Feature extraction using autocorrelation function for radar emitter signals

In this paper, an approach for intra-pulse feature extraction of radar emitter signals is proposed based on the autocorrelation function (ACF) for first differencing. The envelop features, which can highlight the differences in modulation information of radar emitter signals, are extracted from autocorrelation function of first difference transformation. In order to reduce the dimensions of envelop feature set and heighten the sorting rate of radar emitter signals, the criterion adopted degree of separability to select optimal feature subset. Computer simulations show that the features of seven typical radar emitter signals extracted by autocorrelation function have good performance of anti-noise and clustering when SNR varies from -5dB to 0dB.