2020
DOI: 10.1016/j.adhoc.2020.102151
|View full text |Cite
|
Sign up to set email alerts
|

Wireless signal enhancement based on generative adversarial networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
9
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(9 citation statements)
references
References 6 publications
0
9
0
Order By: Relevance
“…Next, traverse the whole noisy image to find similar blocks with similar neighborhood window structure. Then, the weighted re equalization of these similar blocks is calculated, and the calculated pixels are the pixels after noise reduction [23][24][25]. The formula of nonlocal mean noise reduction algorithm is shown in formula (7):…”
Section: Nonlocal Mean Denoising and Enhancement Methods Of Low-power...mentioning
confidence: 99%
“…Next, traverse the whole noisy image to find similar blocks with similar neighborhood window structure. Then, the weighted re equalization of these similar blocks is calculated, and the calculated pixels are the pixels after noise reduction [23][24][25]. The formula of nonlocal mean noise reduction algorithm is shown in formula (7):…”
Section: Nonlocal Mean Denoising and Enhancement Methods Of Low-power...mentioning
confidence: 99%
“…In the same year, Yin et al [ 19 ] propose a full convolutional denoising autoencoder to reduce the noise of underwater acoustic signals, and obtain better results in both the time domain and frequency domain, compared with traditional methods. Xue et al [ 20 ] design a wireless signal enhancement network based on the specialized Generative Adversarial Networks, which can adaptively learn the characteristics of signals and realize signal enhancement in time-varying systems. However, such methods ignore the correlation between the deep feature maps and the shallow feature maps, and they often have high training complexity because of deep layers.…”
Section: Introductionmentioning
confidence: 99%
“…Wang et al [16] developed a deep denoising network based on residual learning, that performed well for quadrative phase shift keying (QPSK) signals with SNRs ranging from −16 dB to −8 dB, but it exhibited poor robustness. Zhou et al [17] designed and built a signal enhancement network based on a generative adversarial network, which was also capable of correcting signal jitter and skewness. The validation was confined to QPSK and QAM64 signals, and additional testing is required for other signal types.…”
Section: Introductionmentioning
confidence: 99%