Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Sources Information Fusion Learning for Multi-Points NLOS Localization

Bohao Wang, Fenghao Zhu, Mengbing Liu, Chongwen Huang, Qianqian Yang, Ahmed Alhammadi, Zhaoyang Zhang, Mérouane Debbah

TL;DR

A novel multi-source information fusion learning framework referred to as the Autosync Multi-Domain NLOS Localization (AMDNLoc) that employs a two-stage matched filter fused with a target tracking algorithm and iterative centroid-based clustering to automatically and irregularly segment NLOS regions, ensuring uniform fingerprint distribution within channel state information across frequency, power, and time-delay domains.

Abstract

Accurate localization of mobile terminals is crucial for integrated sensing and communication systems. Existing fingerprint localization methods, which deduce coordinates from channel information in pre-defined rectangular areas, struggle with the heterogeneous fingerprint distribution inherent in non-line-of-sight (NLOS) scenarios. To address the problem, we introduce a novel multi-source information fusion learning framework referred to as the Autosync Multi-Domain NLOS Localization (AMDNLoc). Specifically, AMDNLoc employs a two-stage matched filter fused with a target tracking algorithm and iterative centroid-based clustering to automatically and irregularly segment NLOS regions, ensuring uniform fingerprint distribution within channel state information across frequency, power, and time-delay domains. Additionally, the framework utilizes a segment-specific linear classifier array, coupled with deep residual network-based feature extraction and fusion, to establish the correlation function between fingerprint features and coordinates within these regions. Simulation results demonstrate that AMDNLoc significantly enhances localization accuracy by over 40\% compared with traditional convolutional neural networks on the wireless artificial intelligence research dataset.

Multi-Sources Information Fusion Learning for Multi-Points NLOS Localization

TL;DR

A novel multi-source information fusion learning framework referred to as the Autosync Multi-Domain NLOS Localization (AMDNLoc) that employs a two-stage matched filter fused with a target tracking algorithm and iterative centroid-based clustering to automatically and irregularly segment NLOS regions, ensuring uniform fingerprint distribution within channel state information across frequency, power, and time-delay domains.

Abstract

Accurate localization of mobile terminals is crucial for integrated sensing and communication systems. Existing fingerprint localization methods, which deduce coordinates from channel information in pre-defined rectangular areas, struggle with the heterogeneous fingerprint distribution inherent in non-line-of-sight (NLOS) scenarios. To address the problem, we introduce a novel multi-source information fusion learning framework referred to as the Autosync Multi-Domain NLOS Localization (AMDNLoc). Specifically, AMDNLoc employs a two-stage matched filter fused with a target tracking algorithm and iterative centroid-based clustering to automatically and irregularly segment NLOS regions, ensuring uniform fingerprint distribution within channel state information across frequency, power, and time-delay domains. Additionally, the framework utilizes a segment-specific linear classifier array, coupled with deep residual network-based feature extraction and fusion, to establish the correlation function between fingerprint features and coordinates within these regions. Simulation results demonstrate that AMDNLoc significantly enhances localization accuracy by over 40\% compared with traditional convolutional neural networks on the wireless artificial intelligence research dataset.
Paper Structure (13 sections, 12 equations, 6 figures, 1 table, 2 algorithms)

This paper contains 13 sections, 12 equations, 6 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. System and Channel Model
  3. AMDNLoc Multi-sources Framework
  4. Heterogeneity Matched Filter
  5. PFCFR
  6. ADCAM
  7. Data Fusing and Cleansing
  8. Network Training
  9. Numerical Results
  10. Datasets
  11. Visualization of Classification Areas
  12. Effectiveness of Classification Methods
  13. Conclusion

Figures (6)

  • Figure 1: System Diagram of proposed AMDNLoc framework compared with existing methods.
  • Figure 2: The wireless channel from MT $m$ to the BS.
  • Figure 3: CFR example figure of randomly selected MTs in the 00743 scenario of WAIR-D
  • Figure 4: NLOS pre-classification.
  • Figure 5: MSE with epochs of multiple processing results.
  • ...and 1 more figures