Artificial neural network for AOA estimation in a multipath environment over the sea

Author

Lo, Titus K Y ; Leung, Henry ; Litva, John

Author_Institution

Commun. Res. Lab., McMaster Univ., Hamilton, Ont., Canada

Volume

19

Issue

4

fYear

1994

fDate

10/1/1994 12:00:00 AM

Firstpage

555

Lastpage

562

Abstract

In this paper, we use a neural network to carry out angle-of-arrival (AOA) estimation in a multipath oceanic environment. In particular, the AOA problem is considered as a mapping from the space of AOA to the space of the sensor output. A neural network is used to determine the inverse mapping from the sensor output space to the space of AOA and this inversion is realized using a radial basis function (RBF) network. We will present the development of the RBF approach for AOA estimation. Simulations are carried out to understand the efficiency and performance of this method. Furthermore, real data are used to evaluate the RBF approach and the results demonstrate the robustness and effectiveness of this neural network method

Keywords

digital simulation; direction-of-arrival estimation; feedforward neural nets; learning (artificial intelligence); multipath channels; signal processing; angle-of-arrival estimation; artificial neural network; effectiveness; inverse mapping; mapping; multipath environment; multipath oceanic environment; radial basis function network; robustness; Artificial neural networks; Biological neural networks; Intelligent networks; Maximum likelihood estimation; Neural networks; Robustness; Sensor arrays; Signal processing algorithms; Signal resolution; Spatial resolution;

fLanguage

English

Journal_Title

Oceanic Engineering, IEEE Journal of

Publisher

ieee

ISSN

0364-9059

Type

jour

DOI

10.1109/48.338391

Filename

338391