Triplet-Based Wireless Channel Charting: Architecture and Experiments

被引:18
|
作者
Ferrand, Paul [1 ]
Decurninge, Alexis [1 ]
Ordonez, Luis G. [1 ]
Guillaud, Maxime [1 ]
机构
[1] Huawei Technol France, Paris Res Ctr, Math & Algorithm Sci Lab, F-92100 Boulogne Billancourt, France
关键词
Dimensionality reduction; Measurement; Antenna arrays; Feature extraction; Neural networks; Euclidean distance; Data models; channel state information; machine learning; self-supervised learning; MASSIVE MIMO; 5G;
D O I
10.1109/JSAC.2021.3087251
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Channel charting is a data-driven baseband processing technique consisting in applying self-supervised machine learning techniques to channel state information (CSI), with the objective of reducing the dimension of the data and extracting the fundamental parameters governing its distribution. We introduce a novel channel charting approach based on triplets of samples. The proposed algorithm learns a meaningful similarity metric between CSI samples on the basis of proximity in their respective acquisition times, and simultaneously performs dimensionality reduction. We present an extensive experimental validation of the proposed approach on data obtained from a commercial Massive MIMO system; in particular, we evaluate to which extent the obtained channel chart is similar to the user location information, although it is not supervised by any geographical data. Finally, we propose and evaluate variations in the channel charting process, including the partially supervised case where some labels are available for part of the dataset.
引用
收藏
页码:2361 / 2373
页数:13
相关论文
共 50 条
  • [1] Triplet-Based Wireless Channel Charting
    Ferrand, Paul
    Decurninge, Alexis
    Ordonez, Luis G.
    Guillaud, Maxime
    [J]. 2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2020,
  • [2] Improving Triplet-Based Channel Charting on Distributed Massive MIMO Measurements
    Euchner, Florian
    Stephan, Phillip
    Gauger, Marc
    Doerner, Sebastian
    ten Brink, Stephan
    [J]. 2022 IEEE 23RD INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATION (SPAWC), 2022,
  • [3] TRIPLET-BASED ARCHITECTURE AND ITS PROCESS MIGRATION MECHANISM
    Liu, Bin
    Tong, Zhi-Chen
    Gao, Yu-Jin
    [J]. PROCEEDINGS OF 2009 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-6, 2009, : 2754 - +
  • [4] A triplet-based computer architecture supporting parallel object computing
    Shi, Feng
    Ji, Weixing
    Qiao, Baojun
    Liu, Bin
    [J]. 2007 IEEE INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES, AND PROCESSORS, 2007, : 192 - 197
  • [5] Dynamic load balancing in embedded systems based on Triplet-based Hierarchical Interconnection Architecture
    Liu, Bin
    Gao, YuJin
    [J]. PROCEEDINGS OF THE 2006 IEEE/ASME INTERNATIONAL CONFERENCE ON MECHATRONIC AND EMBEDDED SYSTEMS AND APPLICATIONS, 2006, : 372 - +
  • [6] SuperTriplets: a triplet-based supertree approach to phylogenomics
    Ranwez, Vincent
    Criscuolo, Alexis
    Douzery, Emmanuel J. P.
    [J]. BIOINFORMATICS, 2010, 26 (12) : i115 - i123
  • [7] Design and Evaluation of Efficient Router Architecture for Triplet-Based Network-on-Chip Topology
    Zhang, Yang
    [J]. JOURNAL OF TESTING AND EVALUATION, 2014, 42 (06) : 1323 - 1334
  • [8] An efficient triplet-based algorithm for evidential reasoning
    Bi, Yaxin
    [J]. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2008, 23 (04) : 483 - 516
  • [9] Audio Feature Learning with Triplet-Based Embedding Network
    Qi, Xiaoyu
    Yang, Deshun
    Chen, Xiaoou
    [J]. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 4979 - 4980
  • [10] Multipoint Channel Charting for Wireless Networks
    Deng, Junquan
    Medjkouh, Said
    Malm, Nicolas
    Tirkkonen, Olav
    Studer, Christoph
    [J]. 2018 CONFERENCE RECORD OF 52ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2018, : 286 - 290