The objective of channel charting is to learn a virtual map of the radio environment from high-dimensional channel state information (CSI) that is acquired by a multi-antenna wireless system. Since, in static environments, CSI is a function of the transmitter location, a mapping from CSI to channel chart coordinates can be learned in a self-supervised manner using dimensionality reduction techniques. The state-of-the-art triplet-based approach is evaluated on multiple datasets measured by a distributed massive multiple-input multiple-output (MIMO) channel sounder, with both co-located and distributed antenna setups. The importance of suitable triplet selection is investigated by comparing results to channel charts learned from a genie-aided triplet generator and learned from triplets on simulated trajectories through measured data. Finally, the transferability of learned forward charting functions to similar, but different radio environments is explored.
%0 Conference Paper
%1 EuchnerCC2022
%A Euchner, Florian
%A Stephan, Phillip
%A Gauger, Marc
%A Dörner, Sebastian
%A ten Brink, Stephan
%B 2022 IEEE 23rd International Workshop on Signal Processing Advances in Wireless Communication (SPAWC)
%D 2022
%K channel charting mimo myown triplet
%R 10.1109/SPAWC51304.2022.9833925
%T Improving Triplet-Based Channel Charting on Distributed Massive MIMO Measurements
%U https://ieeexplore.ieee.org/document/9833925
%X The objective of channel charting is to learn a virtual map of the radio environment from high-dimensional channel state information (CSI) that is acquired by a multi-antenna wireless system. Since, in static environments, CSI is a function of the transmitter location, a mapping from CSI to channel chart coordinates can be learned in a self-supervised manner using dimensionality reduction techniques. The state-of-the-art triplet-based approach is evaluated on multiple datasets measured by a distributed massive multiple-input multiple-output (MIMO) channel sounder, with both co-located and distributed antenna setups. The importance of suitable triplet selection is investigated by comparing results to channel charts learned from a genie-aided triplet generator and learned from triplets on simulated trajectories through measured data. Finally, the transferability of learned forward charting functions to similar, but different radio environments is explored.
@inproceedings{EuchnerCC2022,
abstract = {The objective of channel charting is to learn a virtual map of the radio environment from high-dimensional channel state information (CSI) that is acquired by a multi-antenna wireless system. Since, in static environments, CSI is a function of the transmitter location, a mapping from CSI to channel chart coordinates can be learned in a self-supervised manner using dimensionality reduction techniques. The state-of-the-art triplet-based approach is evaluated on multiple datasets measured by a distributed massive multiple-input multiple-output (MIMO) channel sounder, with both co-located and distributed antenna setups. The importance of suitable triplet selection is investigated by comparing results to channel charts learned from a genie-aided triplet generator and learned from triplets on simulated trajectories through measured data. Finally, the transferability of learned forward charting functions to similar, but different radio environments is explored.},
added-at = {2022-08-15T13:51:58.000+0200},
author = {Euchner, Florian and Stephan, Phillip and Gauger, Marc and Dörner, Sebastian and ten Brink, Stephan},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/29a6985c1d9aa4f77b2cd33b1b6615277/sdnr},
booktitle = {2022 IEEE 23rd International Workshop on Signal Processing Advances in Wireless Communication (SPAWC)},
doi = {10.1109/SPAWC51304.2022.9833925},
interhash = {6dfc7e52bf293f05fbd79233b7f048bd},
intrahash = {9a6985c1d9aa4f77b2cd33b1b6615277},
keywords = {channel charting mimo myown triplet},
timestamp = {2022-08-16T12:00:08.000+0200},
title = {Improving Triplet-Based Channel Charting on Distributed Massive MIMO Measurements},
url = {https://ieeexplore.ieee.org/document/9833925},
year = 2022
}
