摘要
为了有效地解决使用深度神经网络求解波达方向(DOA)估计涉及到的大规模分类器的训练和部署实现,本文提出将传统的one-hot分类器分解为多个类别互质的小分类器,然后联合使用多个互质分类器的分类结果重构原始one-hot标签。首先使用标签分解,将原始标签分解为多个互质的小标签,小标签对应的类别为原始类别对质数取余数的结果。其次,通过独立并行地训练每一个互质分类器,降低了大类别条件下分类器的训练难度。仿真结果表明,相比one-hot分类器,互质分类器网络的复杂度低,易于训练。另外,使用互质分类器进行DOA估计能够实现超分辨并且估计的精度比one-hot分类器以及稀疏贝叶斯学习等方法更高。
In order to effectively solve the training and deployment implementation of large-scale classifiers involved in deep neural network to solve direction of arrival(DOA)estimation,we propose to decompose the traditional one-hot classifier into small co-prime classifiers with relatively small label,and then reconstruct the original one-hot label by combining the classification results of co-prime classifiers.First,the original label is decomposed into a number of small co-prime labels.The corresponding category of the small labels is the result of the remainder of the prime number of the original label.Secondly,by training each co-prime classifier independently and in parallel,the difficulty of training classifiers under the condition of large categories is reduced.The simulation results show that compared with the one-hot classifier,the co-prime classifiers has lower complexity and is easy to train.In addition,DOA estimation using co-prime classifiers can achieve super-resolution and the estimation accuracy is higher than that of one-hot classifier and sparse Bayesian learning method.
作者
吴双
袁野
马育红
黄敬健
袁乃昌
WU Shuang;YUAN Ye;MA Yuhong;HUANG Jingjian;YUAN Naichang(The State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System,National University of Defense Technology,Changsha,Hunan 410073,China)
出处
《信号处理》
CSCD
北大核心
2021年第1期1-10,共10页
Journal of Signal Processing
关键词
波达方向估计
深度卷积神经网络
标签分解
大规模分类问题
direction of arrival estimation
deep convolution neural network
label decomposition
large size classification problem
