Complexity feature extraction of radar emitter signals

Because the intra-pulse modulation laws of radar emitter signals reflect directly on the signal waveform, a novel approach is presented to extract the complexity features (CFs) of radar emitter signals. CFs, including Lempel-Ziv complexity (LZC) and correlation dimension (CD), can measure the complexity and irregularity of radar signals effectively. To show the effectiveness and feasibility of the introduced approach, CFs of 10 typical radar emitter signals are extracted in our experiments. The results demonstrate that the CFs have good characteristics for clustering the same radar signals and separating different radar signals, which indicates that CF can simplify the design procedure of classifiers and greatly heighten the identification accuracy rate of radar emitter signals.