A Gridless DOA Estimation Method Based on Residual Attention Network and Transfer Learning
Xiaohuan Wu, Jiang Wang, Yang Xu, Feng Tian
Abstract
In this paper, we propose a novel deep learning (DL)-based gridless direction-of-arrival (DOA) estimation method for generalized linear arrays using residual attention network (RAN) and transfer learning (TL). The proposed method can improve the DOA estimation performance in both low and high signal-to-noise ratio (SNR) regions by focusing on the important features in the input and avoiding the problems of gradient vanishing and network degradation. Moreover, we introduce the idea of TL to reduce the complexity and costs of training. The experimental results demonstrate the effectiveness and superiority of our method compared with existing methods.
Topics & Concepts
ResidualComputer scienceTransfer of learningSignal-to-noise ratio (imaging)Artificial intelligenceDeep learningDegradation (telecommunications)Direction of arrivalComputational complexity theoryNoise (video)AlgorithmSIGNAL (programming language)Machine learningPattern recognition (psychology)Electronic engineeringEngineeringTelecommunicationsProgramming languageAntenna (radio)Image (mathematics)Direction-of-Arrival Estimation TechniquesSpeech and Audio ProcessingAntenna Design and Optimization