Infrared and Laser Engineering, Volume. 52, Issue 12, 20230183(2023)

Deep learning-based impact mitigation method for UWB NLOS propagation

Wanqing Liu1...2, Guo Wei1,2, Chunfeng Gao1,2, Xudong Yu1,2, Zhongqi Tan1,2, Chengzhong Zhang3, Chengzhi Hou1,2, and Xu Zhu12 |Show fewer author(s)
Author Affiliations
  • 1College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, China
  • 2Nanhu Laser Laboratory, National University of Defense Technology, Changsha 410073, China
  • 3College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China
  • show less
    Figures & Tables(12)
    Two categories of RBU modules
    Basicblock (a) and Bottleneck (b)
    Schematic diagram of ResNet-18 network structure
    Non-local module calculation flow chart
    Two basic types of modules for NLO-ResNet: NLRBU-Iden (a) and NLRBU-Conv (b)
    Schematic diagram of NLO-ResNet network structure
    Typical schematic of CIR data under LOS and NLOS propagation conditions
    Schematic of the variation of the network performance with the dimensionality of the input CIR data
    Comparison of the basic modules of CNN (a), ResNet (b), and NLO-ResNet (c)
    Variation of the loss function on the test sets
    Comparison chart of predicted range error and actual range error
    • Table 1. Experiment results of network performance comparison

      View table
      View in Article

      Table 1. Experiment results of network performance comparison

      NetworkMAE/m
      Raw data0.1242
      SVM0.0782
      MLP0.0815
      CNN0.0776
      ResNet0.0715
      NLO-ResNet0.0681
    Tools

    Get Citation

    Copy Citation Text

    Wanqing Liu, Guo Wei, Chunfeng Gao, Xudong Yu, Zhongqi Tan, Chengzhong Zhang, Chengzhi Hou, Xu Zhu. Deep learning-based impact mitigation method for UWB NLOS propagation[J]. Infrared and Laser Engineering, 2023, 52(12): 20230183

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Apr. 10, 2023

    Accepted: --

    Published Online: Feb. 23, 2024

    The Author Email:

    DOI:10.3788/IRLA20230183

    Topics