2019
DOI: 10.1109/lcomm.2019.2941932
|View full text |Cite
|
Sign up to set email alerts
|

Machine Learning-Based Multi-Layer Multi-Hop Transmission Scheme for Dense Networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 13 publications
(6 citation statements)
references
References 17 publications
0
6
0
Order By: Relevance
“…Moreover, it is interesting to consider the case where more than two satellites in the LEO constellation are coordinating their transmissions. In addition to exploiting machinelearning (ML) techniques to improve the performance of coordinated LEO satellite transmissions [36] including traditional ML and reinforcement learning (RL) techniques which are widely used in many communication networks [37]- [42].…”
Section: Resultsmentioning
confidence: 99%
“…Moreover, it is interesting to consider the case where more than two satellites in the LEO constellation are coordinating their transmissions. In addition to exploiting machinelearning (ML) techniques to improve the performance of coordinated LEO satellite transmissions [36] including traditional ML and reinforcement learning (RL) techniques which are widely used in many communication networks [37]- [42].…”
Section: Resultsmentioning
confidence: 99%
“…[71] considered multi-hop covert communication over a moderate size network where the relays can transmit covertly by using either a single key for all relays or different independent keys at the relays. [72] proposed a machine-learning-based selection approach that adaptively chooses the best forwarding scheme in hybrid multihop dense networks. [73] developed a discrete-componentbased backscatter tag-to-tag transceiver and a communication protocol suite.…”
Section: A Physical Network (Pn) Tiermentioning
confidence: 99%
“…Based on the trellis, we next propose a dynamic programming based efficient path selection algorithm. The main focus on this paper is to find a low-complexity optimal relay selection solution and as commonly assumed in literature, we assume that full channel state information (CSI) is available at a central control node and it is in charge of RS decision [1], [2], [11]. At this control node, branch weights g[i, j, l] are computed based on global CSI and given as input to the proposed algorithm along with all possible relay combinations Z and the number of hops L.…”
Section: Trellis Based Optimal Relay Selectionmentioning
confidence: 99%
“…Taking a different approach, in [8], the authors express the outage probability in a recursive manner and propose a dynamic programming based algorithm for path selection. More recent work in this area focuses on machine learning techniques to select relay nodes in singleuser, multi-hop relay networks [9]- [11]. While these approaches provide interesting solutions in single-user networks, work on multi-user relay networks is still limited.…”
Section: Introductionmentioning
confidence: 99%