An ISSA-SVM-based Approach for Identifying the Radar Working State of Non-cooperator

In this paper, an improved sparrow search algorithm-support vector machine (ISSA-SVM) is proposed for the recognition of radar working state. Firstly, a non-cooperative-based radar signal feature model that better fits the operational scenario is established. Second, the penalty coefficients and width parameters were optimized to improve the accuracy and stability of SVM identification. Tent chaotic sequence is used to expand the search range of the initial solution. The simulation results show that the algorithm can still maintain high recognition accuracy in electronic reconnaissance with limited interception times.