Radar emitter recognition method based on kernel extreme learning machine optimized by sparrow search algorithm

Aiming at the problem of low radar emitter recognition rate in electronic reconnaissance under low signal-to-noise ratio (SNR) conditions, a radar emitter recognition method based on kernel extreme learning machine optimized by sparrow search algorithm is proposed. By constructing a radar database, the kernel extreme learning machine optimized by sparrow search algorithm is used to identify radar data under different noise conditions, and is compared with the traditional kernel extreme learning machine and support vector machine method. The results show that the recognition accuracy of the proposed method is higher than that of other methods in different noise conditions.