Ajou University repository

A Design of Multi-Head Attention Neural Network for UWB NLOS Identification in Outdoor
Citations

SCOPUS

0

Citation Export

Publication Year
2024-03-01
Journal
Journal of Korean Institute of Communications and Information Sciences
Publisher
Korean Institute of Communications and Information Sciences
Citation
Journal of Korean Institute of Communications and Information Sciences, Vol.49 No.3, pp.361-364
Keyword
CIRLOS/NLOSMulti-head attentionUWB
All Science Classification Codes (ASJC)
Computer Networks and CommunicationsInformation Systems and ManagementComputer Science (miscellaneous)
Abstract
In this paper, we introduce a method of classifying UWB CIR data into LOS and NLOS environments by applying the multi-head attention algorithm. The 1016 UWB CIR values sampled at 100 ms intervals are divided into 100 segments. By comparing the classification time and accuracy of the LSTM-CNN algorithm and the multi-head attention algorithm, it is shown that the latter achieved a classification accuracy of 94.41% for LOS/NLOS environments, outperforming the LSTM-CNN model.
ISSN
2287-3880
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/34062
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85189146880&origin=inward
DOI
https://doi.org/10.7840/kics.2024.49.3.361
Journal URL
https://engjournal.kics.or.kr/digital-library/90603
Type
Article
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Ko, Young-Bae Image
Ko, Young-Bae고영배
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.