-
摘要: 为了提高基于卷积神经网络的调制样式识别算法性能，利用CNN的空间特征提取能力和LSTM时序特征提取能力，设计了CNN-LSTM并联网络，上支路由一层卷积层和一层池化层组成，下支路使用单层LSTM网络。直接将同向分量和正交分量作为输入数据，上下支路提取信号的空间和时间特征，提高特征表达能力。对BPSK、QPSK、8PSK、16QAM、32QAM、16APSK、32APSK 等7种信号的调制样式识别仿真实验结果表明：算法无需人为设计特征参数，减少人为因素影响，同时该算法在低信噪比下具有较好的识别性能。Abstract: To improve the performance of modulation type recognition algorithm based on convolutional neural network, CNN-LSTM parallel network is designed by CNN spatial feature extraction ability and LSTM time series feature extraction ability. The upper branch consists of a pooling layer and a convolution layer, and the lower branch uses a single-layer LSTM network. The in-phase component and quadrature component are directly used as input data, and the upper and lower branches extract the spatial and temporal characteristics of the signal respectively, to improve the feature expression ability. The experimental results of modulation type recognition for 7 kinds of signals, such as BPSK, QPSK, 8PSK, 16QAM, 32QAM, 16APSK and 32APSK, show that the algorithm does not need to artificially design the characteristic parameters and reduces the influence of human factors. At the same time, the algorithm has good recognition performance at lower SNR.
-
Keywords:
- Modulation type recognition /
- Convolutional neural network /
- Deep learning /
- Parallel
-
-
[1] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-50. [2] Wang D , Zhang M , Li Z , et al. Modulation format recognition and OSNR estimation using CNN based deep learning[J]. IEEE Photonics Technology Letters, 2017, 29(19):1667-1670. [3] Li J , Qi L , Lin Y . Research on modulation identification of digital signals based on deep learning[C]// IEEE International Conference on Electronic Information & Communication Technology. IEEE, 2016. [4] 彭超然,刁伟鹤,杜振宇. 基于深度卷积神经网络的数字调制方式识别[J].计算机测量与控制, 2018, 26(8): 222-226. [5] Peng Chaoran, Yan Weihe, Du Zhenyu. Digital Modulation Recognition Based on Deep Convolution Neural Network[J]. Computer Measurement & Control, 2018, 26(8): 222-226.(in chinese) [6] Zhi-jin Zhao and Jia-wei Gu. Recognition of digital modulation signals based on hybrid three-order restricted Boltzmann machine[C]// IEEE 16th International Conference on Communication Technology (ICCT), Hangzhou, 2015: 166-169. [7] 周龙梅. 基于深度学习的通信信号识别技术研究[D].北京邮电大学,2018. [8] Zhou Longmei. Research on Communication Signal Recognition Technology Based on Deep Learning [D]. Beijing University of Posts and Telecommunications, 2018.(in chinese) [9] 杨安锋,赵知劲,陈颖.利用稀疏自编码器的调制样式识别算法[J].信号处理,2018,34(07):833-842. [10] Yang Anfeng,Zhao Zhijin,Chen Ying.Modulation Pattern Recognition Algorithm Using Sparse Self-Encoder[J].Signal Processing,2018,34(07):833-842.(in chinese) [11] Gihan J，Mendis，Jin Wei,Arjuna Madanayake, Deep learning-based automated modulation classification for cognitive radio//[C]. 2016 IEEE International Conference on Comunication Systems(ICCS). 2016 [12] Byeoungdo Kim, Jaekyum Kim, Hyunmin Chae, et al. Deep neural network-based automatic modulation classification technique[C]//2016 International Conference on Information and Communication Technology Convergence (ICTC). 2016. [13] Karra K , Kuzdeba S , Petersen J . Modulation recognition using hierarchical deep neural networks[C]// IEEE International Symposium on Dynamic Spectrum Access Networks. IEEE, 2017. [14] Timothy J. O’Shea, Corgan J , Clancy T C . Convolutional radio modulation recognition networks[C]// International Conference on Engineering Applications of Neural Networks. Springer, Cham, 2016. [15] 周江. 基于神经网络的通信信号调制识别研究及实现[D].电子科技大学,2018.(in chinese) [16] Zhou Jiang. Research and implementation of communication signal modulation recognition based on neural network [D]. University of Electronic Science and Technology, 2018.(in chinese) [17] Felix A. Gers, Nicol N. Schraudolph, Jürgen Schmidhuber. Learning precise timing with LSTM recurrent network[J].Journal of Machine Learning Research,2002,3(8):115-120. [18] Y. Wu, X. Li and J. Fang. A Deep learning approach for modulation recognition via exploiting temporal correlations[C]//2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Kalamata, 2018:1-5 [19] 黄婷婷，余磊.SDAE-LSTM 模型在金融时间序列预测中的应用[J]. 计算机工程与应用, 2018,2-3 [20] Huang Tingting, Yu Lei.Application of SDAE-LSTM Model in Financial Time Series Prediction[J]. Computer Engineering and Applications, 2018,2-3(in chinese) -
期刊类型引用(16)
1. 石锐，李勇，朱延晗. 基于特征梯度均值化的调制信号对抗样本攻击算法. 计算机应用. 2024(08): 2521-2527 . 
百度学术
2. 任凯德，董雪，刘志勇，王晓，胡娅，郑盈盈. 基于深度学习的无线电信号调制方式识别算法研究. 电气技术与经济. 2024(08): 13-15+19 . 百度学术
3. 朱宽，余勤. 基于多尺度特征融合的调制识别算法. 计算机应用与软件. 2024(10): 133-139+183 . 百度学术
4. 邓远征，白立云. 基于时空联合与注意力机制的调制识别研究与实现. 无线电工程. 2024(12): 2913-2922 . 百度学术
5. 葛战，孙磊，李兵，蒋鸿宇，周劼. 数据驱动的双通道CNN-LSTM调制分类算法. 无线电工程. 2023(01): 73-79 . 百度学术
6. 任彦洁，唐晓刚，张斌权，冯俊豪. 基于时间卷积网络的通信信号调制识别算法. 无线电工程. 2023(04): 807-814 . 百度学术
7. 马运壮，贺英，郑鑫. 基于时隙IQ信号的瑞利衰落信道的调制信号识别. 青岛大学学报(工程技术版). 2023(02): 60-67 . 百度学术
8. 潘一震，韩顺利，季桓勇，张博. 基于通道融合的调制信号识别方法. 现代电子技术. 2023(12): 57-62 . 百度学术
9. 张承畅，余洒，徐余，罗元. 人工神经网络在调制识别中的应用综述. 重庆邮电大学学报(自然科学版). 2022(02): 181-192 . 百度学术
10. 张天骐，汪锐，安泽亮，王雪怡，方竹. 基于多端特征融合模型的MIMO-OFDM系统盲调制识别. 信号处理. 2022(09): 1940-1953 . 本站查看
11. 高泽鋆，曹菲，何川，冯晓伟，许剑锋，秦建强. 基于半监督学习网络的雷达有源干扰识别. 探测与控制学报. 2022(06): 93-101 . 百度学术
12. 张聿远，闫文君，林冲，姚成柱. 利用卷积-循环神经网络的串行序列空时分组码识别方法. 信号处理. 2021(01): 19-27 . 本站查看
13. 崔凯，崔天舒，朱岩，张晔，黄永辉，赵文杰. 基于多尺度时序特征的信号调制样式识别算法. 信号处理. 2021(08): 1507-1517 . 本站查看
14. 张军，符杰林，林基明. 基于CLDNN的调制信号识别方法. 计算机应用与软件. 2021(10): 216-220+277 . 百度学术
15. 向建，高勇. 基于GRU-CNN并联神经网络的自动调制识别. 电讯技术. 2021(11): 1339-1343 . 百度学术
16. 李江，冯存前，王义哲，许旭光. 基于AlexNet-BiLSTM网络的锥体目标微动分类. 信号处理. 2019(11): 1835-1843 . 本站查看
其他类型引用(15)
计量
- 文章访问数: 259
- HTML全文浏览量: 11
- PDF下载量: 884
- 被引次数: 31
下载:
