Learning Parameters of Stochastic Radio Channel Models From Summaries

被引:18
作者
Bharti, Ayush [1 ]
Adeogun, Ramoni [1 ]
Pedersen, Troels [1 ]
机构
[1] Aalborg Univ, Dept Elect Syst, DK-9220 Aalborg, Denmark
来源
IEEE OPEN JOURNAL OF ANTENNAS AND PROPAGATION | 2020年 / 1卷 / 01期
关键词
Machine learning; Monte Carlo methods; deep learning; Bayesian inference; radio channel modeling; approximate Bayesian computation; summary statistics; propagation graph; parameter estimation; likelihood; APPROXIMATE BAYESIAN COMPUTATION; ENVIRONMENTS;
D O I
10.1109/OJAP.2020.2989814
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
Estimating parameters of stochastic radio channel models based on new measurement data is an arduous task usually involving multiple steps such as multipath extraction and clustering. We propose two different machine learning methods, one based on approximate Bayesian computation (ABC) and the other on deep learning, for fitting stochastic channel models to data directly. The proposed methods make use of easy-to-compute summary statistics of measured data instead of relying on extracted multipath components. Moreover, the need for post-processing of the extracted multipath components is omitted. Taking the polarimetric propagation graph model as an example stochastic model, we present relevant summaries and evaluate the performance of the proposed methods on simulated and measured data. We find that the methods are able to learn the parameters of the model accurately in simulations. Applying the methods on 60 GHz indoor measurement data yields parameter estimates that generate averaged power delay profile from the model that fits the data.
引用
收藏
页码:175 / 188
页数:14
相关论文
共 49 条
[1]  
Adeogun R. O, 2018, P IEEE WCNC, P1
[2]   Calibration of Stochastic Radio Propagation Models Using Machine Learning [J].
Adeogun, Ramoni .
IEEE ANTENNAS AND WIRELESS PROPAGATION LETTERS, 2019, 18 (12) :2538-2542
[3]   Polarimetric Wireless Indoor Channel Modeling Based on Propagation Graph [J].
Adeogun, Ramoni ;
Pedersen, Troels ;
Gustafson, Carl ;
Tufvesson, Fredrik .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 2019, 67 (10) :6585-6595
[4]   An Iterative Transfer Matrix Computation Method for Propagation Graphs in Multiroom Environments [J].
Adeogun, Ramoni ;
Bharti, Ayush ;
Pedersen, Troels .
IEEE ANTENNAS AND WIRELESS PROPAGATION LETTERS, 2019, 18 (04) :616-620
[5]  
Adeogun R, 2018, 2018 2ND URSI ATLANTIC RADIO SCIENCE MEETING (AT-RASC)
[6]  
Adeogun R, 2018, 2018 IEEE 29TH ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS (PIMRC), P566
[7]   Approximate Bayesian computation for forward modeling in cosmology [J].
Akeret, Joel ;
Refregier, Alexandre ;
Amara, Adam ;
Seehars, Sebastian ;
Hasner, Caspar .
JOURNAL OF COSMOLOGY AND ASTROPARTICLE PHYSICS, 2015, (08)
[8]  
[Anonymous], 2006, PROC 1 EUR C ANTENNA, DOI DOI 10.1111/J.1365-3040.2006.01554.X
[9]  
Beaumont MA, 2002, GENETICS, V162, P2025
[10]   Approximate Bayesian Computation [J].
Beaumont, Mark A. .
ANNUAL REVIEW OF STATISTICS AND ITS APPLICATION, VOL 6, 2019, 6 :379-403