A GMM-based Algorithm for Classification of Radar emitters

摘要

A Gaussian Mixture Model(GMM)-based Algorithm for the Classification of Radar emitters in autonomous Electronic Support Measure Systems is described in this paper. We first build a Gaussian model for every radar emitter, and then use the Expectation-Maximization (EM) Algorithm to train the parameters of the model. Finally, we construct a classifier whose input is the parameters of pulse and whose output is the type of radar. Results of experiments and comparisons with Neural Network Algorithm (Fuzzy ARTMAP) demonstrate that the proposed algorithm is effective in the condition of low SNR.