Radar emitter signal recognition based on feature fusion and machine learning

In the current complex electromagnetic environment, the radar emitter signal recognition methods have problems of poor anti-noise performance, low recognition accuracy rate, etc. A machine learning recognition method based on multi-domain projection features of ambiguity function is proposed. First, an ambiguity function is processed by using a Gaussian operator, Secondly, from the multi-domain perspective, select the appropriate angle to carry out two-dimensional projection to build a characteristic data set. Then, a two-stage recognition and classification method based on multi domain feature fusion is constructed. Multiple dense connected networks DenseNet121 are used as primary classifiers to train and learn the three kinds of feature data sets respectively, and the primary classification results are obtained; Finally, the results of the primary classification result is integrated through the Stacking policy to obtain the final classification result. The test results verify the effectiveness and feasibility of the proposed method, which has certain engineering value.