Linear DOA Estimation Method Based on NGO-SVM

In recent years, it has become a major trend to use DOA (Direction of Arrival) estimation method to process array signals in large array systems. DOA estimation methods have shown remarkable capabilities in spatial signal resolution and improving system capacity. However, traditional DOA estimation methods suffer from severe performance degradation in low signal-to-noise ratio conditions. To address this issue, this paper proposes a linear DOA estimation method based on NGO-SVM. The algorithm combines the NGO (Northern Goshawk Optimization) algorithm with SVM (Support Vector Machines) to enhance the performance of the NGO algorithm. By training the extracted features from the samples, the algorithm improves the accuracy of DOA linear estimation. Simulation experiments demonstrate that under identical conditions, the proposed algorithm outperforms the comparison algorithms in terms of Root Mean Square Error (RMSE) performance and exhibits superior angular resolution.