A Novel Support Vector Machine Based Radar Individual Recognition Algorithm Under Inconsistent Noise Condition
Jiayue Wu, Bin Wu, Haonan Niu, Congcong Ma, Zhao Wang, Peng Li · 2020
In modern electronic warfare, the complexity of electromagnetic environment makes it more and more difficult to identify the emitter. Because of the uncertainty of battlefield situation, the signal-to-noise ratio (SNR) of radar signal is different, which affects the accuracy of emitter identification process. Normally, the amount of the received emitter signal may be small, so the selection of classifier has a great impact on the recognition result. Traditional support vector machine (SVM) has high classification accuracy and strong generalization ability for small sample data, which can solve this problem well. Considering the different contribution of features to individual recognition, we propose an improved SVM algorithm with weight optimization, and apply it to the problem of individual recognition of emitter under the condition of different SNR. The correctness and validity of the algorithm are verified by simulation experiments.