A Cascade Network for Blind Recognition of LDPC Codes

Coding blind recognition plays a vital role in non-cooperative communication. Most of the algorithm for coding blind recognition of Low Density Parity Check (LDPC) codes is difficult to apply and the problem of high time complexity and high space complexity cannot be solved. Inspired by deep learnin...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Electronics (Basel) Ročník 12; číslo 9; s. 1979
Hlavní autoři: Zhang, Xiang, Zhang, Wei
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 24.04.2023
Témata:
Algorithms
Artificial neural networks
Codes
Coding
Coding theory
Communications systems
Complexity
Deep learning
Error correcting codes
Error correction & detection
Low density parity check codes
Machine learning
Natural language processing
Neural networks
Noise
Noise reduction
Parity
Recognition
Signal to noise ratio
Teaching methods
Transformers
China
ISSN:2079-9292, 2079-9292
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Coding blind recognition plays a vital role in non-cooperative communication. Most of the algorithm for coding blind recognition of Low Density Parity Check (LDPC) codes is difficult to apply and the problem of high time complexity and high space complexity cannot be solved. Inspired by deep learning, we propose an architecture for coding blind recognition of LDPC codes. This architecture concatenates a Transformer-based network with a convolution neural network (CNN). The CNN is used to suppress the noise in real time, followed by a Transformer-based neural network aimed to identify the rate and length of the LDPC codes. In order to train denoise networks and recognition networks with high performance, we build our own datasets and define loss functions for the denoise networks. Simulation results show that this architecture is able to achieve better performance than the traditional method at a lower signal-noise ratio (SNR). Compared with the existing methods, this approach is more flexible and can therefore be quickly deployed.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics12091979