Multiple Angles of Arrival Estimation using Neural Networks
This work addresses direction-finding problems in signal processing, particularly for radar or communications systems, but is incremental as it applies neural networks to an existing domain without major methodological breakthroughs.
The paper tackles the challenge of estimating multiple angles of arrival (DoA) in scenarios with many source signals, where traditional methods like MUSIC and ESPRIT face computational or robustness issues, and shows that a neural network achieves accurate estimation under low SNR conditions.
MUltiple SIgnal Classification (MUSIC) and Estimation of signal parameters via rotational via rotational invariance (ESPRIT) has been widely used in super resolution direction of arrival estimation (DoA) in both Uniform Linear Arrays (ULA) or Uniform Circular Arrays (UCA). However, problems become challenging when the number of source signal increase, MUSIC suffer from computation complexity when finding the peaks, while ESPRIT may not robust to array geometry offset. Therefore, Neural Network become a potential solution. In this paper, we propose a neural network to estimate the azimuth and elevation angles, based on the correlated matrix extracted from received data. Also, a serial scheme is listed to estimate multiple signals cases. The result shows the neural network can achieve an accurate estimation under low SNR and deal with multiple signals.