欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对利用智能学习方法进行多信号源方向估计模型难以构建的难题,文中提出了一种有效的降维构建方法。该方法首先对构造的DOA矩阵进行特征分解,获取各个信号源的DOA矩阵导向矢量,这样就可以用单信号样本来训练RBF神经网络模型,然后利用训练好的模型分别对分离出来的信号导向矢量进行映射估计,从而达到了对多信号源来波方向进行降维估计的目的,仿真结果也证明了文中方法的有效性和可行性。
英文摘要：
To solve the modeling problem of multi-source direction estimation based on smart learning method,an effective dimension-degraded modeling approach was proposed in this paper.This approach based on decomposing the DOA matrix could result in the steering-vector of each signal source,then they were taken as the input vector to train the radial basis function neural networks（RBFNN） model with the training sets of single source,the trained model could approximate the nonlinear mapping from the separating input vectors of multi-source to direction-of-arrival.The simulation results showed the effectiveness and feasibility of this method.
同期刊论文项目
同项目期刊论文
期刊信息
位置：