Variational autoencoder-based multipath clustering algorithm for terahertz channels

HAO Xinyu; LIAO Xi; ZHENG Xiangquan; WANG Yang; LIN Feng; CHEN Qianbin; ZHANG Jie

doi:10.11959/j.issn.1000-436x.2025084

您当前的位置：

首页 >

文章列表页 >

Variational autoencoder-based multipath clustering algorithm for terahertz channels

Papers | 更新时间：2025-07-04

- Variational autoencoder-based multipath clustering algorithm for terahertz channels
- Journal on Communications Vol. 46, Issue 6, Pages: 89-100(2025)
- 作者机构：
  
  1.重庆邮电大学通信与信息工程学院，重庆 400065
  2.中国人民解放军32002部队，北京 100036
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(62271095;62171071);The Natural Science Foundation of Chongqing(cstc2021jcyj-msxmX0634;CSTB2022NSCQ-MSX1125);The Science and Technology Research Program of Chongqing Municipal Education Commission(KJZD-K202300607);The Natural Science Foundation Innovation and Development Joint Fund Project of Chongqing(CSTB2022NSCQ-LZX0037)
- DOI：10.11959/j.issn.1000-436x.2025084
  CLC： TN92
- Received：06 March 2025，
  
  Revised：2025-04-27，
  
  Published：25 June 2025
- 稿件说明：
移动端阅览
郝昕宇,廖希,郑相全等.基于变分自编码器的太赫兹信道多径分簇算法[J].通信学报,2025,46(06):89-100.

HAO Xinyu,LIAO Xi,ZHENG Xiangquan,et al.Variational autoencoder-based multipath clustering algorithm for terahertz channels[J].Journal on Communications,2025,46(06):89-100.
郝昕宇,廖希,郑相全等.基于变分自编码器的太赫兹信道多径分簇算法[J].通信学报,2025,46(06):89-100. DOI： 10.11959/j.issn.1000-436x.2025084.

HAO Xinyu,LIAO Xi,ZHENG Xiangquan,et al.Variational autoencoder-based multipath clustering algorithm for terahertz channels[J].Journal on Communications,2025,46(06):89-100. DOI： 10.11959/j.issn.1000-436x.2025084.

摘要

针对太赫兹信道中多径分簇算法在多维参数适应性和无监督特征分离中的不足，提出了一种基于变分自编码器的潜层空间多径分簇（VAE-LMC）模型。首先，通过变分自编码器（VAE）学习多径时延与到达角度的潜在表示，增强特征可分离性。其次，将K-Means分簇嵌入VAE框架，联合优化重构损失、KL散度和分簇损失函数，解决无监督学习中的特征分离难题。最后，在潜层空间完成多径分簇并将结果映射至真实数据空间。在小型工厂场景中开展129.5~135 GHz的太赫兹信道测量，构建训练数据集和测试数据集。实验结果表明，VAE-LMC模型在簇内和簇间特性、环境一致性及复杂度等方面均有显著优势，为复杂场景下的太赫兹信道多径分簇提供了高效解决方案。

Abstract

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.

关键词

Keywords

references

BIAN J , WANG C X , GAO X Q , et al . A general 3D non-stationary wireless channel model for 5G and beyond [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 5 ): 3211 - 3224 .

HE R S , AI B , STÜBER G L , et al . Geometrical-based modeling for millimeter-wave MIMO mobile-to-mobile channels [J ] . IEEE Transactions on Vehicular Technology , 2018 , 67 ( 4 ): 2848 - 2863 .

ZHANG J H , TANG P , YU L , et al . Channel measurements and models for 6G: current status and future outlook [J ] . Frontiers of Information Technology & Electronic Engineering , 2020 , 21 ( 1 ): 39 - 61 .

WANG C , ZHANG J H , TUFVESSON F . Random cluster number feature and cluster characteristics of indoor measurement at 28 GHz [J ] . IEEE Antennas and Wireless Propagation Letters , 2018 , 17 ( 10 ): 1881 - 1884 .

HE R S , AI B , MOLISCH A F , et al . Clustering enabled wireless channel modeling using big data algorithms [J ] . IEEE Communications Magazine , 2018 , 56 ( 5 ): 177 - 183 .

CHEN Y , LI Y B , HAN C , et al . Channel measurement and ray-tracing-statistical hybrid modeling for low-terahertz indoor communications [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 12 ): 8163 - 8176 .

HU M T , YE Y X , HE R S , et al . A novel power weighted multipath component clustering algorithm based on spectral clustering [C ] // Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring) . Piscataway : IEEE Press , 2020 : 1 - 5 .

CZINK N , CERA P , SALO J , et al . A framework for automatic clustering of parametric MIMO channel data including path powers [C ] // Proceedings of the IEEE Vehicular Technology Conference . Piscataway : IEEE Press , 2006 : 1 - 5 .

LEE J . Cluster-based millimeter-wave outdoor-to-indoor propagation characteristics based on 32 GHz measurement analysis [J ] . IEEE Antennas and Wireless Propagation Letters , 2021 , 20 ( 1 ): 73 - 77 .

SUZUKI N , TSUKADA H , TAKAHASHI R , et al . Characterization of spatial consistency of cluster channels in urban environments at 24 and 60 GHz [J ] . IEEE Antennas and Wireless Propagation Letters , 2024 , 23 ( 5 ): 1583 - 1587 .

CALIST I , KIM M . Multipath cluster-based scatterer recognition by object detection techniques using panoramic images [C ] // Proceedings of the 2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC) . Piscataway : IEEE Press , 2023 : 1 - 6 .

HE R S , LI Q Y , AI B , et al . A kernel-power-density-based algorithm for channel multipath components clustering [J ] . IEEE Transactions on Wireless Communications , 2017 , 16 ( 11 ): 7138 - 7151 .

XIE J Y , GIRSHICK R , FARHADI A . Unsupervised deep embedding for clustering analysis [C ] // Proceedings of the 33rd International Conference on Machine Learning . New York : PMLR , 2016 : 478 - 487 .

CARON M , BOJANOWSKI P , JOULIN A , et al . Deep clustering for unsupervised learning of visual features [C ] // Proceedings of the European Conference on Computer Vision (ECCV) . Piscataway : IEEE Press , 2018 : 132 - 149 .

PENG X , FENG J S , ZHOU J T , et al . Deep subspace clustering [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2020 , 31 ( 12 ): 5509 - 5521 .

ZHANG T , JI P , HARANDI M , et al . Neural collaborative subspace clustering [C ] // Proceedings of the 36th International Conference on Machine Learning . New York : PMLR , 2019 : 7384 - 7393 .

ZHANG J J , LI C G , YOU C , et al . Self-supervised convolutional subspace clustering network [C ] // Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2019 : 5468 - 5477 .

OPOCHINSKY Y , CHAZAN S E , GANNOT S , et al . K-autoencoders deep clustering [C ] // Proceedings of the ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE Press , 2020 : 4037 - 4041 .

PARK S , HAN S , KIM S , et al . Improving unsupervised image clustering with robust learning [C ] // Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2021 : 12273 - 12282 .

YANG J W , PARIKH D , BATRA D . Joint unsupervised learning of deep representations and image clusters [C ] // Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2016 : 5147 - 5156 .

YU L J , ZHAO X W , DU F , et al . Multipath component clustering based on improved self-organizing feature map for 5G millimeter wave radio channels [C ] // Proceedings of the 2021 13th International Symposium on Antennas, Propagation and EM Theory (ISAPE) . Piscataway : IEEE Press , 2021 : 1 - 3 .

WHITON R , CHEN J S , TUFVESSON F . Flexible density-based multipath component clustering utilizing ground truth pose [C ] // Proceedings of the 2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall) . Piscataway : IEEE Press , 2023 : 1 - 6 .

STEINBAUER M , OZCELIK H , HOFSTETTER H , et al . How to quantify multipath separation [J ] . IEICE Transactions on Electronics , 2002 , 85 ( 3 ): 552 - 557 .

CZINK N , CERA P , SALO J , et al . Improving clustering performance using multipath component distance [J ] . Electronics Letters , 2006 , 42 ( 1 ): 33 - 35 .

LIU Y M , ZHANG J H , ZHANG Y X , et al . A shared cluster-based stochastic channel model for integrated sensing and communication systems [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 5 ): 6032 - 6044 .

LI Y P , ZHANG J H , MA Z Y , et al . Clustering analysis in the wireless propagation channel with a variational Gaussian mixture model [J ] . IEEE Transactions on Big Data , 2020 , 6 ( 2 ): 223 - 232 .

LUO J , LIAO X , WANG Y , et al . An entropy-based adaptive DBSCAN clustering algorithm and its application in THz wireless channels [J ] . IEEE Transactions on Antennas and Propagation , 2023 , 71 ( 12 ): 9830 - 9837 .

SUN G Q , HUANG C , CHENG Z H , et al . A study of clustering algorithms for time-varying multipath components in wireless channels [C ] // Proceedings of the MILCOM 2021-2021 IEEE Military Communications Conference (MILCOM) . Piscataway : IEEE Press , 2021 : 414 - 419 .

WANG H , PAN S G , GAO W , et al . Multipath/NLOS detection based on K-means clustering for GNSS/INS tightly coupled system in urban areas [J ] . Micromachines , 2022 , 13 ( 7 ): 1128 .

LI Y B , WANG Y Q , CHEN Y , et al . Channel measurement and analysis in an indoor corridor scenario at 300 GHz [C ] // Proceedings of the ICC 2022-IEEE International Conference on Communications . Piscataway : IEEE Press , 2022 : 2888 - 2893 .

DONG W H , ZHANG J H , GAO X Y , et al . Cluster identification and properties of outdoor wideband MIMO channel [C ] // Proceedings of the 2007 IEEE 66th Vehicular Technology Conference . Piscataway : IEEE Press , 2007 : 829 - 833 .

Views

1383

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Review of unsupervised anomaly detection techniques for medical imaging

Research on sub-terahertz path loss measurement and modeling for 6G integrated sensing and communication

Sub-THz channel measurement and hybrid channel modeling for indoor scenarios

Heterogeneous federated bidirectional knowledge distillation transfer semi-supervised modulation recognition

Anomaly detection model for multivariate time series based on stochastic Transformer

Related Author

Hei Xinhong

You Zhenzhen

Shi Zhenghao

Song Xiaogang

Zhao Yingcheng

CHEN Qianbin

WANG Yang

ZHAO Haisen

Related Institution

Human Machine Integration Intelligent Robot Shaanxi Provincial University Engineering Research Center

Shaanxi Key Laboratory for Network Computing and Security Technology

School of Computer Science and Engineering, Xi’an University of Technology

Institute of Systems Engineering, Academy of Military Science of PLA

School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications

AI脑图

AI问答

⁰