Back to Search
Start Over
Recognition of error correcting codes based on CNN with block mechanism and embedding
- Source :
- Digital Signal Processing. 111:102986
- Publication Year :
- 2021
- Publisher :
- Elsevier BV, 2021.
-
Abstract
- An error correcting code type recognition technique based on a deep learning approach is proposed in this paper. This problem could be addressed in the context of non-cooperative communications or adaptive coding and modulation. Inspired by text classification, we proposed a convolutional neural network (CNN) model improved by embedding and block mechanism to classify the linear block code, convolutional code, and turbo code with the only knowledge of the noisy information streams. It achieves higher recognition performance than the algorithms which are based on traditional deep learning and rank calculation. Further results show that the performance is greatly affected by block length and the dimension of the embedding layer. In a nutshell, the CNN with block mechanism and embedding is a promising feature extraction and classification technique, and it is suitable for the recognition of different kinds of communication signals.
- Subjects :
- Block code
Computer science
business.industry
Applied Mathematics
Deep learning
Feature extraction
020206 networking & telecommunications
Pattern recognition
02 engineering and technology
Convolutional neural network
Computational Theory and Mathematics
Artificial Intelligence
Convolutional code
Signal Processing
0202 electrical engineering, electronic engineering, information engineering
Turbo code
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
Electrical and Electronic Engineering
Statistics, Probability and Uncertainty
Error detection and correction
business
Block (data storage)
Subjects
Details
- ISSN :
- 10512004
- Volume :
- 111
- Database :
- OpenAIRE
- Journal :
- Digital Signal Processing
- Accession number :
- edsair.doi...........4b45b4f9fa943ed52908c49b8ec46af4