Robust First Path Detection Based on Two-Stage CNN for Unspecified UWB Pulse Shape

Sehwan Choi, Chaehun Im, Chungyong Lee

Research output: Contribution to journalConference articlepeer-review

Abstract

In this paper, we propose a technique by exploiting the two-stage convolutional neural network (CNN) to improve the ranging accuracy regardless of the pulse shape of the received signal in the ultra-wideband (UWB) system. UWB system could be degraded localization accuracy according to pulse shapes between transceiver. In particular, the capability of the receiver to detect a small signal level has been improved recently, and pulse shape compatibility will become even more important for UWB devices. There are no mandatory specifications or interoperability testing, as of now, so that future compatibility issues can exacerbate positioning accuracy. The proposed method shows that precise ranging even if an unspecified pulse shape-based signal is received.

Original languageEnglish
Pages (from-to)519-520
Number of pages2
JournalProceedings - IEEE Consumer Communications and Networking Conference, CCNC
DOIs
Publication statusPublished - 2022
Event19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022 - Virtual, Online, United States
Duration: 2022 Jan 82022 Jan 11

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Robust First Path Detection Based on Two-Stage CNN for Unspecified UWB Pulse Shape'. Together they form a unique fingerprint.

Cite this