Variational autoencoder-based multipath clustering algorithm for terahertz channels

To address the shortcomings of multipath clustering algorithms in terahertz channel modeling, particularly in terms of multidimensional parameter adaptability and unsupervised feature separation, a variational autoencoder-based latent space multipath clustering (VAE-LMC) model was proposed. Firstly,...

Full description

Saved in:
Bibliographic Details
Main Authors: HAO Xinyu, LIAO Xi, ZHENG Xiangquan, WANG Yang, LIN Feng, CHEN Qianbin, ZHANG Jie
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2025-06-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025084/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849424452426661888
author HAO Xinyu
LIAO Xi
ZHENG Xiangquan
WANG Yang
LIN Feng
CHEN Qianbin
ZHANG Jie
author_facet HAO Xinyu
LIAO Xi
ZHENG Xiangquan
WANG Yang
LIN Feng
CHEN Qianbin
ZHANG Jie
author_sort HAO Xinyu
collection DOAJ
description To address the shortcomings of multipath clustering algorithms in terahertz channel modeling, particularly in terms of multidimensional parameter adaptability and unsupervised feature separation, a variational autoencoder-based latent space multipath clustering (VAE-LMC) model was proposed. Firstly, the variational autoencoder (VAE) was utilized to learn latent representations of multipath delays and arrival angles, enhancing feature separability. Secondly, K-Means clustering was embedded into the VAE framework, with joint optimization of reconstruction loss, KL divergence, and clustering loss functions to resolve the challenges of feature separation in unsupervised learning. Finally, multipath clustering was performed in the latent space, and the results were mapped back to the real data space. Terahertz channel measurements at 129.5~135 GHz were conducted in a small factory scenario to construct training datasets and testing datasets. Experimental results demonstrate that the VAE-LMC model exhibits significant advantages in intra-cluster and inter-cluster characteristics, environmental consistency, and computational complexity, providing an efficient solution for terahertz channel multipath clustering in complex scenarios.
format Article
id doaj-art-1eeb4d73015e441baa70d3b513b9d34e
institution Kabale University
issn 1000-436X
language zho
publishDate 2025-06-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-1eeb4d73015e441baa70d3b513b9d34e2025-08-20T03:30:09ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2025-06-014689100114256604Variational autoencoder-based multipath clustering algorithm for terahertz channelsHAO XinyuLIAO XiZHENG XiangquanWANG YangLIN FengCHEN QianbinZHANG JieTo address the shortcomings of multipath clustering algorithms in terahertz channel modeling, particularly in terms of multidimensional parameter adaptability and unsupervised feature separation, a variational autoencoder-based latent space multipath clustering (VAE-LMC) model was proposed. Firstly, the variational autoencoder (VAE) was utilized to learn latent representations of multipath delays and arrival angles, enhancing feature separability. Secondly, K-Means clustering was embedded into the VAE framework, with joint optimization of reconstruction loss, KL divergence, and clustering loss functions to resolve the challenges of feature separation in unsupervised learning. Finally, multipath clustering was performed in the latent space, and the results were mapped back to the real data space. Terahertz channel measurements at 129.5~135 GHz were conducted in a small factory scenario to construct training datasets and testing datasets. Experimental results demonstrate that the VAE-LMC model exhibits significant advantages in intra-cluster and inter-cluster characteristics, environmental consistency, and computational complexity, providing an efficient solution for terahertz channel multipath clustering in complex scenarios.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025084/terahertz channelchannel measurementmultipath clusteringvariational autoencoderunsupervised learning
spellingShingle HAO Xinyu
LIAO Xi
ZHENG Xiangquan
WANG Yang
LIN Feng
CHEN Qianbin
ZHANG Jie
Variational autoencoder-based multipath clustering algorithm for terahertz channels
Tongxin xuebao
terahertz channel
channel measurement
multipath clustering
variational autoencoder
unsupervised learning
title Variational autoencoder-based multipath clustering algorithm for terahertz channels
title_full Variational autoencoder-based multipath clustering algorithm for terahertz channels
title_fullStr Variational autoencoder-based multipath clustering algorithm for terahertz channels
title_full_unstemmed Variational autoencoder-based multipath clustering algorithm for terahertz channels
title_short Variational autoencoder-based multipath clustering algorithm for terahertz channels
title_sort variational autoencoder based multipath clustering algorithm for terahertz channels
topic terahertz channel
channel measurement
multipath clustering
variational autoencoder
unsupervised learning
url http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025084/
work_keys_str_mv AT haoxinyu variationalautoencoderbasedmultipathclusteringalgorithmforterahertzchannels
AT liaoxi variationalautoencoderbasedmultipathclusteringalgorithmforterahertzchannels
AT zhengxiangquan variationalautoencoderbasedmultipathclusteringalgorithmforterahertzchannels
AT wangyang variationalautoencoderbasedmultipathclusteringalgorithmforterahertzchannels
AT linfeng variationalautoencoderbasedmultipathclusteringalgorithmforterahertzchannels
AT chenqianbin variationalautoencoderbasedmultipathclusteringalgorithmforterahertzchannels
AT zhangjie variationalautoencoderbasedmultipathclusteringalgorithmforterahertzchannels