基于栈式降维与字典学习的辐射源调制识别

doi:10.3969/j.issn.1000-1093.2020.10.012

摘要/Abstract

摘要： 针对低信噪比环境下辐射源调制识别准确率和时效性不高问题，提出一种基于时频特征、栈式降维和字典学习的分类识别系统。对时域信号进行时频变换和稀疏域降噪，获取二维时频特征并降低噪声干扰；基于无监督学习的栈式降维网络提取低维非线性特征，进而降低特征冗余并提高后续处理时效性；通过多项判别约束和正则约束强化字典类间判别能力与分类时效性，并实现调制类型识别。仿真结果验证了该分类识别系统的有效性和可行性：当信噪比为-8 dB时，单载频信号、二相频率编码信号、四相频率编码信号、线性调频信号、二相编码信号、四相编码信号、Frank信号7类辐射源信号的整体平均识别率达到95.93%，具备较强的鲁棒性和时效性。

关键词: 辐射源调制识别, 栈式降维, 字典学习, 稀疏域降噪, 正则约束, 时频特征

Abstract: A classification and recognition system based on time-frequency features, stacked dimension reduction and dictionary learning is proposed for the problems about low accuracy and timeliness of modulation recognition of emitter signal in a low signal-to-noise ratio environment. The system performs time-frequency transformation and sparse domain noise reduction on the time-domain signals to obtain the two-dimensional time-frequency features and reduce the noise interference. Then it extracts the low-dimensional non-linear features based on unsupervised stacked dimension reduction networks to reduce the feature redundancy. In addition, it improves the timeliness of subsequent processing. Based on multiple discriminant constraints and regular constraints, the discriminative ability and classification timeliness of the dictionary are enhanced to realize the modulation recognition. The simulated results verify the effectiveness and feasibility of the proposed method. The overall average recoghition rate of 7 types of emitter signals, such as single carrier frequency modulation (SCFM) signal, binary frequency shift keying (BPSK) signal, quadrature frequency shift keying (QFSK) signal, linear frequency modulation (LFM) signal, binary phase shift keying (BPSK) signal, quadrature phase shift keying (QPSK) signal, Frank signal, is 95.93% at -8 dB, which has strong robustness and timeliness.

Key words: emittersignalmodulationrecognition, stackeddimensionreduction, dictionarylearning, sparsedomainnoisereduction, regularconstraint, time-frequencyfeature

中图分类号:

TN974

李东瑾，杨瑞娟，李晓柏，朱晟坤，费太勇. 基于栈式降维与字典学习的辐射源调制识别[J]. 兵工学报, 2020, 41(10): 2023-2032.

LI Dongjin， YANG Ruijuan， LI Xiaobai， ZHU Shengkun， FEI Taiyong. Emitter Signal Modulation Recognition Based on Stacked Dimension Reduction and Dictionary Learning[J]. Acta Armamentarii, 2020, 41(10): 2023-2032.

参考文献

［1］ GUO Q, NAN P L, WAN J. Radar signal recognition based on ambiguity function features and cloud model similarity［C］∥Proceedings of the 8th International Conference on Ultrawideband and Ultrashort Impulse Signals. Odessa, Ukraine: IEEE, 2016: 128-134.
［2］ ZHANG G X, JIN W D, HU L Z. Radar emitter signal recognition based on complexity features［J］. Journal of Southwest Jiaotong University, 2004, 12(2): 116-122.
［3］ ZHANG Z, LI Y B, JIN S S, et al. Modulation signal recognition based on information entropy and ensemble learning［J］. Entropy, 2018, 20(3): 198.
［4］ ASLAM M W, ZHU Z C, NANDI A K. Automatic modulation classification using combination of genetic programming and KNN［J］. IEEE Transactions on Wireless Communications, 2012, 11(8): 2742-2750.
［5］ LIU L T, WANG S, ZHAO Z K. Radar waveform recognition based on time-frequency analysis and artificial bee colony-support vector machine［J］. Electronics, 2018, 7(5): 59.
［6］ ZHANG M, DIAO M, GUO L M. Convolutional neural networks for automatic cognitive radio waveform recognition［J］. IEEE Access, 2017, 5: 11074-11082.
［7］ WAN J, YU X, GUO Q. LPI radar waveform recognition based on CNN and TPOT［J］. Symmetry, 2019, 11(5): 725.
［8］ GAO L P, ZHANG X L, GAO J P, et al. Fusion image based radar signal feature extraction and modulation recognition［J］. IEEE Access, 2019, 7: 13135-13148.
［9］ GUO Q, YU X, RUAN G Q. LPI radar waveform recognition based on deep convolutional neural network transfer learning［J］. Symmetry, 2019, 11(4): 540.
［10］ CAO R, CAO J W, MEI J P, et al. Radar emitter identification with bispectrum and hierarchical extreme learning machine［J］. Multimedia Tools and Applications, 2019, 78(20): 28953-28970.
［11］ WANG X B, HUANG G M, ZHOU Z W, et al. Radar emitter recognition based on the energy cumulant of short time Fourier transform and reinforced deep belief network［J］. Sensors, 2018, 18(9): 3103.
［12］ QU Z Y, MAO X J, DENG Z A. Radar signal intra-pulse modulation recognition based on convolutional neural network［J］. IEEE Access, 2018, 6: 43874-43884.
［13］ KONG S H, KIM M, HOANG L M, et al. Automatic LPI radar waveform recognition using CNN［J］. IEEE Access, 2018, 6: 4207-4219.
［14］ QU Z Y, WANG W, HOU C, et al. Radar signal intra-pulse modulation recognition based on convolutional denoising autoencoder and deep convolutional neural network［J］. IEEE Access, 2019, 7: 112339-112347.
［15］ BAO C L, JI H, QUAN Y H, et al. Dictionary Learning for sparse coding: algorithms and convergence analysis［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(7):1356-1369.
［16］ SONG J Q, XIE X M, SHI G M, et al. Multi-layer discriminative dictionary learning with locality constraint for image classification［J］. Pattern Recognition, 2019, 91(7): 135-146.
［17］ ZHAO Z, FENG G C, ZHANG L F, et al. Novel orthogonal based collaborative dictionary learning for efficient face recognition［J］. Knowledge-Based Systems, 2019, 163(1): 533-545.
［18］ REN J H, ZHANG Z, LI S, et al. Learning hybrid representation by robust dictionary learning in factorized compressed space［J］. IEEE Transactions on Image Processing, 2020, 29: 3941-3956.
［19］ MA J, HUANG G M, ZUO W, et al. Robust radar waveform recognition algorithm based on random projections and sparse classification［J］. IET Radar, Sonar & Navigation, 2014, 8(4): 290-296.
［20］周志文, 黄高明, 高俊. 基于压缩协作表示的辐射源识别算法［J］. 航空学报, 2016, 37(7):2251-2258.
ZHOU Z W, HUANG G M, GAO J. Emitter recognition algorithm based on compressively collaborative representation［J］. Acta Aeronautica et Astronautica Sinica, 2016, 37(7): 2251-2258. (in Chinese)
［21］ LI F, WONG A, CLAUSI D A. Comparative study of feature space projection methods for hyperspectral image classification［C］∥Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium. Quebec City, QC,Canada: IEEE, 2014: 3438-3441.
［22］ SCHLKOPF B, SMOLA A, MLLER K R. Kernel principal component analysis［C］∥Proceedings of International Conference on Artificial Neural Networks. Cambridge, UK: IET, 1997: 583-588.
［23］ KASUN L L C, YANG Y, HUANG G B, et al. Dimension reduction with extreme learning machine［J］. IEEE Transactions on Image Processing, 2016, 25(8): 3906-3918.
［24］ HUANG H, SHI G Y, HE H B, et al. Dimensionality reduction of hyperspectral imagery based on spatial-spectral manifold learning［J］. IEEE Transactions on Cybernetics, 2019, 50(6): 2604-2616.
［25］ ZHANG M, LIU L T, DIAO M, et al. LPI radar waveform recognition based on time-frequency distribution［J］. Sensors, 2016, 16(10): 1682-1706.
［26］ FENG Z Z, YANG M, ZHANG L, et al. Joint discriminative dimensionality reduction and dictionary learning for face recognition［J］. Pattern Recognition, 2013, 46(8): 2134-2143.
［27］ XU J, XIANG L, LIU Q S, et al. Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images［J］. IEEE Transactions on Medical Imaging, 2015, 35(1): 119-130.
［28］ ZHANG J, YU J, TAO D C. Local deep-feature alignment for unsupervised dimension reduction［J］. IEEE Transactions on Image Processing, 2018, 27(5): 2420-2432.
［29］ GUO J, LI H H, NING J F, et al. Feature dimension reduction using stacked sparse auto-encoders for crop classification with multi-temporal, quad-pol SAR data［J］. Remote Sensing, 2020, 12(2): 321.
［30］ VAN ERVEN T, HARREMOS P. Rényi divergence and Kullback-Leibler divergence［J］. IEEE Transactions on Information Theory, 2014, 60(7): 3797-3820.
［31］ LI H, LI K L, AN J Y, et al. MSGD: a novel matrix factorization approach for large-scale collaborative filtering recommender systems on GPUs［J］. IEEE Transactions on Parallel and Distributed Systems, 2017, 29(7): 1530-1544.
［32］ BECK A, TEBOULLE M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems［J］. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202.
［33］ ZOU H, HASTIE T. Regularization and variable selection via the elastic net［J］. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2005, 67(2): 301-320.
［34］ ZHANG L, YANG M, FENG X C. Sparse representation or collaborative representation: which helps face recognition?［C］∥Proceedings of 2011 International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 471-478.

[1]	李东瑾，杨瑞娟，董睿杰. 基于联合投影字典学习的辐射源调制识别[J]. 兵工学报, 2020, 41(7): 1464-1472.
[2]	呙鹏程，吴礼洋. 融合卷积特征与判别字典学习的低截获概率雷达信号识别[J]. 兵工学报, 2019, 40(9): 1881-1889.
[3]	吴笑天，王星，王志鹏，周一鹏，陈游. 基于Fisher判别字典学习的辐射源调制特征识别[J]. 兵工学报, 2018, 39(3): 553-559.
[4]	计宏磊，杨清文，秦晓燕. 基于分层模型和鲁棒字典学习的背景差分炸点检测[J]. 兵工学报, 2016, 37(4): 705-711.