2020
DOI: 10.1109/jiot.2020.2986442
|View full text |Cite
|
Sign up to set email alerts
|

A Novel OFDM Autoencoder Featuring CNN-Based Channel Estimation for Internet of Vessels

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
15
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 46 publications
(15 citation statements)
references
References 31 publications
0
15
0
Order By: Relevance
“…In the field of UWAC, the physical layer algorithm is the basis of building the network layer. Due to the particularity of underwater acoustic network [27][28][29][30], the physical layer technology is particularly important. is paper starts from the physical layer technology, which can effectively connect the physical layer technology with the network and is an important research direction in the future.…”
Section: Introductionmentioning
confidence: 99%
“…In the field of UWAC, the physical layer algorithm is the basis of building the network layer. Due to the particularity of underwater acoustic network [27][28][29][30], the physical layer technology is particularly important. is paper starts from the physical layer technology, which can effectively connect the physical layer technology with the network and is an important research direction in the future.…”
Section: Introductionmentioning
confidence: 99%
“…Since neural networks has shown powerful feature learning capacity, researchers had tried extensive explorations and designed two types of DL models, which are, as previously mentioned, data-driven [8] and model-driven [9] learning networks. A specially designed CE algorithm was proposed in [8], in which low resolution pilot information images were reconstructed into high resolution images rate image. And gradient disappearance problem in traditional CNN was resolved by adopting dense connection and feature reuse.…”
Section: Based Ce In Ofdm Systemmentioning
confidence: 99%
“…The estimation of the channel at pilot frequencies depends on LS and LMS while the channel insertion is finished utilizing straight interposition, second solicitation inclusion, low-pass presentation, spline cubic interjection, also, time-space addition. The time-space introduction is gotten by breathing easy area through inverse discrete Fourier transform (IDFT), zero cushioning and returning to recurrence space through discrete Fourier transform (DFT) [24], [25]. Also, Pilots are sent in all the sub-transporters of the principal image of each square and channel estimation is performed by utilizing LS estimation.…”
Section: Channel Estimationmentioning
confidence: 99%