2019
DOI: 10.1109/lawp.2019.2903787
|View full text |Cite
|
Sign up to set email alerts
|

Nonlinear Mutual Coupling Compensation Operator Design Using a Novel Electromagnetic Machine Learning Paradigm

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
41
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 62 publications
(41 citation statements)
references
References 16 publications
0
41
0
Order By: Relevance
“…Therefore, when two antennas (Tx and Rx) are placed next to each other, the individual Tx and Rx ACGFs used in formulae like those to be derived in this paper already account in full for the impact of mutual coupling between antennas, regardless to separation and distance between the coupled elements. This was demonstrated by good computational and experimental results in works like [14,15,20,21,25], mostly in the frequency domain; while some results in the time domain were given in [18,19], more data will be provided in §4a.The purpose of the present work is to explore several applications of the recently introduced ACGF approach [7-25] for communication systems research at a very general and fundamental level. The intention here is investigating new methods for performing wireless communication when the impact of the antenna on the digital link performance is explicitly taken into account.…”
mentioning
confidence: 95%
See 1 more Smart Citation
“…Therefore, when two antennas (Tx and Rx) are placed next to each other, the individual Tx and Rx ACGFs used in formulae like those to be derived in this paper already account in full for the impact of mutual coupling between antennas, regardless to separation and distance between the coupled elements. This was demonstrated by good computational and experimental results in works like [14,15,20,21,25], mostly in the frequency domain; while some results in the time domain were given in [18,19], more data will be provided in §4a.The purpose of the present work is to explore several applications of the recently introduced ACGF approach [7-25] for communication systems research at a very general and fundamental level. The intention here is investigating new methods for performing wireless communication when the impact of the antenna on the digital link performance is explicitly taken into account.…”
mentioning
confidence: 95%
“…whereḠ(r − r ; t − t ) is the free-space (forward) time-dependent dyadic Green's function, see detailed expressions in [28]. 15 In the presence of other scatterers and objects in the environment,…”
mentioning
confidence: 99%
“…Expediting design procedures that require repetitive references to the EM model has been the subject of extensive research over the recent years. Available solutions include incorporation of adjoint sensitivities into gradientbased routines [11], [12], algorithmic improvements of conventional methods (e.g., suppression of finite-differentiation sensitivity updates [13], [14]), exploring response features (e.g., [15], [16]), or utilization of surrogate models, both physics-based (space mapping [17], manifold mapping [18], adaptive response scaling [19]) and data-driven (response surfaces [20], kriging [21], neural networks [22]), as well as machine learning techniques [23], [24].…”
Section: Introductionmentioning
confidence: 99%
“…Others include response correction methods, e.g., manifold mapping [44] or adaptive response scaling [45]. Popular solutions for global search are data-driven surrogates [46] and machine learning techniques [47], often combined with sequential sampling procedures [48], where construction of the surrogate is interleaved with prediction stages leading to a generation of infill points and identifying the promising regions of the search space [49]. Robust design can be also aided by approximation surrogates, with a notable example of polynomial chaos expansion (PCE) models [50], which have the advantage of estimating the statistical moments of the system outputs without the necessity of running Monte Carlo analysis [51].…”
Section: Introductionmentioning
confidence: 99%