Radar transmitter classification using non-stationary signal classifier

Abstract

This paper presents a classification method which discriminates between two radar transmitters based on the received pulses. A simple radar transmitter model is presented to which a non-stationary signal classifier is applied. The classifier is a support vector machine which is applied to the radar pulse's time-frequency representation. The time-frequency representation is refined using particle swarm optimization to increase the classification accuracy. The classification accuracy is tested in an additive white Gaussian noise channel. An acceptable classification accuracy is reported from component tolerances as small as 2% on the transmitter's modulator.