摘要
提出利用粒子群算法优化BP神经网络来改善来波到达角估计性能的方法。传统的BP神经网络易陷入局部最优,因此采用粒子群算法对网络的权值和阈值进行优化,并将其应用到来波到达角估计中。所提方法仅利用阵列协方差矩阵的第一行作为来波方位特征,与常用的协方差矩阵上三角特征相比,在不损失有效方位信息的基础上使特征维数极大降低。仿真实验证明:同经典的RBF神经网络方法相比,基于所提方法的神经网络结构更简洁,泛化性能更好,来波方位估计精度更高。
Particle swarm optimization(PSO) is used for optimization of BP neural network to improve the performance of direction of arrival(DOA) estimation. Due to the fact that BP neural network is inclined to be trapped in local minimum point, a novel network - PSO based BP neural network is proposed and applied to DOA esti- mation. This method uses the first row of correlation matrix instead of commonly used upper triangular haft of the covarianee matrix, therefore the feature dimension is largely reduced without losing any DOA information. Experimental results show that the performance of the proposed method is much better than that of classic RBF method in terms of neural network size, generalization and estimation precision.
出处
《电讯技术》
北大核心
2012年第5期694-698,共5页
Telecommunication Engineering
基金
国防科技预研项目(10J3.5.2)~~
关键词
波达角估计
粒子群算法
神经网络
特征维数
DOA estimation
particle swarm optimization
neural network
feature dimension