Neural Networks for Sequential Discrimination of Radar Targets.

摘要

In this paper, perceptron neural networks are applied to the problem of discriminating between two classes of radar returns. The perceptron neural networks are used as nonlinearities in two threshold sequential discriminators which act upon samples of the radar return. The test statistic compared to the thresholds is of the form T sub n(Z) = sum over j=1 to n-K+1 of gamma(Zj,Zj+1, ... ,Zj+K-1) where Z sub i, i = 1,2,3,... are the radar samples and gamma() is the nonlinearity formed by the neural network. Numerical results are presented and compared to existing discrimination schemes.