BBTGA Progressing

% 0.5 1 5 10 20 50
Training size 168502 337992
Testing size 33615853 33446363
Tree size 8034 16165
Nimpurity 449 869
Pimpurity 124626 250404
Nsize 3568 7213
Psize 43876 87588
Time(Hour) 0.266 0.569
Atraining 88.3 88.5
Atesting 79.9 80.1
 

Table 1. Test on the newly implemented BBTGA. %: the proportion of scene 33 data used for training. Training size: the training data set size. Testing size: testing data set size. Tree size: the size of the generated tree. Nimpurity: the terminal node number from criterion of impurity reduction. Pimpurity: the population of training data in the terminal node number from criterion of impurity reduction. Nsize: the terminal node number from criterion of terminal node size. Psize: the population of training data in the terminal node number from criterion of  terminal node size. Time(Hour): the time needed for training. Atraining: the classification accuracy when applied the tree on the training data set. Atesting: the classification accuracy when applied the tree on the testing data set.
 

1 2 3 Average
Tree size 115 147 113 125
Nimpurity 9 12 6 9
Pimpurity 2067 1981 1991 2013
Nsize 49 62 51 54
Psize 633 719 709 687
Time (second) 7 9 7 8
Atraining 90.41 90.67 89.78 90.29
Atesting 72.89 72.03 73.55 72.82

Table 2. Test on the newly implemented BBTGA with ground observation. Nimpurity: the terminal node number from criterion of impurity reduction. Pimpurity: the population of training data in the terminal node number from criterion of impurity reduction. Nsize: the terminal node number from criterion of terminal node size. Psize: the population of training data in the terminal node number from criterion of  terminal node size. Time(Hour): the time needed for training. Atraining: the classification accuracy when applied the tree on the training data set. Atesting: the classification accuracy when applied the tree on the testing data set.