A Deep Learning Architecture for Broadband DOA Estimation
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 244-247
Abstract
An efficient neural network-based approach for broadband direction of arrival (DOA) estimation is presented in this paper. The received data of the uniform circle array (UCA) is transformed into direction image, which is used as the input of the neural network. The phase component of the spatial covariance matrix of the received signal is extracted to form the direction image. We establish a convolutional neural network (CNN) with five hidden layers to learn the inverse mapping from the space of possible antenna element excitations to the space of possible angular directions to the signal source. DOA estimation is formulated as a regression problem, where the each DOA label to the direction image is consisted of the sine and cosine values of the angle of arrival. Simulation results show that the trained CNN network can be successfully used for broadband DOA estimation. The performance of the developed CNN model is comparable to the performance of the conventional algorithms at the lower signal-to-noise ratio. Importantly, the proposed CNN estimator further reduces the computation time which makes it successful to apply to real-time applications.Keywords
This publication has 8 references indexed in Scilit:
- RF-based Direction Finding of UAVs Using DNN2018
- Direction of arrival estimation for smart antenna in multipath environment using convolutional neural networkInternational Journal of RF and Microwave Computer-Aided Engineering, 2018
- Underdetermined Wideband DOA Estimation for Off-Grid Sources with Coprime Array Using Sparse Bayesian LearningSensors, 2018
- Joint DOA and frequency estimation with sub‐Nyquist sampling for more sources than sensorsIET Radar, Sonar & Navigation, 2017
- Joint frequency and 2-D DOA recovery with sub-Nyquist difference space-time array2017
- Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Underdetermined DOA Estimation Method for Wideband Signals Using Joint Nonnegative Sparse Bayesian LearningIEEE Signal Processing Letters, 2017