DocumentCode
3196758
Title
A novel algorithm for wideband DOA estimates based on neural network
Author
Lei, Zhong Ding ; Huang, Xiu Kun ; Zhang, Shu Jing
Author_Institution
Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
Volume
4
fYear
1997
fDate
9-12 Jun 1997
Firstpage
2167
Abstract
In this paper, a novel class of focusing matrices for the coherent signal subspace method is proposed. These matrices are formed based on a BP neural network and the concept of uniform focusing transformation of the direction-of-arrival (DOA) of wideband sources. The proposed DOA estimating procedure is efficient without prior knowledge of the DOAs
Keywords
Monte Carlo methods; backpropagation; direction-of-arrival estimation; matrix algebra; neural nets; signal sources; BP neural network; coherent signal subspace method; focusing matrices; uniform focusing transformation; wideband DOA estimates; wideband sources; Covariance matrix; Direction of arrival estimation; Frequency; Geometry; Matrix decomposition; Narrowband; Neural networks; Sensor arrays; Signal processing algorithms; Wideband;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks,1997., International Conference on
Conference_Location
Houston, TX
Print_ISBN
0-7803-4122-8
Type
conf
DOI
10.1109/ICNN.1997.614242
Filename
614242
Link To Document