Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference
The continuous development of communication technology and various deep learning models has led to the invention and application of many anti-interference technologies in the field of communication countermeasures. The existing communication interference models have defects such as low anti-interfer...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10227291/ |
| _version_ | 1797689593526484992 |
|---|---|
| author | Zhoutai Tian Daojie Yu Yijie Bai Shuntian Lei Yicheng Wang |
| author_facet | Zhoutai Tian Daojie Yu Yijie Bai Shuntian Lei Yicheng Wang |
| author_sort | Zhoutai Tian |
| collection | DOAJ |
| description | The continuous development of communication technology and various deep learning models has led to the invention and application of many anti-interference technologies in the field of communication countermeasures. The existing communication interference models have defects such as low anti-interference rate and low accuracy in communication spectrum prediction. To solve these problems, this study attempts to construct a Convolutional Neural Networks Long Short Term Memory (CNN-LSTM) and apply it to the communication jamming system for spectrum state prediction. Firstly, the framework of the communication interference system using the USRP RIO radio platform software was designed, and based on it, the communication interference channel was optimized using reinforcement learning Q-learning algorithm. Next, to further predict the signal spectrum state during the communication process, neural networks are utilized to construct a communication spectrum state prediction model. According to the optimization effect of communication interference channel and network spectrum prediction effect tested, the communication model under the Q-learning algorithm can achieve a 100% effective interference probability in fixed communication strategies. The Convolutional Neural Networks-1 Long-Short Term Memory-2 model has a prediction accuracy of 95.2% and can accurately predict changes in the communication spectrum. In summary, the Convolutional Neural Networks-1 Long-Short Term Memory-2 network constructed by this paper can provide new solutions and achieve good results for communication spectrum prediction. |
| first_indexed | 2024-03-12T01:47:49Z |
| format | Article |
| id | doaj.art-d77d93960700477aa09042e4678ce424 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T01:47:49Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d77d93960700477aa09042e4678ce4242023-09-08T23:01:34ZengIEEEIEEE Access2169-35362023-01-0111935389355010.1109/ACCESS.2023.330770810227291Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication InterferenceZhoutai Tian0Daojie Yu1https://orcid.org/0009-0005-5237-309XYijie Bai2Shuntian Lei3Yicheng Wang4School of Information and Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaSchool of Information and Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaSchool of Information and Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaSchool of Information and Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaSchool of Information and Systems Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou, ChinaThe continuous development of communication technology and various deep learning models has led to the invention and application of many anti-interference technologies in the field of communication countermeasures. The existing communication interference models have defects such as low anti-interference rate and low accuracy in communication spectrum prediction. To solve these problems, this study attempts to construct a Convolutional Neural Networks Long Short Term Memory (CNN-LSTM) and apply it to the communication jamming system for spectrum state prediction. Firstly, the framework of the communication interference system using the USRP RIO radio platform software was designed, and based on it, the communication interference channel was optimized using reinforcement learning Q-learning algorithm. Next, to further predict the signal spectrum state during the communication process, neural networks are utilized to construct a communication spectrum state prediction model. According to the optimization effect of communication interference channel and network spectrum prediction effect tested, the communication model under the Q-learning algorithm can achieve a 100% effective interference probability in fixed communication strategies. The Convolutional Neural Networks-1 Long-Short Term Memory-2 model has a prediction accuracy of 95.2% and can accurately predict changes in the communication spectrum. In summary, the Convolutional Neural Networks-1 Long-Short Term Memory-2 network constructed by this paper can provide new solutions and achieve good results for communication spectrum prediction.https://ieeexplore.ieee.org/document/10227291/Convolutional neural networkslong-term and short-term memory networkcommunication interferencespectrumstate prediction |
| spellingShingle | Zhoutai Tian Daojie Yu Yijie Bai Shuntian Lei Yicheng Wang Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference IEEE Access Convolutional neural networks long-term and short-term memory network communication interference spectrum state prediction |
| title | Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference |
| title_full | Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference |
| title_fullStr | Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference |
| title_full_unstemmed | Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference |
| title_short | Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference |
| title_sort | application of spectrum state prediction method based on cnn lstm network in communication interference |
| topic | Convolutional neural networks long-term and short-term memory network communication interference spectrum state prediction |
| url | https://ieeexplore.ieee.org/document/10227291/ |
| work_keys_str_mv | AT zhoutaitian applicationofspectrumstatepredictionmethodbasedoncnnlstmnetworkincommunicationinterference AT daojieyu applicationofspectrumstatepredictionmethodbasedoncnnlstmnetworkincommunicationinterference AT yijiebai applicationofspectrumstatepredictionmethodbasedoncnnlstmnetworkincommunicationinterference AT shuntianlei applicationofspectrumstatepredictionmethodbasedoncnnlstmnetworkincommunicationinterference AT yichengwang applicationofspectrumstatepredictionmethodbasedoncnnlstmnetworkincommunicationinterference |