基于集成深度学习的雷达信号分选研究

doi:10.16182/j.issn1004731x.joss.17-0313

系统仿真学报 ›› 2019, Vol. 31 ›› Issue (9): 1868-1874.doi: 10.16182/j.issn1004731x.joss.17-0313

基于集成深度学习的雷达信号分选研究

金炜东, 陈春利

西南交通大学电气工程学院,四川成都 610031

收稿日期:2017-06-30 修回日期:2017-09-20 发布日期:2019-12-12
作者简介:金炜东(1959-),男,安徽,博士,教授,博导,研究方向为系统仿真与优化方法、智能信息处理等;陈春利(1993-),女,四川达州,硕士生,研究方向为雷达信号处理、模式识别。
基金资助:
国家自然科学基金(61461051),国家科技支撑计划(2015BAG14B01-05)

Research on Radar Signal Sorting based on Ensemble Deep Learning

Jin Weidong, Chen Chunli

School of Electrical Engineering, Southwest Jiao tong University, Chengdu 610031, China

Received:2017-06-30 Revised:2017-09-20 Published:2019-12-12

摘要/Abstract

摘要： 针对目前雷达信号分选方法中难以快速提取到合适的特征,且其准确度较低等问题,提出一种基于集成深度学习模型的信号分选方法。通过堆叠不同类型的深度信念网络改进算法,对雷达辐射源信号进行深入特征学习,将每层模型得到的后验概率进行线性集成学习,再通过决策层确定最终的分类结果,从而进一步提高信号的识别率。采用所提方法对仿真的不同类型的雷达辐射源信号进行分选,实验结果表明,该方法展现出较强的学习到更多数据本质特征的能力;相比于其它信号分选方法,所提方法能显著地提高信号分类的准确率,从而验证了方法的有效性和优越性。

关键词: 集成学习, 深度信念网络, 信号分选, 线性集成

Abstract: In view of the fact it is difficult to extract the appropriate features quickly and present signal sorting method’s accuracy is low, a signal sorting method based on ensemble deep learning model is proposed. This method stacks different types of deep belief network for radar emitter signal feature learning to improve algorithm. After learning the characteristics of the radar emitter signals deeply, the posterior probability of each model is linearly integrated and learned and the final classification results are determined by the decision layer to further improve the signal recognition rate. The method is used to separate different types of radar emitter simulation signals, and the results show that this method exhibits strong learning ability to nature features. Compared with other methods, it can significantly improve the classification accuracy, meanwhile it verifies the effectiveness and superiority.

Key words: ensemble learning, Deep Belief Networks, signal sorting, linear ensemble

中图分类号:

TP183

金炜东, 陈春利. 基于集成深度学习的雷达信号分选研究[J]. 系统仿真学报, 2019, 31(9): 1868-1874.

Jin Weidong, Chen Chunli. Research on Radar Signal Sorting based on Ensemble Deep Learning[J]. Journal of System Simulation, 2019, 31(9): 1868-1874.

参考文献

[1] Zhu J D, Zhao Y J, Tang J.Automatic Recognition of Radar Signals Based on Time-frequency Image Character[C]. IET International Radar Conference. Xi'an, China: IEEE, 2013: 1-6.
[2] 张葛祥, 荣海娜, 金炜东. 基于小波包变换和特征选择的雷达辐射源信号识别[J]. 电路与系统学报, 2006, 11(6): 45-49.
Zhang Gexiang, Rong Haina, Jin Weidong.Identification of radar emitter signals based on wavelet packet transform and feature selection[J]. Chinese Journal of circuits and systems, 2006, 11(6): 45-49.
[3] 余志斌. 基于脉内特征的雷达辐射源信号识别研究 [D]. 成都: 西南交通大学, 2010: 33-51.
Yu Zhibin.Study on Radar Emitter Signal Identification based on Intra-pulse Features [D]. Chengdu: Sourthwest Jiaotong University, 2010: 33-51.
[4] 周志文, 黄高明, 高俊, 等. 一种深度学习的雷达辐射源识别算法[J]. 西安电子科技大学学报, 2017, 44(3): 85-90.
Zhou Zhiwen, Huang Gaoming, Gao Jun, et al.A deep learning algorithm for radar emitter recognition[J]. Journal of Xi'an Electronic and Science University, 2017, 44(3): 85-90.
[5] Jurgen S.Deep learning in Neural Networks: an Overview[J]. Neural Networks (S0893-6080), 2015, 61: 85-117.
[6] Welling M.A new learning algorithm for mean field Boltzmann machines[C]. Proceedings of the International Conference on Artificial Neural Networks, Madrid, Spain, 2001.
[7] Hinton G E, Osindero S, Teh Y W.A Fast Learning Algorithm for Deep Belief Nets[J]. Neural Computation (S0899-7667), 2006, 18(7): 1527-1554.
[8] Deng L, Chen J.Sequence classification using the high-level features extracted from deep neural networks[C]. IEEE International Conference on Acoustics: IEEE, 2014.
[9] Deng L, Li J, Huang J T, et al.Recent advances in deep learning for speech research at Microsoft[C]. IEEE International Conference on Acoustics: IEEE, 2013.
[10] Deng L, Hinton G, Kingsbury B.New types of deep neural network learning for speech recognition and related applications: an overview[C]. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing: IEEE, 2013.
[11] Deng L, Yu D, Platt J.Scalable stacking and learning for building deep architectures[C]. IEEE International Conference on Acoustics: IEEE, 2012.
[12] Hinton G, Salakhutdinov R.Reducing the dimensionality of data with neural networks[J]. Science (S0036-8075), 2006, 313(5786): 504-507.
[13] Hinton G, Deng L, Yu D, et al.Deep Neural Networks for Acoustic Modeling in Speech Recognition[J]. IEEE Signal Processing Magazine (S1053-5888), 2012, 29(6): 82-97.
[14] Mohamed A, Dahl G E, Hinton G.Acoustic Modeling Using Deep Belief Networks[J]. IEEE Transactions on Audio, Speech and Language Processing (S1558-7916), 2012, 20(1): 14-22.

基于集成深度学习的雷达信号分选研究

Research on Radar Signal Sorting based on Ensemble Deep Learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	董海, 高秀秀, 魏铭琦. 基于ACS-DBN的电弧增材制造焊道尺寸预测[J]. 系统仿真学报, 2021, 33(12): 2828-2837.
[2]	邓欣, 龙灿, 米建勋, 张博宪, 孙开伟, 王进. 基于多域特征与随机子空间集成的脑电分类[J]. 系统仿真学报, 2020, 32(9): 1787-1798.
[3]	吴迎年, 贺梦嘉, 项伟. 基于集成学习的人眼定位和头部状态检测研究[J]. 系统仿真学报, 2019, 31(11): 2366-2373.
[4]	高强, 阳武, 李倩. 基于空间信息的DBN图像分类快速训练模型[J]. 系统仿真学报, 2015, 27(3): 549-558.