Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes

Evangelos N. Papasotiriou; Alexandros Apostolos A. Boulogeorgos; Mar Francis De Guzman; Katsuyuki Haneda; Angeliki Alexiou

doi:10.1109/PIMRC54779.2022.9977784

Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes

Evangelos N. Papasotiriou^*, Alexandros Apostolos A. Boulogeorgos, Mar Francis De Guzman, Katsuyuki Haneda, Angeliki Alexiou

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

6 Downloads (Pure)

Abstract

This contribution aims at experimentally validating the suitability of Gaussian mixture (GM) distributions to capture the stochastic characteristics of outdoor terahertz (THz) wireless channels. In this direction, we employ a machine learning enabled approach, based on the expectation maximization algorithm, in order to identify the suitable number of Gaussian distributions as well as their corresponding parameters that result to an acceptable fit. The fitting accuracy of the GMs to the empirical distributions is evaluated by means of the Kolmogorov-Smirnov (KS), Kullback-Leibler (KL), root-mean-square-error (RMSE) and R2 fitting accuracy tests. These tests verify the suitability of GMs to model the small-scale fading channel amplitude of outdoor THz wireless links. In addition, the fitting accuracy results indicate that as the number of mixtures increases the resulting GMs achieve a better fit to the empirical data.

Original language	English
Title of host publication	2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2022
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	978-1-6654-8053-6
DOIs	https://doi.org/10.1109/PIMRC54779.2022.9977784
Publication status	Published - 2022
MoE publication type	A4 Article in a conference publication
Event	IEEE International Symposium on Personal, Indoor and Mobile Radio Communications - Virtual, Online, Japan Duration: 12 Sep 2022 → 15 Sep 2022

Publication series

Name	IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications
ISSN (Print)	2166-9570
ISSN (Electronic)	2166-9589

Conference

Conference	IEEE International Symposium on Personal, Indoor and Mobile Radio Communications
Abbreviated title	PIMRC
Country/Territory	Japan
City	Virtual, Online
Period	12/09/2022 → 15/09/2022

Access to Document

10.1109/PIMRC54779.2022.9977784

Stochastic_Characterization_of_outdoor_Terahertz_Channels_Through_Mixture_Gaussian_ProcessesFinal published version, 1.99 MB

OpenUrl availability

Full text

Cite this

Papasotiriou, E. N., Boulogeorgos, A. A. A., De Guzman, M. F., Haneda, K., & Alexiou, A. (2022). Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes. In 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2022 (IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications). IEEE. https://doi.org/10.1109/PIMRC54779.2022.9977784

Papasotiriou, Evangelos N. ; Boulogeorgos, Alexandros Apostolos A. ; De Guzman, Mar Francis et al. / Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes. 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2022. IEEE, 2022. (IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications).

@inproceedings{67b48f08d5334c099efcc80c211d598c,

title = "Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes",

abstract = "This contribution aims at experimentally validating the suitability of Gaussian mixture (GM) distributions to capture the stochastic characteristics of outdoor terahertz (THz) wireless channels. In this direction, we employ a machine learning enabled approach, based on the expectation maximization algorithm, in order to identify the suitable number of Gaussian distributions as well as their corresponding parameters that result to an acceptable fit. The fitting accuracy of the GMs to the empirical distributions is evaluated by means of the Kolmogorov-Smirnov (KS), Kullback-Leibler (KL), root-mean-square-error (RMSE) and R2 fitting accuracy tests. These tests verify the suitability of GMs to model the small-scale fading channel amplitude of outdoor THz wireless links. In addition, the fitting accuracy results indicate that as the number of mixtures increases the resulting GMs achieve a better fit to the empirical data.",

author = "Papasotiriou, {Evangelos N.} and Boulogeorgos, {Alexandros Apostolos A.} and {De Guzman}, {Mar Francis} and Katsuyuki Haneda and Angeliki Alexiou",

note = "Funding Information: This work has received funding from the European Commission Horizon 2020 research and innovation programme ARIADNE under grant agreement No. 871464. The multipath measured data used in this work were provided by Aalto University Finland. Publisher Copyright: {\textcopyright} 2022 IEEE.; IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC ; Conference date: 12-09-2022 Through 15-09-2022",

year = "2022",

doi = "10.1109/PIMRC54779.2022.9977784",

language = "English",

series = "IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications",

publisher = "IEEE",

booktitle = "2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2022",

address = "United States",

}

Papasotiriou, EN, Boulogeorgos, AAA, De Guzman, MF , Haneda, K & Alexiou, A 2022, Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes. in 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2022. IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications, IEEE, IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, Virtual, Online, Japan, 12/09/2022. https://doi.org/10.1109/PIMRC54779.2022.9977784

Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes. / Papasotiriou, Evangelos N.; Boulogeorgos, Alexandros Apostolos A.; De Guzman, Mar Francis et al.

2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2022. IEEE, 2022. (IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes

AU - Papasotiriou, Evangelos N.

AU - Boulogeorgos, Alexandros Apostolos A.

AU - De Guzman, Mar Francis

AU - Haneda, Katsuyuki

AU - Alexiou, Angeliki

N1 - Funding Information: This work has received funding from the European Commission Horizon 2020 research and innovation programme ARIADNE under grant agreement No. 871464. The multipath measured data used in this work were provided by Aalto University Finland. Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - This contribution aims at experimentally validating the suitability of Gaussian mixture (GM) distributions to capture the stochastic characteristics of outdoor terahertz (THz) wireless channels. In this direction, we employ a machine learning enabled approach, based on the expectation maximization algorithm, in order to identify the suitable number of Gaussian distributions as well as their corresponding parameters that result to an acceptable fit. The fitting accuracy of the GMs to the empirical distributions is evaluated by means of the Kolmogorov-Smirnov (KS), Kullback-Leibler (KL), root-mean-square-error (RMSE) and R2 fitting accuracy tests. These tests verify the suitability of GMs to model the small-scale fading channel amplitude of outdoor THz wireless links. In addition, the fitting accuracy results indicate that as the number of mixtures increases the resulting GMs achieve a better fit to the empirical data.

AB - This contribution aims at experimentally validating the suitability of Gaussian mixture (GM) distributions to capture the stochastic characteristics of outdoor terahertz (THz) wireless channels. In this direction, we employ a machine learning enabled approach, based on the expectation maximization algorithm, in order to identify the suitable number of Gaussian distributions as well as their corresponding parameters that result to an acceptable fit. The fitting accuracy of the GMs to the empirical distributions is evaluated by means of the Kolmogorov-Smirnov (KS), Kullback-Leibler (KL), root-mean-square-error (RMSE) and R2 fitting accuracy tests. These tests verify the suitability of GMs to model the small-scale fading channel amplitude of outdoor THz wireless links. In addition, the fitting accuracy results indicate that as the number of mixtures increases the resulting GMs achieve a better fit to the empirical data.

UR - http://www.scopus.com/inward/record.url?scp=85145666264&partnerID=8YFLogxK

U2 - 10.1109/PIMRC54779.2022.9977784

DO - 10.1109/PIMRC54779.2022.9977784

M3 - Conference contribution

AN - SCOPUS:85145666264

T3 - IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications

BT - 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2022

PB - IEEE

T2 - IEEE International Symposium on Personal, Indoor and Mobile Radio Communications

Y2 - 12 September 2022 through 15 September 2022

ER -

Papasotiriou EN, Boulogeorgos AAA, De Guzman MF , Haneda K, Alexiou A. Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes. In 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2022. IEEE. 2022. (IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications). doi: 10.1109/PIMRC54779.2022.9977784

Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes

Abstract

Publication series

Conference

Access to Document

OpenUrl availability

Other files and links

Fingerprint

ARIADNE: Artificial Intelligence Aided D-band Network for 5G Long Term Evolution

Cite this

Stochastic Characterization of outdoor Terahertz Channels Through Mixture Gaussian Processes

Abstract

Publication series

Conference

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Projects

ARIADNE: Artificial Intelligence Aided D-band Network for 5G Long Term Evolution

Cite this