Research Article
Convolutional Neural Network-Based DOA Estimation Using Non-uniform Linear Array for Multipath Channels
@INPROCEEDINGS{10.1007/978-3-030-63083-6_4, author={Van-Sang Doan and Thien Huynh-The and Van-Phuc Hoang and Dong-Seong Kim}, title={Convolutional Neural Network-Based DOA Estimation Using Non-uniform Linear Array for Multipath Channels}, proceedings={Industrial Networks and Intelligent Systems. 6th EAI International Conference, INISCOM 2020, Hanoi, Vietnam, August 27--28, 2020, Proceedings}, proceedings_a={INISCOM}, year={2020}, month={11}, keywords={Convolution neural network DOA estimation Multipath channels Antenna array}, doi={10.1007/978-3-030-63083-6_4} }- Van-Sang Doan
Thien Huynh-The
Van-Phuc Hoang
Dong-Seong Kim
Year: 2020
Convolutional Neural Network-Based DOA Estimation Using Non-uniform Linear Array for Multipath Channels
INISCOM
Springer
DOI: 10.1007/978-3-030-63083-6_4
Abstract
In this paper, a novel convolutional neural network (CNN) was designed for DOA estimation, which could deploy in radio-electronics systems for improving the accuracy and operation efficiency. The proposed model was evaluated with different hyper-parameter configurations for optimization, and then a suitable model was compared with other existing models to demonstrate its preeminence. Regarding dataset generation, our work considered the influence of both Gaussian noise and multipath channels to DOA estimation accuracy. According to the analysis, in frame of this study, the model with 5 conv-blocks, 48 filters, and a filter size of( 1\times 7 )achieved the best performance in terms of accuracy ((75.27\%)at(+5)dB SNR) and prediction time (10.1 ms) that notably outperformed two other state-of-the-art CNN model-based DOA estimation techniques.
