基于TCNN-BiLSTM网络的调制识别算法

doi:10.3969/j.issn.1001-506X.2020.08.26

摘要/Abstract

摘要：

针对传统调制识别算法在低信噪比下识别率不高的情况,提出双路卷积神经网络级联双向长短时记忆(two-way convolutional neural network cascaded bidirectional long short-term memory, TCNN-BiLSTM)网络的调制识别算法。首先,该算法并联不同尺度卷积核的卷积层,提取调制信号不同维度的特征。然后,级联BiLSTM层,对多维特征构建LSTM时间模型。最后,使用softmax分类器完成识别。仿真实验表明,所提算法结构在加性高斯白噪声和特定信道参数的瑞利衰落信道下，性能要优于基于传统特征和其他网络结构的识别算法。在特定信道参数的瑞利衰落信道下信噪比低至6 dB时,该算法对6种数字调制信号的识别率仍可达到92%以上。

关键词: 调制识别, 并联网络, 卷积神经网络, 双向长短时记忆网络

Abstract:

For the traditional modulation recognition algorithm, the recognition rate is not high at low signal to noise ratio (SNR). The paper proposes a two-way convolutional neural network casaded bidirectional long short-term memory (TCNN-BiLSTM) network modulation recognition algorithm. Firstly, the algorithm parallelizes the convolutional layers with convolution kernels of different scales to extract features of different dimensions of the modulation signal. Then it cascades the BiLSTM layers to build LSTM time model for multi-dimensional features. Finally, a softmax classifier is used to complete the recognition. Simulation experiments show that the performance of the algorithm structure under additive Gaussian white noise and Rayleigh fading channels with specific channel parameters is better than the recognition algorithms based on traditional features and other network structures. When the SNR in the Rayleigh fading channel with specific channel parameters is as low as 6 dB, the recognition rate of the six digital modulation signals can still reach above 92%.

Key words: modulation recognition, parallel network, convolutional neural network, bidirectional long short-term memory network

中图分类号:

TN911.3

刘凯, 张斌, 黄青华. 基于TCNN-BiLSTM网络的调制识别算法[J]. 系统工程与电子技术, 2020, 42(8): 1841-1849.

Kai LIU, Bin ZHANG, Qinghua HUANG. Modulation recognition algorithm based on TCNN-BiLSTM[J]. Systems Engineering and Electronics, 2020, 42(8): 1841-1849.

图/表 17

图1

图2

图3

图4

表1

图5

图6

图7

图8

图9

图10

表2

图11

图12

图13

图14

表3

参考文献 33

1	BASAR E , WEN M , MESLEH R , et al. Index modulation techniques for next-generation wireless networks[J]. IEEE Access, 2017, 5, 16693- 16746. doi: 10.1109/ACCESS.2017.2737528
2	谭晓衡, 褚国星, 张雪静, 等. 基于高阶累积量和小波变换的调制识别算法[J]. 系统工程与电子技术, 2018, 40 (1): 171- 177.
	TAN X H , CHU G X , ZHANG X J , et al. Modulation recognition algorithm based on high-order cumulants and wavelet transform[J]. Systems Engineering and Electronics, 2018, 40 (1): 171- 177.
3	DOBRE O A , ABDI A , BARNESS Y , et al. Survey of automatic modulation classification techniques: classical approaches and new trends[J]. Institution of Engineering and Technology, 2007, 1 (2): 137- 156.
4	O'SHEA T J , ROY T , CLANCY T C . Over-the-air deep lear-ning based radio signal classification[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12 (1): 168- 179. doi: 10.1109/JSTSP.2018.2797022
5	TANG B , TU Y , ZHANG Z , et al. Digital signal modulation classification with data augmentation using generative adversarial nets in cognitive radio networks[J]. IEEE Access, 2018, 6, 15713- 15722. doi: 10.1109/ACCESS.2018.2815741
6	XU J L , SU W , ZHOU M . Likelihood-ratio approaches to automatic modulation classification[J]. IEEE Trans.on Systems, 2011, 41 (4): 455- 469.
7	XU J L , SU W , ZHOU M . Software-defined radio equipped with rapid modulation recognition[J]. IEEE Trans.on Vehicular Technology, 2010, 59 (4): 1659- 1667. doi: 10.1109/TVT.2010.2041805
8	NANDI A K , AZZOUZ E E . Algorithms for automatic modulation recognition of communication signals[J]. IEEE Trans.on Communications, 1998, 46 (4): 431- 436. doi: 10.1109/26.664294
9	陈泽艺. 基于循环谱和高阶累积量的联合模式识别方法[J]. 电讯技术, 2015, 1 (3): 100- 104.
	CHEN Z Y . A combined modulation recognition based on cyclic spectrum and high-order cumulants[J]. Telecommunication Engineering, 2015, 1 (3): 100- 104.
10	SOLIMAN S S , HSUE S . Signal classification using statistical moments[J]. IEEE Trans.on Communications, 1992, 40 (5): 908- 916. doi: 10.1109/26.141456
11	WU H , SAQUIB M , YUN Z . Novel automatic modulation classification using cumulant features for communications via multipath channels[J]. IEEE Trans.on Wireless Communications, 2008, 7 (8): 3098- 3105. doi: 10.1109/TWC.2008.070015
12	刘亚冲, 唐智灵. 基于softmax回归的通信信号循环谱的多分类识别方法[J]. 现代电子技术, 2018, 41 (3): 1- 5.
	LIU Y C , TANG Z L . Softmax regression based on multi-classification recognition method of communication signal cyclic spectrum[J]. Modern Electronics Technique, 2018, 41 (3): 1- 5.
13	O'SHEA T J , HOYDIS J . An introduction to deep learning for the physical layer[J]. IEEE Trans.on Cognitive Communications and Networking, 2017, 3 (4): 563- 575. doi: 10.1109/TCCN.2017.2758370
14	MAO Q , HU F , HAO Q . Deep learning for intelligent wireless networks: a comprehensive survey[J]. IEEE Communications Surveys & Tutorials, 2018, 20 (4): 2595- 2621.
15	LEE J H , KIM J , KIM B , et al. Robust automatic modulation classification technique for fading channels via deep neural network[J]. Entropy, 2017, 19 (9): 454. doi: 10.3390/e19090454
16	ZHANG M , DIAO M , GUO L M . Convolutional neural networks for automatic cognitive radio waveform recognition[J]. IEEE Access, 2017, 5, 11074- 11082. doi: 10.1109/ACCESS.2017.2716191
17	ZENG Y , ZHANG M , HAN F , et al. Spectrum analysis and convolutional neural network for automatic modulation recognition[J]. IEEE Wireless Communications Letters, 2019, 8 (3): 929- 932.
18	WANG D S , ZHANG M , LI J , et al. Intelligent constellation diagram analyzer using convolutional neural network-based deep learning[J]. Optics Express, 2017, 25 (15): 17150. doi: 10.1364/OE.25.017150
19	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. doi: 10.1109/LPT.2017.2742553
20	O'SHEA T J , CORGAN J , CLANCY T C . Convolutional radio modulation recognition networks[J]. Engineering Applications of Neural Networks, 2016, 629, 213- 226.
21	YANG C , HE Z , PENG Y , et al. Deep learning aided method for automatic modulation recognition[J]. IEEE Access, 2019, 7, 109063- 109068. doi: 10.1109/ACCESS.2019.2933448
22	ZHANG D , DING W , ZHANG B , et al. Automatic modulation classification based on deep learning for unmanned aerial vehicles[J]. Sensors, 2018, 18 (3): 924. doi: 10.3390/s18030924
23	WEST N E, O'SHEA T J. Deep architectures for modulation recognition[C]//Proc.of the IEEE International Symposium on Dynamic Spectrum Access Networks, 2017.
24	MENG F , CHEN P , WU L , et al. Automatic modulation classification: a deep learning enabled approach[J]. IEEE Trans.on Vehicular Technology, 2018, 67 (11): 10760- 10772. doi: 10.1109/TVT.2018.2868698
25	XU J L , SU W , ZHOU M . Likelihood-ratio approaches to automatic modulation classification[J]. IEEE Trans.on Systems, 2011, 41 (4): 455- 469.
26	HORNIK K . Approximation capabilities of multilayer feedforward networks[J]. Neural Networks, 1991, 4 (2): 251- 257.
27	TARA N S, ORIOL V, SENIOR A, et al. Convolutional, long short-term memory, fully connected deep neural networks[C]// Proc.of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2015.
28	GOODFELLOW I , BENGI O Y , COURVILLE A . Deep lear-ning[M]. Boston: Massachusetts Institute of Technology, 2016.
29	LIAO K S , TAO G H , ZHONG Y , et al. Sequential convolutional recurrent neural networks for fast automatic modulation classification[J]. Signal Processing, 2019. doi: 10.3847/1538-4357/ab1b2a
30	HOCHREITER S , SCHMIDHUBER , JURGEN . Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780. doi: 10.1162/neco.1997.9.8.1735
31	PASCANU R, GULCEHRE C, CHO K, et al. How to construct deep recurrent neural networks[C]//Proc.of the International Conference on Learning Representations, 2014.
32	YANG Y , SOLIMAN S . A suboptimal algorithm for modulation classification[J]. IEEE Trans.on Aerospace and Electronic Systems, 1997, 33 (1): 38- 45. doi: 10.1109/7.570706
33	YANG Y , LIU C H . An asymptotic optimal algorithm for modulation classification[J]. IEEE Communications Letters, 1998, 2 (5): 117- 119. doi: 10.1109/4234.673652

调制信号处理平台	Matlab 2016b
深度学习仿真平台	Tensorflow 1.4.0
硬件加速平台	NVIDIA GTX1080Ti
调制方式	2PSK, 4PSK, 2FSK, 4FSK, 8QAM, 16QAM
符号速率/Mbps	1
每个符号采样点数	4
载波频率/MHz	8
SNR/dB	-6:2:20

BiLSTM层数	无	一层	两层	3层	4层
预测时间/s	0.58	2.09	4.15	4.95	6.15

层类型	激活函数	输出维度
输入层	/	(1, 2, 128)
批标准化层	/	(1, 2, 128)
卷积层L11	Relu	(128, 2, 125)
卷积层L21	Relu	(128, 2, 130)
卷积层L1	Relu	(16, 1, 126)
卷积层L2	Relu	(16, 1, 131)
融合层	/	(16, 1, 257)
3层BiLSTM层	/	(None, 64)
输出层	softmax	(None, 6)

[1]	宋爽, 张悦, 张琳娜, 岑翼刚, 李浥东. 基于深度学习的轻量化目标检测算法[J]. 系统工程与电子技术, 2022, 44(9): 2716-2725.
[2]	王彩云, 吴钇达, 王佳宁, 马璐, 赵焕玥. 基于改进的CNN和数据增强的SAR目标识别[J]. 系统工程与电子技术, 2022, 44(8): 2483-2487.
[3]	康颖, 赵治华, 吴灏, 李亚星, 孟进. 基于Deep SVDD的通信信号异常检测方法[J]. 系统工程与电子技术, 2022, 44(7): 2319-2328.
[4]	秦博伟, 蒋磊, 许华, 齐子森. 基于残差生成对抗网络的调制识别算法[J]. 系统工程与电子技术, 2022, 44(6): 2019-2026.
[5]	韦娟, 杨皇卫, 宁方立. 基于NMF与CNN联合优化的声学场景分类[J]. 系统工程与电子技术, 2022, 44(5): 1433-1438.
[6]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[7]	方伟, 王玉, 闫文君, 林冲. 基于神经网络的符号化飞行动作识别[J]. 系统工程与电子技术, 2022, 44(3): 737-745.
[8]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[9]	刘恒燕, 张立民, 闫文君, 钟兆根, 凌青, 梁晓军. 基于WBP-CNN算法的LDPC译码[J]. 系统工程与电子技术, 2022, 44(3): 1030-1035.
[10]	邵凯, 朱苗苗, 王光宇. 基于生成对抗与卷积神经网络的调制识别方法[J]. 系统工程与电子技术, 2022, 44(3): 1036-1043.
[11]	张玺, 金正猛, 姜亚琴. 融合深度图像先验的全变差图像着色算法[J]. 系统工程与电子技术, 2022, 44(2): 385-393.
[12]	金涛, 王晓峰, 田润澜, 张歆东. 基于改进1DCNN+TCN的雷达辐射源快速识别方法[J]. 系统工程与电子技术, 2022, 44(2): 463-469.
[13]	吕勤哲, 全英汇, 沙明辉, 董淑仙, 邢孟道. 基于集成深度学习的有源干扰智能分类[J]. 系统工程与电子技术, 2022, 44(12): 3595-3602.
[14]	高涌荇, 王旭东, 汪玲, 朱岱寅, 郭军, 孟凡旺. 基于RCNN的双极化气象雷达天气信号检测[J]. 系统工程与电子技术, 2022, 44(11): 3380-3387.
[15]	李永刚, 朱卫纲, 黄琼男, 李云涛, 何永华. 复杂背景下SAR图像近岸舰船目标检测[J]. 系统工程与电子技术, 2022, 44(10): 3096-3103.