The Recognition Method of MQAM Signals Based on BP Neural Network and Bird Swarm Algorithm
With the commercialization of 5G, in order to recognize QAM signals, one of the main modulation modes in 5G communication systems, this paper put forward the BP-BSA network model based on bird swarm algorithm (BSA) and BP neural network. Firstly, the instantaneous features and high-order cumulants w...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9360768/ |
| _version_ | 1818639993125470208 |
|---|---|
| author | Chengchang Zhang Sa Yu Guojun Li Yu Xu |
| author_facet | Chengchang Zhang Sa Yu Guojun Li Yu Xu |
| author_sort | Chengchang Zhang |
| collection | DOAJ |
| description | With the commercialization of 5G, in order to recognize QAM signals, one of the main modulation modes in 5G communication systems, this paper put forward the BP-BSA network model based on bird swarm algorithm (BSA) and BP neural network. Firstly, the instantaneous features and high-order cumulants were selected as the appropriate feature statistics by analyzing the characteristics of MQAM signals. After that, the structure of the BP neural network model was determined, and the initial parameters of the BP neural network were optimized using BSA to accelerate the convergence speed of the network. Finally, the features processed with signal to noise ratio (SNR) disorder were used to train and test the BP neural network model. The BP-BSA network model proposed in this paper applies the bird swarm algorithm to the field of modulation recognition for the first time. And the simulation results show that the recognition accuracies of 16, 32, 64, 128, 256QAM signals in the SNR range of -5 dB to 20 dB all reach above 98%. Compared with the same type algorithms, the algorithm proposed in this paper has good recognition performance. |
| first_indexed | 2024-12-16T23:04:12Z |
| format | Article |
| id | doaj.art-6d75d98b17b1460c8de2860daa49f502 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T23:04:12Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6d75d98b17b1460c8de2860daa49f5022022-12-21T22:12:36ZengIEEEIEEE Access2169-35362021-01-019360783608610.1109/ACCESS.2021.30615859360768The Recognition Method of MQAM Signals Based on BP Neural Network and Bird Swarm AlgorithmChengchang Zhang0Sa Yu1https://orcid.org/0000-0002-7038-309XGuojun Li2Yu Xu3Institute of Optoelectric Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaInstitute of Optoelectric Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaInstitute of Optoelectric Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaInstitute of Optoelectric Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaWith the commercialization of 5G, in order to recognize QAM signals, one of the main modulation modes in 5G communication systems, this paper put forward the BP-BSA network model based on bird swarm algorithm (BSA) and BP neural network. Firstly, the instantaneous features and high-order cumulants were selected as the appropriate feature statistics by analyzing the characteristics of MQAM signals. After that, the structure of the BP neural network model was determined, and the initial parameters of the BP neural network were optimized using BSA to accelerate the convergence speed of the network. Finally, the features processed with signal to noise ratio (SNR) disorder were used to train and test the BP neural network model. The BP-BSA network model proposed in this paper applies the bird swarm algorithm to the field of modulation recognition for the first time. And the simulation results show that the recognition accuracies of 16, 32, 64, 128, 256QAM signals in the SNR range of -5 dB to 20 dB all reach above 98%. Compared with the same type algorithms, the algorithm proposed in this paper has good recognition performance.https://ieeexplore.ieee.org/document/9360768/MQAM signals recognitionBP neural networkbird swarm algorithmfeature extraction |
| spellingShingle | Chengchang Zhang Sa Yu Guojun Li Yu Xu The Recognition Method of MQAM Signals Based on BP Neural Network and Bird Swarm Algorithm IEEE Access MQAM signals recognition BP neural network bird swarm algorithm feature extraction |
| title | The Recognition Method of MQAM Signals Based on BP Neural Network and Bird Swarm Algorithm |
| title_full | The Recognition Method of MQAM Signals Based on BP Neural Network and Bird Swarm Algorithm |
| title_fullStr | The Recognition Method of MQAM Signals Based on BP Neural Network and Bird Swarm Algorithm |
| title_full_unstemmed | The Recognition Method of MQAM Signals Based on BP Neural Network and Bird Swarm Algorithm |
| title_short | The Recognition Method of MQAM Signals Based on BP Neural Network and Bird Swarm Algorithm |
| title_sort | recognition method of mqam signals based on bp neural network and bird swarm algorithm |
| topic | MQAM signals recognition BP neural network bird swarm algorithm feature extraction |
| url | https://ieeexplore.ieee.org/document/9360768/ |
| work_keys_str_mv | AT chengchangzhang therecognitionmethodofmqamsignalsbasedonbpneuralnetworkandbirdswarmalgorithm AT sayu therecognitionmethodofmqamsignalsbasedonbpneuralnetworkandbirdswarmalgorithm AT guojunli therecognitionmethodofmqamsignalsbasedonbpneuralnetworkandbirdswarmalgorithm AT yuxu therecognitionmethodofmqamsignalsbasedonbpneuralnetworkandbirdswarmalgorithm AT chengchangzhang recognitionmethodofmqamsignalsbasedonbpneuralnetworkandbirdswarmalgorithm AT sayu recognitionmethodofmqamsignalsbasedonbpneuralnetworkandbirdswarmalgorithm AT guojunli recognitionmethodofmqamsignalsbasedonbpneuralnetworkandbirdswarmalgorithm AT yuxu recognitionmethodofmqamsignalsbasedonbpneuralnetworkandbirdswarmalgorithm |