基于自适应小波分解和轻量化网络架构的特定辐射源识别算法

doi:10.12305/j.issn.1001-506X.2025.09.02

摘要/Abstract

摘要：

针对特定辐射源识别（specific emitter identification，SEI）算法在复杂多变的电磁环境中识别率低的问题，提出一种基于自适应小波分解和轻量化网络架构的SEI算法。首先，设计自适应小波分解的预处理方法，确定每个信号样本的最优小波系数。然后，设计特征拼接算法综合所有信号样本的最优系数，构建辐射源个体的特征表示。最后，设计一种轻量高效的网络模型，引入倒置残差模块和多头注意力机制，提取更具可分性的细微特征。在3种不同数据集上识别率分别为99.6%、99.31%和98.8%，该结果表明所提算法相较于其他识别算法有着更高的识别率。在高斯白噪声和典型多径衰落信道环境中，所提算法仍可以进行有效识别，展现出优异的鲁棒性。

关键词: 特定辐射源识别, 小波变换, 神经网络

Abstract:

To address the issue of low recognition rates of specific emitter identification （SEI） algorithms in complex and dynamic electromagnetic environments, a SEI algorithm based on adaptive wavelet decomposition and lightweight network architecture is proposed. Initially, a preprocessing method of adaptive wavelet decomposition is designed to determine the optimal wavelet coefficients for each signal sample. Subsequently, a feature concatenation algorithm is devised to integrate the optimal coefficients of all signal samples, forming the feature representation of the emitter individual. Finally, a lightweight and efficient network model is destgned, integrating inverted residual modules and a multi-head attention mechanism to extract more discriminative fine-grained features. The recognition rates on three different datasets are 99.6%, 99.31%, and 98.8%, respectively, indicating that the proposed algorithm has a higher recognition rate compared to other recognition algorithms.The proposed algorithm exhibits remarkable robustness, maintaining effective identification performance in the presence of Gaussian white noise and typical multipath fading channel environments.

Key words: specific emitter identification （SEI）, wavelet transform, neural network

中图分类号:

TN 911.7

石文强, 雷迎科, 金虎, 滕飞. 基于自适应小波分解和轻量化网络架构的特定辐射源识别算法[J]. 系统工程与电子技术, 2025, 47(9): 2785-2796.

Wenqiang SHI, Yingke LEI, Hu JIN, Fei TENG. Algorithm for specific emitter identification based on adaptive wavelet decomposition and lightweight network architecture[J]. Systems Engineering and Electronics, 2025, 47(9): 2785-2796.

图/表 14

图1

图2

图3

图4

图5

图6

表1

图7

图8

图9

图10

表2

表3

图11

参考文献 31

1	MATTHEW D Z, ROB F. Visualizing and understanding convolutional networks[C]// Proc. of the 14th European Conference on Computer Vision, 2014: 818−833.
2	WONG L J, HEADLRY W C, MICHAELS A J. Specific emitter identification using convolutional neural network-based IQ imbalance estimators[J]. IEEE Access, 2019, 7, 33544- 33555.
3	WU Q Y, FERES C, KUZMENKO D, et al. Deep learning based RF fingerprinting for device identification and wireless security[J]. Electronics Letters, 2018, 54 (24): 1405- 1407.
4	KONG M X, ZHANG J, LIU W F, et al. Radar emitter identification based on deep convolutional neural network[C]// Proc. of the International Conference on Control, 2018: 309−314.
5	何遵文, 侯帅, 张万成, 等. 通信特定辐射源识别的多特征融合方法[J]. 通信学报, 2021, 42 (2): 104- 112.
	HE Z W, HOU S, ZHANG W C, et al. Multi-feature fusion classification method for communication specific emitter identification[J]. Journal on Communications, 2021, 42 (2): 104- 112.
6	韩洁, 张涛, 王欢欢, 等. 基于3D-Hibert能量谱和多尺度分形特征的通信辐射源个体识别[J]. 通信学报, 2017, 38 (4): 99- 109. doi: 10.11959/j.issn.1000-436x.2017080
	HAN J, ZHANG T, WANG H H, et al. Communication emitter individual identification based on 3D-Hibert energy spectrum and multi-scale fractal features[J]. Journal on Communications, 2017, 38 (4): 99- 109. doi: 10.11959/j.issn.1000-436x.2017080
7	YUAN Y J, HUANG Z T, WU H, et al. Specific emitter identification based on Hilbert-Huang transform based time-frequency-energy distribution features[J]. IET Communications, 2014, 8 (13): 2404- 2412.
8	ZHANG J W, WANG F G, DOBRE O A, et al. Specific emitter identification via Hilbert–Huang transform in single-hop and relaying scenarios[J]. IEEE Trans. on Information Forensics and Security, 2016, 11 (6): 1192- 1205.
9	SATIJA U, TRIVEDI G, BISWAL G, et al. Specific emitter identification based on variational mode decomposition and spectral features in single hop and relaying scenarios[J]. IEEE Trans. on Information Forensics and Security, 2019, 14 (3): 581- 591.
10	GLOROT X, BENGIO Y. Understanding the difficulty of training deep feedforward neural networks[J]. Journal of Machine Learning Research, 2010, 9, 249- 256.
11	XIN Q, HU S H, LIU S Q, et al. An attention-based wavelet convolution neural network for epilepsy EEG classification[J]. IEEE Trans. on Neural Systems and Rehabilitation Engineering, 2022, 30, 957- 966.
12	BENGIO Y, SIMARD P, FRASCONI P. Learning long-term dependencies with gradient descent is difficult[J]. IEEE Trans. on Neural Networks, 1994, 5 (2): 157- 166.
13	ZHOU Y P, WANG C Y, ZHOU R, et al. A specific emitter identification method based on RF-DNA and XGBoost[C]// Proc. of the 7th International Conference on Intelligent Computing and Signal Processing, 2022: 1530−1533.
14	MUHAMMAD U Z, MUHAMMAD D N, MAQSOOD H S, et al. Specific emitter identification based on multi-scale multi-dimensional approximate entropy[J]. IEEE Signal Processing Letters, 2024, 31, 850- 854.
15	SERGEY I, CHRISTIAN S. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// Proc. of the International Conference on Machine Learning, 2015: 448−456.
16	HE K M, ZHANG X Y, REN S Q, et al. Identity mappings in deep residual networks[C]// Proc. of the 14th European Conference on Computer Vision, 2016: 630−645.
17	TANG J X, DENG C W, HUANG G B, et al. Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine[J]. IEEE Trans. on Geoscience and Remote Sensing, 2015, 53 (3): 1174- 1185.
18	YAN G L, CAI Z X, LIU Y C, et al. Intelligent specific emitter identification using complex-valued convolutional neural network[C]// Proc. of the 23rd IEEE International Conference on Communication Technology, 2023: 1259−1263.
19	PAN J F, GUO L Q, CHEN Q J, et al. Specific radar emitter identification using 1D-CBAM-ResNet[C]// Proc. of the 14th IEEE International Conference on Wireless Communications and Signal Processing, 2022: 483−488.
20	ZHANG Y B, ZHANG Q Y, ZHAO H T, et al. Multisource heterogeneous specific emitter identification using attention mechanism-based RFF fusion method[J]. IEEE Trans. on Information Forensics and Security, 2024, 19, 2639- 2650.
21	PENG Y, ZHAO X L, GUO L T, et al. Enhanced specific emitter identification with limited data through dual implicit regularization[J]. IEEE Internet of Things Journal, 2024, 15 (11): 26395- 26405.
22	XU Z W, HAN G J, LIU L, et al. A lightweight specific emitter identification model for IIoT devices based on adaptive broad learning[J]. IEEE Trans. on Industrial Informatics, 2023, 19 (5): 7066- 7075.
23	XIE C X, ZHANG L M, ZHONG Z G. Few-shot unsupervised specific emitter identification based on density peak clustering algorithm and meta-learning[J], IEEE Sensors Journal, 2022, 22(18): 18008−18120.
24	TONG L, FANG M Q, XU Y L, et al. Specific emitter identification based on multichannel depth feature fusion[J]. Wireless Communications and Mobile Computing, 2022, 1, 9342085.
25	MARK S, ANDREW H, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]// Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 4510−4520.
26	ASHISH V, NOAM S, NIKI P, et al. Attention is all you need[EB/OL]. [2024-04-30]. http://arxiv.org/abs/1706.03762.
27	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc. of the Conference on Computer Vision and Pattern Recognition, 2016.
28	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale[C]//Proc. of the International Conference on Learning Representations, 2021.
29	DIKSHIT C, ANUPAM Y, FERRANTE N. A multi-agent optimization algorithm and its application to training multilayer perceptron models[J]. Evolving System, 2024, 15 (3): 849- 879.
30	SANKHE K, BELGIOVINE M, ZHOU F, et al. ORACLE: optimized radio classification through convolutional neural networks[C]// Proc. of the IEEE International Conference on Computer Communications, 2019: 370−378.
31	AMANI A S, FRANCESCO R, SALVATORE D, et al. Exposing the fingerprint: dissecting the impact of the wireless channel on radio fingerprinting[C]// Proc. of the IEEE INFOCOM, 2020: 646−655.

对照组	识别率
对照组	数据集1	数据集2	数据集3
1	95.67	92.36	87.38
2	94.25	93.12	93.15
3	91.66	94.65	88.11
4	84.52	87.33	79.28
5	75.35	81.05	75.17
6	70.31	74.63	70.57
7	62.2	70.66	64.27
8	99.6	99.31	98.8

算法	模型参数量	收敛时间/s
算法	模型参数量	数据集1	数据集2	数据集3
本文算法	628 813	100.36	131.26	115.14
MSMD-AE	416 157	97.32	128.31	127.35
DIR	633 135	104.78	138.1	126.76
MH-SEI	18 201 062	132.2	162.12	151.1
ABL	1 837 691	115.2	138.18	124.11

函数	识别率
函数	数据集1	数据集2	数据集3
Coiflet	95.32	94.21	91.22
Haar	92.21	88.10	90.37
Daubechies	94.24	91.62	87.55
Symlet	99.60	99.31	98.8

[1]	黄庚, 李旦, 张建秋. 时变二次规划的鲁棒归零神经网络求解模型[J]. 系统工程与电子技术, 2025, 47(9): 2775-2784.
[2]	王奇, 潘宇宁, 郑峻峰, 王力. 考虑力学形变的相控阵天线波束控制实现策略[J]. 系统工程与电子技术, 2025, 47(8): 2421-2428.
[3]	张梦泽, 田黎育. 基于高分辨谱估计的雷达目标分类方法[J]. 系统工程与电子技术, 2025, 47(7): 2146-2153.
[4]	魏波, 胡财富, 任芮彬. 面向不平衡数据的二阶段网络入侵检测新方法[J]. 系统工程与电子技术, 2025, 47(6): 2065-2075.
[5]	段阿敏, 张朝辉. 基于二次分解的混合神经网络蜂窝流量预测[J]. 系统工程与电子技术, 2025, 47(5): 1687-1697.
[6]	陈凯, 张德平. 基于图神经网络的导弹时序规划方法[J]. 系统工程与电子技术, 2025, 47(3): 862-870.
[7]	郭鹏飞, 靳锴, 陈琪锋, 魏才盛. 基于噪声元学习的卫星遥测信号异常检测方法[J]. 系统工程与电子技术, 2025, 47(2): 352-359.
[8]	付卫红, 张鑫钰, 刘乃安. 基于多尺度融合神经网络的同频同调制单通道盲源分离算法[J]. 系统工程与电子技术, 2025, 47(2): 641-649.
[9]	邵永琪, 杨丽花, 常澳, 任露露. RIS辅助的OFDM系统中时变信道估计方法[J]. 系统工程与电子技术, 2025, 47(1): 324-331.
[10]	张天骐, 杨宗方, 邹涵, 马焜然. 基于编码矩阵估计的极化码参数盲识别算法[J]. 系统工程与电子技术, 2024, 46(9): 3221-3230.
[11]	王磊, 张劲, 叶秋炫. LDACS系统基于循环谱和残差神经网络的频谱感知方法[J]. 系统工程与电子技术, 2024, 46(9): 3231-3238.
[12]	张瑞斌, 朱梦韬, 李云杰. 对调制识别网络隐身的雷达发射信号生成方法[J]. 系统工程与电子技术, 2024, 46(7): 2256-2268.
[13]	王彩云, 张慧雯, 王佳宁, 吴钇达, 常韵. 基于DTCWT-VAE的弹道中段目标RCS识别[J]. 系统工程与电子技术, 2024, 46(7): 2269-2275.
[14]	齐兵, 程建华, 赵砚驰, 汪籽粒. 基于微形变分析的电容式MEMS加速度计温漂误差精密估计方法[J]. 系统工程与电子技术, 2024, 46(7): 2437-2445.
[15]	吴巍屹, 贾云献, 姜相争, 史宪铭, 刘洁, 刘彬, 董恩志, 朱曦. 面向阶段任务的携行器材品种确定方法[J]. 系统工程与电子技术, 2024, 46(6): 2054-2064.