Calibration of Stochastic Radio Propagation Models Using Machine Learning

Research output: Contribution to journalLetterResearchpeer-review

22 Downloads (Pure)

Abstract

This letter proposes a machine learning based method for the calibration of stochastic radio propagation models. Model calibration is cast as a regression problem involving mapping of the channel transfer function or impulse response to the model parameters. A multilayer perceptron is trained with summary statistics computed from synthetically generated channel realizations using the model. To calibrate the model, the trained network is used to estimate the model parameters from channel statistics obtained from measurements. The performance of the proposed method is evaluated with propagation graph and Saleh-Valenzuela models using both simulated data and in-room channel measurements. Results show accurate estimation of the parameters of both models.
Original languageEnglish
JournalI E E E Antennas and Wireless Propagation Letters
ISSN1536-1225
DOIs
Publication statusE-pub ahead of print - 2019

Fingerprint

Radio transmission
Learning systems
Calibration
Statistics
Multilayer neural networks
Impulse response
Transfer functions

Cite this

@article{c3b702efd1bd41ff801575e240fc7d6b,
title = "Calibration of Stochastic Radio Propagation Models Using Machine Learning",
abstract = "This letter proposes a machine learning based method for the calibration of stochastic radio propagation models. Model calibration is cast as a regression problem involving mapping of the channel transfer function or impulse response to the model parameters. A multilayer perceptron is trained with summary statistics computed from synthetically generated channel realizations using the model. To calibrate the model, the trained network is used to estimate the model parameters from channel statistics obtained from measurements. The performance of the proposed method is evaluated with propagation graph and Saleh-Valenzuela models using both simulated data and in-room channel measurements. Results show accurate estimation of the parameters of both models.",
author = "Adeogun, {Ramoni Ojekunle}",
year = "2019",
doi = "10.1109/LAWP.2019.2942819",
language = "English",
journal = "I E E E Antennas and Wireless Propagation Letters",
issn = "1536-1225",
publisher = "IEEE",

}

TY - JOUR

T1 - Calibration of Stochastic Radio Propagation Models Using Machine Learning

AU - Adeogun, Ramoni Ojekunle

PY - 2019

Y1 - 2019

N2 - This letter proposes a machine learning based method for the calibration of stochastic radio propagation models. Model calibration is cast as a regression problem involving mapping of the channel transfer function or impulse response to the model parameters. A multilayer perceptron is trained with summary statistics computed from synthetically generated channel realizations using the model. To calibrate the model, the trained network is used to estimate the model parameters from channel statistics obtained from measurements. The performance of the proposed method is evaluated with propagation graph and Saleh-Valenzuela models using both simulated data and in-room channel measurements. Results show accurate estimation of the parameters of both models.

AB - This letter proposes a machine learning based method for the calibration of stochastic radio propagation models. Model calibration is cast as a regression problem involving mapping of the channel transfer function or impulse response to the model parameters. A multilayer perceptron is trained with summary statistics computed from synthetically generated channel realizations using the model. To calibrate the model, the trained network is used to estimate the model parameters from channel statistics obtained from measurements. The performance of the proposed method is evaluated with propagation graph and Saleh-Valenzuela models using both simulated data and in-room channel measurements. Results show accurate estimation of the parameters of both models.

U2 - 10.1109/LAWP.2019.2942819

DO - 10.1109/LAWP.2019.2942819

M3 - Letter

JO - I E E E Antennas and Wireless Propagation Letters

JF - I E E E Antennas and Wireless Propagation Letters

SN - 1536-1225

ER -