Title :
Direction of arrival estimation based on phase differences using neural fuzzy network
Author :
Shieh, Ching-Sung ; Lin, Chin-Teng
Author_Institution :
Dept. of Electr. & Control Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
fDate :
7/1/2000 12:00:00 AM
Abstract :
A new high-resolution direction of arrival (DOA) estimation technique using a neural fuzzy network based on phase difference (PD) is proposed. The conventional DOA estimation method such as MUSIC and MLE, are computationally intensive and difficult to implement in real time. To attack these problems, neural networks have become popular for DOA estimation. However, the normal neural networks such as the multilayer perceptron (MLP) and radial basis function network (RBFN) usually produce the extra problems of low convergence speed and/or large network size (i.e., the number of network parameters is large). Also, the may to decide the network structure is heuristic. To overcome these defects and take use of neural learning ability, a powerful self-constructing neural fuzzy inference network (SONFIN) is used to develop a new DOA estimation algorithm. By feeding the PDs of the received radar-array signals, the trained SONFIN can give high-resolution DOA estimation. The proposed scheme is thus called PD-SONFIN. This new algorithm avoids the need of empirically determining the network size and parameters in normal neural networks due to the powerful on-line structure and parameter learning ability of SONFIN. The PD-SONFIN can always find itself an economical network size in the fast learning process. Our simulation results show that the performance of the new algorithm is superior to the RBFN in terms of convergence accuracy, estimation accuracy, sensitivity to noise, and network size
Keywords :
array signal processing; convergence of numerical methods; digital simulation; direction-of-arrival estimation; fuzzy neural nets; inference mechanisms; learning (artificial intelligence); noise; radar computing; radar resolution; signal resolution; DOA estimation algorithm; PD-SONFIN; RBFN; convergence accuracy; direction of arrival estimation; economical network size; estimation accuracy; fast learning process; high-resolution DOA estimation; network size; neural fuzzy network; neural learning; noise sensitivity; on-line structure; parameter learning ability; performance; phase differences; radial basis function network; received radar-array signals; self-constructing neural fuzzy inference network; simulation results; trained SONFIN; Convergence; Direction of arrival estimation; Fuzzy neural networks; Inference algorithms; Maximum likelihood estimation; Multi-layer neural network; Multilayer perceptrons; Multiple signal classification; Neural networks; Phase estimation;
Journal_Title :
Antennas and Propagation, IEEE Transactions on