ResNet Based for Sum and Difference Co-array DOA Estimation
YOU Yuliang
GUO Hongcan
WANG Xue
Abstract：The differentce co-array of the traditional co-prime array has"holes",it lacks some virtual array elements.In this paper,the sum-and-difference co-array is used to form a larger continuous virtual array,which retains the traditional co-prime ar-ray configuration.At the same time,residual network(ResNet)is applied to the direction of arrival(DOA)estimation algorithm.The proposed algorithm first processes the spatial smoothing matrix output by the sum and difference co-array to obtain the charac-teristic data,and then input it into ResNet to transform the DOA estimation into a non-linear mapping relationship between the char-acteristic data and the DOA.DOA estimation is achieved by signal classification through ResNet.Compared with the traditional co-prime array,the ResNet-based sum and difference co-array DOA estimation algorithm has stronger accuracy and adaptability.
Keywords：sum and difference co-arrayDOA estimationResNetspatial smoothing matrix
Publication Date：2023-10-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 2251-2256 )