Radar emitter classification using intrapulse data

We consider the situation where a radar intercept rcceiver collects incomin g pulse samples from a number of of known emitters. Our objectives are to ( 1) determine the number of emitters present (duster validation); (2) classi fy the incoming pulses according to the emitters from which they originate (clustering), The determination here is only based on intrinsic pulse shape s, without any inter-poise information such as pulse repetition intervals, directions of arrival, carrier frequencies, or Doppler shifts. After pre-pr ocessing the received pulses and formulating the problem as multivariate cl ustering, we develop a coding length based on the Minimum Description Lengt h (MDL) criterion for cluster validation and develop an efficient algorithm for clustering. Comparative study and computer simulations show that the p erformance of our method is very promising.