Title
Direction-of-Arrival Estimation of Ultra-Wideband Signals in Narrowband Interference Environment Based on Power Inversion and Complex-Valued Neural Networks.
Abstract
We propose two-stage null-steering direction-of-arrival (DoA) estimation of ultra wideband (UWB) signals with power inversion algorithm and complex spatio-temporal neural network (CVSTNN). This method can estimate DoA more accurately than conventional methods in narrowband interference (NBI) environment. For null steering in UWB systems, it is necessary to adjust the amplitude and phase of tapped delay lines (TDLs) of CVSTNN. However, with a conventional CVSTNN, it often fails to estimate the arrival direction because of the NBI. We aim to reduce the influence of NBI in the learning process to avoid falling into a local solution by setting the initial weights of the TDLs with power inversion. In simulation results, it is shown that the two-stage method can realize higher DoA estimation accuracy than conventional methods.
Year
DOI
Venue
2018
https://doi.org/10.1007/s11063-017-9669-4
Neural Processing Letters
Keywords
Field
DocType
Null steering,Power inversion,Complex-valued spatio-temporal neural network (CVSTNN)
Pattern recognition,Direction of arrival,Inversion (meteorology),Control theory,Electronic engineering,Ultra-wideband,Artificial intelligence,Narrowband interference,Artificial neural network,Amplitude,Mathematics
Journal
Volume
Issue
ISSN
47
3
1370-4621
Citations 
PageRank 
References 
0
0.34
4
Authors
2
Name
Order
Citations
PageRank
Kazutaka Kikuta101.69
Akira Hirose2218.41