Research on ultra wide band NLoS/LoS recognition method based on the fusion of 1DCNN and LSTM

ZHENG Enrang; MENG Xin; JIANG Suying; XUE Jing; ZHANG Yi; LI Qiang

doi:10.11959/j.issn.1000-436x.2025102

您当前的位置：

首页 >

文章列表页 >

Research on ultra wide band NLoS/LoS recognition method based on the fusion of 1DCNN and LSTM

Correspondences | 更新时间：2025-07-04

- Research on ultra wide band NLoS/LoS recognition method based on the fusion of 1DCNN and LSTM
- Journal on Communications Vol. 46, Issue 6, Pages: 285-302(2025)
- 作者机构：
  
  1.陕西科技大学电气与控制工程学院，陕西西安 710021
  2.贵州大学大数据与信息工程学院，贵州贵阳 550025
- 作者简介：
- 基金信息：
  
  The Natural Science Basic Research Program of Shaanxi Province(2024JC-YBQN-0400)
- DOI：10.11959/j.issn.1000-436x.2025102
  CLC： TN98
- Received：14 February 2025，
  
  Revised：2025-05-23，
  
  Published：25 June 2025
- 稿件说明：
移动端阅览
郑恩让,孟鑫,姜苏英等.基于1DCNN和LSTM融合的超宽带NLoS/LoS识别方法研究[J].通信学报,2025,46(06):285-302.

ZHENG Enrang,MENG Xin,JIANG Suying,et al.Research on ultra wide band NLoS/LoS recognition method based on the fusion of 1DCNN and LSTM[J].Journal on Communications,2025,46(06):285-302.
郑恩让,孟鑫,姜苏英等.基于1DCNN和LSTM融合的超宽带NLoS/LoS识别方法研究[J].通信学报,2025,46(06):285-302. DOI： 10.11959/j.issn.1000-436x.2025102.

ZHENG Enrang,MENG Xin,JIANG Suying,et al.Research on ultra wide band NLoS/LoS recognition method based on the fusion of 1DCNN and LSTM[J].Journal on Communications,2025,46(06):285-302. DOI： 10.11959/j.issn.1000-436x.2025102.

摘要

为提升超宽带（UWB）定位系统在非视距（NLoS）条件下的测距精度与定位性能，提出一种基于一维卷积-卷积长短期记忆（LSTM）注意力网络（1DCNN-CLANet）的深度学习模型。该模型首先利用卷积神经网络（CNN）提取通道脉冲响应（CIR）的空间特征，并利用长短期记忆网络捕捉CIR的时序特征。其次，利用CNN深度挖掘距离数据、信号振幅、最大噪声强度等额外特征。最后，引入注意力机制并构建CIR分支和额外特征分支的融合模型，实现对UWB信号的非视距/视距识别。实验结果表明，复杂环境下1DCNN-CLANet的二分类和四分类识别准确率分别为99.51%和98.47%，优于其他方案。该模型在UWB定位系统中表现出良好的非视距识别能力，具有较强的应用前景。

Abstract

A deep learning model based on one-dimensional-convolutional neural network-convolutional long short-term memory (LSTM) attention network (1DCNN-CLANet) was proposed to improve the ranging accuracy and positioning performance of ultra wide band (UWB) localization systems under non-line-of-sight (NLoS) conditions. Convolutional neural network (CNN) was first employed to extract spatial features from channel impulse response (CIR) data

and LSTM network was used to capture their temporal characteristics. Then

CNN was further applied to extract additional features such as distance data

signal amplitude

and maximum noise strength. Finally

An attention mechanism was then incorporated to fuse the CIR and additional feature branches for accurate NLoS/LoS classification. Experimental results show that 1DCNN-CLANet achieves classification accuracies of 99.51% for binary classification and 98.47% for four-class classification in complex environments

outperforming other approaches. The model demonstrates strong potential for robust NLoS identification in practical UWB localization systems.

关键词

Keywords

references

孙大洋 , 石文孝 , 张定国 . 基于室内地图推演与信号穿墙修正的定位优化方法 [J ] . 通信学报 , 2022 , 43 ( 10 ): 146 - 156 .

SUN D Y , SHI W X , ZHANG D G . Positioning optimization method based on indoor map deduction and signal through-wall correction [J ] . Journal on Communications , 2022 , 43 ( 10 ): 146 - 156 .

VEDDER B , SVENSSON B J , VINTER J , et al . Automated testing of ultrawideband positioning for autonomous driving [J ] . Journal of Robotics , 2020 , 2020 ( 1 ): 9345360 .

LEE J C , CHEN C C , SHEN C T , et al . Landmark-based scale estimation and correction of visual inertial odometry for VTOL UAVs in a GPS-denied environment [J ] . Sensors , 2022 , 22 ( 24 ): 9654 .

王慧强 , 高凯旋 , 吕宏武 . 高精度室内定位研究评述及未来演进展望 [J ] . 通信学报 , 2021 , 42 ( 7 ): 198 - 210 .

WANG H Q , GAO K X , LYU H W . Survey of high-precision localization and the prospect of future evolution [J ] . Journal on Communications , 2021 , 42 ( 7 ): 198 - 210 .

蒋锐 , 虞跃 , 徐友云 , 等 . 基于CHAN的改进卡尔曼滤波室内定位算法 [J ] . 通信学报 , 2023 , 44 ( 2 ): 136 - 147 .

JIANG R , YU Y , XU Y Y , et al . Improved Kalman filter indoor positioning algorithm based on CHAN [J ] . Journal on Communications , 2023 , 44 ( 2 ): 136 - 147 .

MOON S , YOUN W . A novel movable UWB localization system using UAVs [J ] . IEEE Access , 2022 , 10 : 41303 - 41312 .

从飞云 , 洪纵横 , 汤子安 , 等 . 基于脉冲响应消岐重构的UWB测距优化方法 [J ] . 仪器仪表学报 , 2022 , 43 ( 10 ): 13 - 21 .

CONG F Y , HONG Z H , TANG Zian , et al . An optimization method of UWB ranging based on pulse response disambiguation and reconstruction [J ] . Chinese Journal of Scientific Instrument , 2022 , 43 ( 10 ): 13 - 21 .

李文锋 , 周敬龙 , 王其 , 等 . 超宽带信号的非视距识别与测距误差抑制 [J ] . 控制与决策 , 2024 , 39 ( 8 ): 2605 - 2612 .

LI W F , ZHOU J L , WANG Q , et al . Non-line-of-sight identification and ranging error mitigation for ultra wide band signal [J ] . Control and Decision , 2024 , 39 ( 8 ): 2605 - 2612 .

李荣冰 , 王念曾 , 刘建业 , 等 . 面向相对导航的UWB测距误差估计与补偿方法 [J ] . 仪器仪表学报 , 2019 , 40 ( 5 ): 28 - 35 .

LI R B , WANG N Z , LIU J Y , et al . UWB ranging error estimation and compensation method for relative navigation [J ] . Chinese Journal of Scientific Instrument , 2019 , 40 ( 5 ): 28 - 35 .

LEE S M , YOO S , LEE J Y , et al . Drone positioning system using UWB sensing and out-of-band control [J ] . IEEE Sensors Journal , 2022 , 22 ( 6 ): 5329 - 5343 .

齐小刚 , 陈谌 , 李芷楠 . 室内定位中非视距的识别和抑制算法研究综述 [J ] . 控制与决策 , 2022 , 37 ( 8 ): 1921 - 1933 .

QI X G , CHEN C , LI Z N . A review of non-line-of-sight identification and mitigation algorithms for indoor localization [J ] . Control and Decision , 2022 , 37 ( 8 ): 1921 - 1933 .

LEE K , OH J , YOU K . CLoSed-form solution of TDOA-based geolocation and tracking: a recursive weighted least square approach [J ] . Wireless Personal Communications , 2017 , 94 ( 4 ): 3451 - 3464 .

YANG X F , ZHAO F , CHEN T J . NLoS identification for UWB localization based on import vector machine [J ] . AEU - International Journal of Electronics and Communications , 2018 , 87 : 128 - 133 .

YU K G , WEN K , LI Y B , et al . A novel NLoS mitigation algorithm for UWB localization in harsh indoor environments [J ] . IEEE Transactions on Vehicular Technology , 2019 , 68 ( 1 ): 686 - 699 .

韦子辉 , 廖戈 , 李明轩 , 等 . 基于ISODATA改进K均值聚类算法的NLoS识别技术 [J ] . 电子测量技术 , 2024 , 47 ( 4 ): 172 - 180 .

WEI Z H , LIAO G , LI M X , et al . NLoS identification technology based on ISODATA improved K-means clustering algorithm [J ] . Electronic Measurement Technology , 2024 , 47 ( 4 ): 172 - 180 .

JIANG C H , CHEN S , CHEN Y W , et al . An UWB channel impulse response de-noising method for NLoS/LoS classification boosting [J ] . IEEE Communications Letters , 2020 , 24 ( 11 ): 2513 - 2517 .

JIANG C H , SHEN J C , CHEN S , et al . UWB NLoS/LoS classification using deep learning method [J ] . IEEE Communications Letters , 2020 , 24 ( 10 ): 2226 - 2230 .

PEI Y , CHEN R Z , LI D R , et al . FCN-Attention: a deep learning UWB NLoS/LoS classification algorithm using fully convolution neural network with self-attention mechanism [J ] . Geo-spatial Information Science , 2024 , 27 ( 4 ): 1162 - 1181 .

CUI Z C , GAO Y F , HU J , et al . LoS/NLoS identification for indoor UWB positioning based on morlet wavelet transform and convolutional neural networks [J ] . IEEE Communications Letters , 2021 , 25 ( 3 ): 879 - 882 .

WANG J , YU K G , BU J W , et al . Multi-classification of UWB signal propagation channels based on one-dimensional wavelet packet analysis and CNN [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 8 ): 8534 - 8547 .

HOCHREITER S , SCHMIDHUBER J . Long short-term memory [J ] . Neural Computation , 1997 , 9 ( 8 ): 1735 - 1780 .

WYMEERSCH H , MARANO S , GIFFORD W M , et al . A machine learning approach to ranging error mitigation for UWB localization [J ] . IEEE Transactions on Communications , 2012 , 60 ( 6 ): 1719 - 1728 .

WANG Q , CHEN M S , LIU J J , et al . 1D-CLANet: a novel network for NLoS classification in UWB indoor positioning system [J ] . Applied Sciences , 2024 , 14 ( 17 ): 7609 .

BREGAR K , MOHORČIČ M . Improving indoor localization using convolutional neural networks on computationally restricted devices [J ] . IEEE Access , 2018 , 6 : 17429 - 17441 .

Views

930

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

SW-FGO target tracking method with dynamic status recognition and compensation in LOS/NLOS environments

Intelligent interference decision algorithm with prior knowledge embedded LSTM-PPO model

Using deep learning for detecting BotCloud

GMM-based localization algorithm under NLOS conditions

Blind frequency tracking based on time-domain spreading for MB-OFDM-UWB systems

Related Author

LI Qi

XIE Liangbo

YIN Huili

YANG Xiaolong

ZHOU Mu

XU Peng

ZHANG Jingke

YANG Kai

Related Institution

Chongqing Key Laboratory of Intelligent Perception and Blockchain Technology, Chongqing Technology and Business University

Chongqing Key Laboratory of Mobile Communications Technology

Chongqing Key Laboratory of Dedicated Quantum Computing and Quantum Artificial Intelligence

School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications

School of Computer Science and Technology, Zhejiang Sci-Tech University

AI脑图

AI问答

⁰