Zhang Z., He X., Sun X., Guo L., Wang J., Wang F., 2015, Image Recognition of Maize Leaf Disease Based on GA-SVM, Chemical Engineering Transactions, 46, 199-204.
An improved SVM named genetic algorithm support vector machines (GA-SVM) is discussed in this paper for classifying maize disease. According to the disadvantage of manually determining the parameters in traditional SVM, the genetic algorithms is used to automatically obtain the penalty factor and kernel function. The appropriate parameters are selected by rotational orthogonal method. The extracted eigenvalue is entered to the GA-SVM classification model to improve the classification performance. After the comparisons of different genetic operators and different kernel functions, the results show that the appropriate parameters for genetic algorithms is when M=50, Pc=0.7 and Pm=0.05, the average classification rate is at peak when choosing RBF kernel function. The results also demonstrate that the GA-SVM algorithm achieves a better improvement than SVM.
