Classification of Radar Emitter Signals Using Cascade Feature Extractions and Hierarchical Decision Technique

An effective approach to classify the radar emitter signals is presented, which is based on a cascade feature extractions and a hierarchical decision technique. Firstly, the instantaneous autocorrelation, improved by non-ambiguity phase expansion and moving average, is used to extract the primary instantaneous frequencies of radar signals. Then, a successive normalization-based feature re-extraction algorithm is performed on the previously extracted instantaneous frequencies to obtain the classification characteristics vector. Finally, a hierarchical decision classifier is exploited to categorize signals automatically. Simulation results demonstrate the effectiveness and feasibility of the proposed scheme of signals classification.