无线电工程2024，Vol.54Issue(8)：1871-1880,10.DOI:10.3969/j.issn.1003-3106.2024.08.005
基于CNN-CAM的NLoS/LoS识别方法研究
Research on NLoS/LoS Identification Method Based on CNN-CAM
摘要
Abstract
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.关键词
超宽带/非视距/视距识别/卷积神经网络/通道注意力模块/信道脉冲响应Key words
UWB/NLoS/LoS identification/CNN/CAM/CIR分类
信息技术与安全科学引用本文复制引用
苏佳,张晶晶,易卿武,黄璐,杨子寒..基于CNN-CAM的NLoS/LoS识别方法研究[J].无线电工程,2024,54(8):1871-1880,10.基金项目
国家重点研发计划——地下大空间高精度定位导航与控制技术(2021YFB3900800)High Precision Positioning,Navigation and Control Technology for Large Underground Space,National Key R&D Program of China(2021YFB3900800) （2021YFB3900800）
