Auto-Generated Summaries for Stochastic Radio Channel Models

Ayush Bharti; Ramoni Ojekunle Adeogun; Troels Pedersen

doi:10.23919/EuCAP51087.2021.9411312

Auto-Generated Summaries for Stochastic Radio Channel Models

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

2 Citations (Scopus)

217 Downloads (Pure)

Abstract

Recently, a calibration method has been proposed for estimating the parameters of stochastic radio channel models using summaries of channel impulse response measurements without multipath extraction. In this paper, we attempt to automatically generate summaries using an autoencoder for calibration of channel models. This approach avoids the need for explicitly designing informative summaries about the model parameters, which can be tedious. We test the method by calibrating the stochastic polarized propagation graph model on simulated as well as measured data. The autoencoder is found to generate summaries that give reasonably accurate results while calibrating the considered model.

Original language	English
Title of host publication	2021 15th European Conference on Antennas and Propagation (EuCAP)
Number of pages	5
Publisher	IEEE (Institute of Electrical and Electronics Engineers)
Publication date	22 Mar 2021
Article number	9411312
ISBN (Print)	978-1-7281-8845-4
ISBN (Electronic)	978-88-31299-02-2
DOIs	https://doi.org/10.23919/EuCAP51087.2021.9411312
Publication status	Published - 22 Mar 2021
Event	15th European Conference on Antennas and Propagation - Dusseldorf, Dusseldorf, Germany Duration: 22 Mar 2021 → 26 Mar 2021 https://www.eucap2021.org/

Conference

Conference	15th European Conference on Antennas and Propagation
Location	Dusseldorf
Country/Territory	Germany
City	Dusseldorf
Period	22/03/2021 → 26/03/2021
Internet address	https://www.eucap2021.org/

Keywords

approximate Bayesian computation
autoencoder
machine learning
parameter estimation
propagation graph
radio channel modeling

Access to Document

10.23919/EuCAP51087.2021.9411312

Auto_generated_Summaries_for_Stochastic_Radio_Channel_ModelsAccepted author manuscript, 321 KB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{a407220d2ae745949bebea8322e816b1,

title = "Auto-Generated Summaries for Stochastic Radio Channel Models",

abstract = "Recently, a calibration method has been proposed for estimating the parameters of stochastic radio channel models using summaries of channel impulse response measurements without multipath extraction. In this paper, we attempt to automatically generate summaries using an autoencoder for calibration of channel models. This approach avoids the need for explicitly designing informative summaries about the model parameters, which can be tedious. We test the method by calibrating the stochastic polarized propagation graph model on simulated as well as measured data. The autoencoder is found to generate summaries that give reasonably accurate results while calibrating the considered model.",

keywords = "approximate Bayesian computation, autoencoder, machine learning, parameter estimation, propagation graph, radio channel modeling",

author = "Ayush Bharti and Adeogun, \{Ramoni Ojekunle\} and Troels Pedersen",

year = "2021",

month = mar,

day = "22",

doi = "10.23919/EuCAP51087.2021.9411312",

language = "English",

isbn = "978-1-7281-8845-4",

booktitle = "2021 15th European Conference on Antennas and Propagation (EuCAP)",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

address = "United States",

note = "15th European Conference on Antennas and Propagation, EuCAP 2021 ; Conference date: 22-03-2021 Through 26-03-2021",

url = "https://www.eucap2021.org/",

}

Bharti, A, Adeogun, RO & Pedersen, T 2021, Auto-Generated Summaries for Stochastic Radio Channel Models. in 2021 15th European Conference on Antennas and Propagation (EuCAP)., 9411312, IEEE (Institute of Electrical and Electronics Engineers), 15th European Conference on Antennas and Propagation, Dusseldorf, Germany, 22/03/2021. https://doi.org/10.23919/EuCAP51087.2021.9411312

Auto-Generated Summaries for Stochastic Radio Channel Models. / Bharti, Ayush; Adeogun, Ramoni Ojekunle ; Pedersen, Troels.
2021 15th European Conference on Antennas and Propagation (EuCAP). IEEE (Institute of Electrical and Electronics Engineers), 2021. 9411312.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Auto-Generated Summaries for Stochastic Radio Channel Models

AU - Bharti, Ayush

AU - Adeogun, Ramoni Ojekunle

AU - Pedersen, Troels

PY - 2021/3/22

Y1 - 2021/3/22

N2 - Recently, a calibration method has been proposed for estimating the parameters of stochastic radio channel models using summaries of channel impulse response measurements without multipath extraction. In this paper, we attempt to automatically generate summaries using an autoencoder for calibration of channel models. This approach avoids the need for explicitly designing informative summaries about the model parameters, which can be tedious. We test the method by calibrating the stochastic polarized propagation graph model on simulated as well as measured data. The autoencoder is found to generate summaries that give reasonably accurate results while calibrating the considered model.

AB - Recently, a calibration method has been proposed for estimating the parameters of stochastic radio channel models using summaries of channel impulse response measurements without multipath extraction. In this paper, we attempt to automatically generate summaries using an autoencoder for calibration of channel models. This approach avoids the need for explicitly designing informative summaries about the model parameters, which can be tedious. We test the method by calibrating the stochastic polarized propagation graph model on simulated as well as measured data. The autoencoder is found to generate summaries that give reasonably accurate results while calibrating the considered model.

KW - approximate Bayesian computation

KW - autoencoder

KW - machine learning

KW - parameter estimation

KW - propagation graph

KW - radio channel modeling

UR - https://www.scopus.com/pages/publications/85105450191

U2 - 10.23919/EuCAP51087.2021.9411312

DO - 10.23919/EuCAP51087.2021.9411312

M3 - Article in proceeding

SN - 978-1-7281-8845-4

BT - 2021 15th European Conference on Antennas and Propagation (EuCAP)

PB - IEEE (Institute of Electrical and Electronics Engineers)

T2 - 15th European Conference on Antennas and Propagation

Y2 - 22 March 2021 through 26 March 2021

ER -

Auto-Generated Summaries for Stochastic Radio Channel Models

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Calibrating Stochastic Radio Channel Models: An Approximate Bayesian Computation Approach

Cite this