An Efficient Fitness Function in Genetic Algorithm Classifier for Landuse Recognition on Satellite Images

Table 5

Overall accuracy of each index varying with selection ways.

Selection way	Index
	Overall accuracy (%)
	DBI	FCMI	PASI	DBFCMI	Average
Roulette wheel selection	71.6	73.2	64.9	75.5	71.3
Rank selection	68.3	47.7	69.1	75.1	65.0
Standard deviation	2.3	18.0	3.0	0.3	—

∗String length: 8, population: 30, crossover rate: 0.8, crossover way: two-point crossover, and mutation rate: 0.003.