables were effective in the
equation achieved for the TreeNet method. The variable with the highest
relative importance for the MARS method was the population variable, while
the variable with the highest relative importance in the TreeNet method was
the gross domestic product.
The performance statistics obtained for the training, verification and test
data sets of ANN-based models developed using a mixed selection data set
and established to predict the number of licenses variable are given in Table 11
for four different neuron numbers. Tests were conducted by trial and error for
the neuron numbers given in the table, and the results of the models that gave
the highest performance values were presented within the scope of the thesis.

Table 11. Performance statistics of the training, verification and test data sets of ANN-
based models developed for the number of licenses variable

Training ANN_5 ANN_10 ANN_15 ANN_20 GWO_5 GWO_10 GWO_15 GWO_20
RMSE(pcs.) 2956 2858 2908 2929 9939 15480 5800 9309
MAE(pcs.) 2404 2252 2287 2337 7444 12485 4509 7070
NS 0,85 0,86 0,86 0,86 -0,67 -3,04 0,43 -0,46
Doğrulama ANN_5 ANN_10 ANN_15 ANN_20 GWO_5 GWO_10 GWO_15 GWO_20
RMSE (pcs.) 7589 7918 7949 7890 5300 16887 7498 5441
MAE(pcs.) 5325 5526 5762 5451 4346 12880 5256 4444
NS 0,41 0,36 0,35 0,36 0,71 -1,92 0,42 0,70
Test ANN_5 ANN_10 ANN_15 ANN_20 GWO_5 GWO_10 GWO_15 GWO_20
RMSE(pcs.) 3599 3534 3628 3620 9537 15428 5758 9311
MAE(pcs.) 2997 2887 3152 2896 8242 11055 4847 8096
NS 0,74 0,75 0,74 0,74 -0,83 -3,79 0,33 -0,74

62 The Journal of Environment, Urban and Climate