Off-grid doa estimation via two-stage cascaded neural network

Hyeonjin Chung, Hyeongwook Seo, Jeungmin Joo, Dongkeun Lee, Sunwoo Kim

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


This paper introduces an off-grid DoA estimation via two-stage cascaded network which can resolve a mismatch between true direction-of-arrival (DoA) and discrete angular grid. In the first-stage network, the initial DoAs are estimated with a convolutional neural network (CNN), where initial DoAs are mapped on the discrete angular grid. To deal with the mismatch between initially estimated DoAs and true DoAs, the second-stage network estimates a tuning vector which represents the difference between true DoAs and nearest discrete angles. By using tuning vector, the final DoAs are estimated by moving initially estimated DoAs as much as the difference between true DoAs and nearest discrete angles. The limitation on estimation accuracy induced by the discrete angular grid can be resolved with the proposed two-stage network so that the estimation accuracy can be further enhanced. Simulation results show that adding the second-stage network after the first-stage network helps improve the estimation accuracy by resolving mismatch induced by the discretized grid. In the aspect of the implementation of machine learning, results also show that using CNN and using PReLU as the activation function is the best option for accurate estimation.

Original languageEnglish
Article number228
Issue number1
StatePublished - 2021 Jan 1


  • Cascaded neural net-work
  • Convolutional neural network (CNN)
  • Deep neural network (DNN)
  • Machine learning
  • Off-grid direction-of-arrival (DoA) estimation
  • Sparse representation


Dive into the research topics of 'Off-grid doa estimation via two-stage cascaded neural network'. Together they form a unique fingerprint.

Cite this