The radar emitter recognition seems to be one of the most important tasks in electronic support measures (ESM) and electronic intelligence (ELINT) systems. The main function of electronic support measures system is threat detection and area surveillance to determine the identity of surrounding emitters (radars). A typical intercept receiver system in ESM must be able to intercept signals from antenna (or antenna array) and extracts the basic parameters (features) into structures called pulse descriptor words (PDWs). These basic parameters usually contain the values for radio frequency (RF), pulse width (PW), direction of arrival (DOA), pulse repetition interval (PRI), time of arrival (TOA) and pulse amplitude (PA). After determining these parameters it is possible to identify the specific emitters. The radar emitter recognition consists of two major goals. First goal is determining the number of emitters present. Second objective is justify; MARGIN: 0cm 0cm 0pt; unicode-bidi: embed; DIRECTION: ltr" In this thesis we propose a three layer model for achieving specific emitter identification. A new feature subset selection method via multi-objective particle swarm optimization and gap-statistic clustering criterion is proposed in order to determine the number of emitters and eliminate superfluous features. Then we propose a new hybrid clustering algorithm by combining Rough k-means and imperialist competitive algorithm. Finally radar data are justify; MARGIN: 0cm 0cm 0pt; unicode-bidi: embed; DIRECTION: ltr" Keywords: Radar, pulse descriptor words, feature selection, Rough k-means, artificial neural network, clustering.
