Radar signal feature extraction based on wavelet ridge and high order spectra analysis

In this paper, a novel feature extraction method for radar emitter signals is introduced. The modern radar signal waveforms are used for experiment simulation such as the linear frequency modulation, FSK and PSK-coded. The wavelet ridges and higher-order statistics are used to extract signal features. These features extracted by proposed methods are discriminative and suitable for radar emitter classification, especially for specific emitter identification (SEI). Then these discriminative and low dimensional features achieved are fed to a fuzzy support vector machine classifier for different radar emitter signals. In simulation, the classifier attains over 80% overall average correct classification rate. Experimental results show that the proposed methodology is efficient for different complex radar signals detection and classification in modern electronic warfare environment.