针对目前基于信道脉冲响应(Channel Impulse Response,CIR)的非视距(None Line of Sight,NLoS)/视距(Line of Sight,LoS)识别方法精度低、泛化能力差的问题,提出了一种多层卷积神经网络(Convolutional Neural Network,CNN)与通道注意力模块(Channel Attention Module,CAM)相结合的NLoS/LoS识别方法.在多层CNN中嵌入CAM提取原始CIR的时域数据特征,利用全局平均池化层代替全连接层进行特征整合并分类输出.使用欧洲地平线2020计划项目eWINE公开的数据集进行不同结构模型和不同识别方法的对比实验,结果表明,所提出的CNN-CAM模型LoS和NLoS召回率分别达到了 92.29％与87.71％,准确率达到了 90.00％,F1分数达到了 90.22％.与现有多种传统识别方法相比,均具有更好的识别效果.
Research on NLoS/LoS Identification Method Based on CNN-CAM
To address the low accuracy and insufficient generalization ability of current None Line of Sight(NLoS)/Line of Sight(LoS)identification methods based on Channel Impulse Response(CIR),a multilayer Convolutional Neural Network(CNN)combined with Channel Attention Module(CAM)for NLoS/LoS identification method is proposed.Firstly,the CAM is embedded in the multilayer CNN to extract the time-domain data features of the original CIR.Then,the global average pooling layer is used to replace the fully connected layer for feature integration and classification output.In addition,the public dataset from project eWINE of the European Horizon 2020 Program is used to perform comparative experiments with different structural models and different identification methods.The results show that the proposed CNN-CAM model has a LoS recall of 92.29％,NLoS recall of 87.71％,accuracy of 90.00％,and F1-score of 90.22％.Compared with the existing conventional methods,it has better performance advantages.
国家科技期刊平台
NSTL
万方数据
