Genetic based feed-forward neural network training for chaff cluster detection

Data classification is one of the most important and fundamental problems in many decision making tasks. As traditional methods for data classification, discriminant analysis, k-nearest neighbor (k-NN) and support vector machine (SVM) is widely used. Also, artificial neural net-works (ANN) have emerged as an important tool for data classification. In this paper, we propose a learning method of ANN for data classification by combining genetic algorithm (GA) and performance criterion (PC). We can prevent ANN from trapping in local minimum by using GA and also avoid over-fitting problems of training data by using PC. The data used in the simulations has four attribute and can be classified by two classes. We compare the classification performance of BP learning, SVM and proposed learning method by using the k-fold cross validation technique. Among the methods used in the simulations, we can demonstrate that our proposed method shows the best performance.