Where pixeli+1;3 Ccej . . .), and y is

Where f is the number of the cluster centers in a chromosome, and Value (Ccej)is the value of the three bands of cluster center Ccej. It is the sum of the obtainedweights multiplied by 255. Value (pixelir) are the values of the three bands of thepixel on the left side of the cluster center Ccej in the chromosome(. . . pixeli;1 pixeli;2pixeli;3 Ccej pixeli+1;1 pixeli+1;2 pixeli+1;3 Ccej . . .), and y is the number of pixelsin each cluster. The fitness F(Chromosome) of each chromosome xi in the currentpopulation P(0) is the objective function, and according to the fitness value, eachchromosome will be given a number of chances to be selected using the roulettewheel selection process 46, where the lower in cost is given more possibilities formating. Two chromosomes are selected randomly, and they are mated (by replacingcluster centers from one parent with the other parent and vice versa) to create twonew children. Mutation operation works on individual chromosomes by changing acluster value “intensity” with another cluster value that is selected randomly fromthe available clusters in the image. The probability of crossover can vary between40% and 70%, while mutation can vary between 10% and 20%. These reproducedchildren replace their parents, and their fitness values are calculated again. The reproductionprocess is tailed by the Hill Climbing process in order to slow the fastconvergence of GA toward a local optimal solution. In the first experiment, SPOT5 is used where three bands are enhanced with respect to spatial resolution usingthe panchromatic image. The size of the SPOT image is 360 X 360 pixels and theresolution is 5 meters see Figure 2a. SPOT remote-sensing satellites program wascreated by France in partnership with other European countries such as Belgium.The deployment of SPOT satellites in orbit facilitated the mission of observing basicallythe entire planet in 1 day. Field work is carried out to verify the classifiedimage where 110 different samples are collected from three classes (1-Urban settlements(light brown), 2-Bare soil (light green), and 3-Vegetation (dark green)). Theresults are verified based on a collection of samples combined with the confusionmatrix 47. The matrix covers information about real and projected classificationsdone by a specific system. Performance of such systems is commonly evaluatedusing the data in the matrix. The confusion matrix (Table 1) demonstrates that theaccuracy value of the HyGA method is 82%.