Polarimetric Wireless Indoor Channel Modeling Based on Propagation Graph

Adeogun, Ramoni; Pedersen, Troels; Gustafson, Carl; Tufvesson, Fredrik

doi:10.1109/tap.2019.2925128

Cited by 18 publications

(33 citation statements)

References 38 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus it is not necessary to provide side information to the algorithm (as is often done by separately estimating, e.g., noise variance) or to post-process the data by setting the noise threshold. This advantage is clearly seen when comparing with the method of moments (MoM) approach of calibrating polarimetric PG models [30] where noise is not estimated (see Fig. 11).…”

Section: Discussionmentioning

confidence: 99%

“…The proposed ABC and DL methods are applied for estimating parameters of a polarimetric propagation graph (PG) model [30], [38], [39]. First proposed in [40], the PG offers a simple and efficient approach for modeling propagation channels that account for both specular and dense multipath components.…”

Section: Calibration Of Polarimetric Propagation Graph Modelmentioning

confidence: 99%

“…A vast majority of works utilizing the PG model are either based on the stochastic generation procedure in [49] or in combination with a map of the environment. The polarimetric PG model in [30] was calibrated with measurements using method of moments. However, the method requires manually fixing one parameter due to identifiability issues.…”

Section: Calibration Of Polarimetric Propagation Graph Modelmentioning

confidence: 99%

“…In this paper, we present two machine learning methods based on ABC and DL to calibrate stochastic radio channel models without multipath extraction. We show the applicability of the methods by calibrating the polarimetric propagation graph (PG) model [30] as an example, since multipath extraction cannot be directly applied to calibrate it. We also present a number of summary statistics for representing channel measurements that are used as input for the learning methods.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning Parameters of Stochastic Radio Channel Models From Summaries

Bharti

Adeogun

Pedersen

2020

IEEE Open J. Antennas Propag.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Calibration Of Polarimetric Propagation Graph Modelmentioning

confidence: 99%

Section: Calibration Of Polarimetric Propagation Graph Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning Parameters of Stochastic Radio Channel Models From Summaries

Bharti

Adeogun

Pedersen

2020

IEEE Open J. Antennas Propag.

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, as future wireless communications will seek to improve coverage in the outdoor to indoor transition, there is a need to go beyond single environment modelling, thus consider coupling across multiply connected environments. Recently, a graph model of multi-room environment has been developed [ 21 ].…”

Section: Introductionmentioning

confidence: 99%

Wireless power distributions in multi-cavity systems at high frequencies

et al. 2021

View full text Add to dashboard Cite

The next generations of wireless networks will work in frequency bands ranging from sub-6 GHz up to 100 GHz. Radio signal propagation differs here in several critical aspects from the behaviour in the microwave frequencies currently used. With wavelengths in the millimetre range (mmWave), both penetration loss and free-space path loss increase, while specular reflection will dominate over diffraction as an important propagation channel. Thus, current channel model protocols used for the generation of mobile networks and based on statistical parameter distributions obtained from measurements become insufficient due to the lack of deterministic information about the surroundings of the base station and the receiver-devices. These challenges call for new modelling tools for channel modelling which work in the short-wavelength/high-frequency limit and incorporate site-specific details—both indoors and outdoors. Typical high-frequency tools used in this context—besides purely statistical approaches—are based on ray-tracing techniques. Ray-tracing can become challenging when multiple reflections dominate. In this context, mesh-based energy flow methods have become popular in recent years. In this study, we compare the two approaches both in terms of accuracy and efficiency and benchmark them against traditional power balance methods.

show abstract

A Novel Wireless Propagation Model Based on Bi-LSTM Algorithm

Wan

Tong

2022

IEEE Access

View full text Add to dashboard Cite

Establishing accurate wireless propagation models is essential for high-quality communications. Aiming to the low accuracy and complexity of the traditional wireless propagation model, a novel accurate wireless propagation model is proposed based on the bi-directional long short-term memory (Bi-LSTM) algorithm of machine learning. The model uses the machine learning technology driven by big data and can achieve a high real-time performance with a low complexity. Also, it can accurately predict the wireless signal coverage intensity in a new environment. In order to allow the model to accommodate the actual environment of target areas, the propagation model can be dynamically corrected by a deep learning and training. The Bi-LSTM is used to describe the relationship between features themselves and the relationship between features and target values of reference signal receiving power (RSRP). The Bi-LSTM is also used to represent the relationship through a full-connection layer to obtain the results so that sufficient parameter space can be provided for the model. The parameters of propagation model are searched and fitted through a full-connection optimization. After training and tuning, the predicted value of poor coverage recognition rate (PCRR) of the model can reach 0.2371 while the predicted value of root mean squared error (RMSE) can be 10.4855, which demonstrates the better accuracy of the proposed model. INDEX TERMS Bi-LSTM, deep learning, feature extraction, fully connected layer, wireless propagation.

show abstract

Polarimetric Wireless Indoor Channel Modeling Based on Propagation Graph

Cited by 18 publications

References 38 publications

Learning Parameters of Stochastic Radio Channel Models From Summaries

Learning Parameters of Stochastic Radio Channel Models From Summaries

Wireless power distributions in multi-cavity systems at high frequencies

A Novel Wireless Propagation Model Based on Bi-LSTM Algorithm

Contact Info

Product

Resources

About