A Lightweight UWB NLOS Detection Algorithm Using Referenced CIR Similarity Metrics

被引:0
|
作者
He, Xu [1 ]
Yang, Runkun [1 ]
Mo, Lingfei [1 ]
Meng, Xiaolin [1 ]
Yang, Fanxing [1 ]
Zhang, Youdong [1 ]
Wang, Qing [1 ]
机构
[1] Southeast Univ, Sch Instrument & Engn, Nanjing 210096, Peoples R China
关键词
Vectors; Measurement; Radio frequency; Feature extraction; Data models; Probability distribution; Entropy; UWB; NLOS; CIR; similarity metric; RCS;
D O I
10.1109/LWC.2024.3446632
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A lightweight and effective algorithm is benefit for real-world applications and edge devices. This letter presents a lightweight algorithm for Non-Line-of-Sight (NLOS) detection in Ultra-Wideband (UWB) systems, using the referenced Channel Impulse Response (CIR) similarity metrics. It retains essential UWB channel characteristics while incorporating a Radar Cross-Section (RCS)-inspired feature engineering method to capture the effective NLOS representation. It bears novel features to significantly reduce the input data dimensions, model parameters, and Floating-point operations (Flops) by 64.9%, 78.5%, 76.0%, respectively, with comparable performance to the latest State-Of-The-Art (SOTA) solutions. We demonstrate its effectiveness through actual measurements and comparative experiments in mixed complex Line-Of-Sight (LOS)/NLOS dataset, offering a computationally efficient solution for UWB NLOS detection with effective representation.
引用
收藏
页码:2797 / 2801
页数:5
相关论文
共 50 条
  • [1] Predictive NLOS Detection for UWB Indoor Positioning Systems Based on the CIR
    Schroeer, Guido
    Haefner, Bernhard
    2018 15TH WORKSHOP ON POSITIONING, NAVIGATION AND COMMUNICATIONS (WPNC), 2018,
  • [2] A Lightweight CIR-Based CNN With MLP for NLOS/LOS Identification in a UWB Positioning System
    Si, Minghao
    Wang, Yunjia
    Siljak, Harun
    Seow, Cheekiat
    Yang, Hongchao
    IEEE COMMUNICATIONS LETTERS, 2023, 27 (05) : 1332 - 1336
  • [3] NLOS Detection and Mitigation for UWB/IMU Fusion System Based on EKF and CIR
    Zeng, Zhuoqi
    Liu, Steven
    Wang, Lei
    2018 IEEE 18TH INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY (ICCT), 2018, : 376 - 381
  • [4] NLoS Measurement Elimination in UWB Signals Using Anomaly Detection
    Gunes, Ahmet
    Gullu, Ali Ihsan
    Alam, Muhammad Shahab
    Sucu, Esat Serhat
    Kose, Serdar
    Goze, Ahmet Gokhan
    Yaldtz, Hilal Esra
    Cihangeri, Ahmet Adil
    Akman, Caglar
    2023 31ST SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU, 2023,
  • [5] Detection Scheme for Human Body using UWB Radio in NLOS Environments
    Ohno, Kohei
    Echizenya, Daiki
    Shigenobu, Taiga
    2017 IEEE 17TH INTERNATIONAL CONFERENCE ON UBIQUITOUS WIRELESS BROADBAND (ICUWB), 2017,
  • [6] NLOS Detection using UWB Channel Impulse Responses and Convolutional Neural Networks
    Stahlke, Maximilian
    Kram, Sebastian
    Mutschler, Christopher
    Mahr, Thomas
    2020 INTERNATIONAL CONFERENCE ON LOCALIZATION AND GNSS (ICL-GNSS), 2020,
  • [7] Performance improvement of multiuser detection using a genetic algorithm in DS-CDNIA UWB systems over an extreme NLOS multipath channel
    Tan-Hsu Tan
    Yung-Fa Huang
    Chung-Weng Lin
    Ray-Hsiang Fu
    2006 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-6, PROCEEDINGS, 2006, : 1945 - +
  • [8] Detection of a reservoir water level using shape similarity metrics
    Pipitone, Claudia
    Maltese, Antonino
    Dardanelli, Gino
    Capodici, Fulvio
    Lo Brutto, Mauro
    La Loggia, Goffredo
    REMOTE SENSING FOR AGRICULTURE, ECOSYSTEMS, AND HYDROLOGY XIX, 2017, 10421
  • [9] Differential NLOS Error Detection in UWB-based Localization Systems using Logistic Regression
    Zandian, Reza
    Witkowski, Ulf
    2018 15TH WORKSHOP ON POSITIONING, NAVIGATION AND COMMUNICATIONS (WPNC), 2018,
  • [10] A Lightweight Intrusion Detection System for CAN Protocol Using Neighborhood Similarity
    Refat, Rafi Ud Daula
    Abu Elkhail, Abdulrahman
    Malik, Hafiz
    2022 7TH INTERNATIONAL CONFERENCE ON DATA SCIENCE AND MACHINE LEARNING APPLICATIONS (CDMA 2022), 2022, : 121 - 126