A 2layer-BiLSTM-Attention-Based Method for Modulation Recognition of Communication Signals
Pages 146 - 152
Abstract
Aiming at the problems that feature extraction accuracy of feature-based modulation recognition methods is difficult to guarantee, the recognition accuracy of one-dimensional-feature-based deep learning methods is low, and the time and storage overhead of high-dimensional-feature-based deep learning methods is large, a recognition method based on the two-layer BiLSTM followed by the attention layer is proposed. The experiment results show that, based on the RadioML2016.10a dataset, the method achieves high recognition accuracy without increasing the training burden and extracting features from original signals. The recognition reaches 86.7% at 0 dB and 91.5% at 18 dB, outperforming other deep learning methods.
References
[1]
O'Shea T J, Corgan J, Clancy T C. 2016. Convolutional radio modulation recognition networks. International conference on engineering applications of neural networks. Springer, Cham, 2016: 213-226. https://doi.org/10.1007/978-3-319-44188-7_16
[2]
Liu X, Yang D, El Gamal A. 2017. Deep neural network architectures for modulation classification. 51st Asilomar Conference on Signals, Systems, and Computers. IEEE, Pacific Grove, CA, USA, 915-919. https://doi.org/10.1109/ACSSC.2017.8335483
[3]
Peng S, Jiang H, Wang H, 2018. Modulation classification based on signal constellation diagrams and deep learning. IEEE transactions on neural networks and learning systems, 30(3): 718-727. https://10.1109/TNNLS.2018.2850703
[4]
Zhang Z, Wang C, Gan C, 2019. Automatic modulation classification using convolutional neural network with features fusion of SPWVD and BJD. IEEE Transactions on Signal and Information Processing over Networks, 5(3): 469-478. https://10.1109/TSIPN.2019.2900201
[5]
Li Nan. 2019. Application of Bi-spectral Feature and Deep Learning in Signal Modulation Recognition. Journal of Projectiles, Rockets, Missiles and Guidance. 39(5): 81-84. http://10.15892/j.cnki.djzdxb.2019.05.019
[6]
Song Zihao, Cheng Wei, Peng Cenxin, et.al. 2021. Modulation recognition method based on CWD and residual shrinkage network. Systems Engineering and Electronics, 43(11): 3371-3379. https://10.7540/j.ynu.20200075
[7]
Vaswani A, Shazeer N, Parmar N, 2017. Attention is all you need. In Proceedings of 31st Conference on Neural Information Processing Systems (NIPS 2017), NIPS, Long Beach, CA, USA, 30. https://dl.acm.org/doi/10.5555/3295222.3295349
[8]
Ren Sirui, Huang Ming. 2021. A modulation classification algorithm based on modified LSTM network. Journal of Yunnan University: Natural Sciences Edition, 43(1):39∼45. https://10.7540/j.ynu.20200075
[9]
Zhang B, Liu K, Zhao M.W. 2020. Deep learning modulation recognition algorithm based on time-frequency analysis. Industrial Control Computer, 33(05): 66-68+71. http://www.cnki.com.cn/Article/CJFDTotal-GYKJ202005028.html
Index Terms
- A 2layer-BiLSTM-Attention-Based Method for Modulation Recognition of Communication Signals
Recommendations
Research on the Modulation Recognition Method OFDM Signal Based on Short-time Fourier Transform and Convolutional Neural Network
ICBTA '21: Proceedings of the 2021 4th International Conference on Blockchain Technology and ApplicationsIn order to improve the modulation recognition accuracy of the Orthogonal Frequency Division Multiplexing (OFDM) signal under low signal-to-noise ratio, an OFDM signal modulation recognition method based on short-time Fourier transform and convolutional ...
Research on Modulation Recognition Method of MSK Signals Based on Wavelet Transform
ISCID '14: Proceedings of the 2014 Seventh International Symposium on Computational Intelligence and Design - Volume 02According to the characteristics of MSK signals, detecting statistics about mean ratio and variance ratio of the modulus which is calculated by normalized and non-normalized amplitude through Haar wavelet transform is established. Between-classes and ...
Deep convolutional BiLSTM fusion network for facial expression recognition
AbstractDeep learning algorithms have shown significant performance improvements for facial expression recognition (FER). Most deep learning-based methods, however, focus more attention on spatial appearance features for classification, discarding much ...
Comments
Information & Contributors
Information
Published In
December 2022
385 pages
ISBN:9781450397438
DOI:10.1145/3582197
Copyright © 2022 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 30 March 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICIT 2022
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 22Total Downloads
- Downloads (Last 12 months)5
- Downloads (Last 6 weeks)1
Reflects downloads up to 17 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format