干扰规则库未知条件下的干扰决策
|
摘要
针对模板匹配(template matching,TM)应用于未知干扰规则库时干扰决策正确率低问题,提出基于迁移成分分析-支持向量机(transfer component analysis-support vector machine,TCA-SVM)的干扰决策方法。对空-空场景机载多功能火控雷达,提取雷达信号特征,构建雷达干扰规则库及未知威胁数据集,通过迁移成分分析把两个样本集的特征映射到同一低维隐藏空间,提取样本隐藏空间特征,经过支持向量机训练,实现对未知威胁数据集的干扰决策。实验结果表明:所提方法有效提高了干扰决策正确率,TCA-SVM出色的学习及泛化能力,较好地解决了干扰规则库未知条件下干扰决策问题。
To solve the problem of low jamming decision accuracy of template matching(TM)method under condition of unknown jamming rule base,a method based on transfer component analysis-support vector machine(TCA-SVM)is proposed.For airborne multifunctional fire control radar on air-to-air scene,the signal features are extracted and the jamming rule base and unknown threat dataset are constructed.The features of the two sample sets are mapped to the same low dimension hidden space via transfer component analysis.The hidden space sample features are extracted and trained by support vector machine to realize jamming decision on the unknown threat dataset.The experiment results show that the proposed method can effectively improve the jamming decision accuracy rate.The jamming decision problem under the condition of unknown jamming rule base is solved because of excellent learning and generalization ability of TCA-SVM.
To solve the problem of low jamming decision accuracy of template matching(TM)method under condition of unknown jamming rule base,a method based on transfer component analysis-support vector machine(TCA-SVM)is proposed.For airborne multifunctional fire control radar on air-to-air scene,the signal features are extracted and the jamming rule base and unknown threat dataset are constructed.The features of the two sample sets are mapped to the same low dimension hidden space via transfer component analysis.The hidden space sample features are extracted and trained by support vector machine to realize jamming decision on the unknown threat dataset.The experiment results show that the proposed method can effectively improve the jamming decision accuracy rate.The jamming decision problem under the condition of unknown jamming rule base is solved because of excellent learning and generalization ability of TCA-SVM.
引文
[1]MARTINEZ D L,BRUSONI S.Cognitive flexibility and adaptive decision-making:evidence from a laboratory study of expert decision-makers[J].Strategic Management Journal,2018,39(4):1031-1058.
[2]GUO Y Q,WU Y M,LIU H.Construction of waveform library in cognitive radar[J].Polish Maritime Research,2017,24(s2):22-29.
[3]HAYKIN S.Cognitive radar:a way of the future[J].IEEE Signal Processing Magazine,2006,23(1):30-40.
[4]KWON G,PARK J Y,HWANG K C.Design of a subarray configuration for multifunction radars using a nested optimization scheme[J].Electromagnetics,2016,36(4):276-285.
[5]SAMEER A.Cognitive electronic warfare system[C]∥Proc.of the Cognitive Radio Network,2016.
[6]DABCEVIC K,MUGHAL M O,MARCENARO L,et al.Cognitive radio as the facilitator for advanced communications electronic warfare solutions[J].Journal of Signal Processing Systems,2016,83(1):29-44.
[7]LESTER A M,KALLE R K,JOSEPH K C.A concept for the application of artificial intelligence technology to battlefield spectrum management[C]∥Proc.of the Military Communications Conference Crisis Communications:the Promise and Reality,1987:161-166.
[8]DARPA.Adaptive radar countermeasures[EB/OL].[2012-08-27].https:∥www.fbo.gov.
[9]DARPA.Behavior learning for adaptive electronic warfare[EB/OL].[2010-10-06].https:∥www.fbo.gov.
[10]Air Force.Cognitive jammer[EB/OL].[2010-1-20].https:∥www.fbo.gov.
[11]DARPA.Communications under extreme RF spectrum conditions[R/OL].[2010-9-10].https:∥www.fbo.gov.
[12]唐文龙,张剑云,王冰川,等.干扰样式选择方法研究[J].现代雷达,2017,39(1):72-76.TANG W L,ZHANG J Y,WANG B C,et al.A study on jamming style selecting[J].Modern Radar,2017,39(1):72-76.
[13]李云杰,朱云鹏,高梅国.基于Q-学习算法的认知雷达对抗过程设计[J].北京理工大学学报,2015,35(11):1194-1199.LI Y J,ZHU Y P,GAO M G.Design of cognitive radar jamming based on Q-learning algorithm[J].Transaction of Beijing Institute of Technology,2015,35(11):1194-1199.
[14]陈凯.对相控阵雷达的智能干扰决策技术研究[D].西安:西安电子科技大学,2012:39-47.CHEN K.Research on intelligent jamming decision making technology against phased array radar[D].Xi’an:Xidian University,2012:39-47.
[15]YAN H L,DING Y K,LI P H,et al.Mind the class weight bias:weighted maximum mean discrepancy for unsupervised domain adaptation[C]∥Proc.of the IEEE Conference on Computer Vision and Pattern Recognition,2017:945-954.
[16]DONG R P,MENG H,LONG Z G,et al.Dimensionality reduction by soft-margin support vector machine[C]∥Proc.of the IEEE International Conference on Agents,2017:154-156.
[17]GRUBINGER T,BIRLUTIU A,SCHNER H,et al.Multidomain transfer component analysis for domain generalization[J].Neural Processing Letters,2017,46(3):1-11.
[18]GOUSSIES N A,UBALDE S,MEJAIL M.Transfer learningdecision forests for gesture recognition[J].Journal of Machine Learning Research,2017,15(1):3667-3690.
[19]GRUBINGER T,BIRLUTIU A,SCHNER H,et al.Multi-domain transfer component analysis for domain generalization[J].Neural Processing Letters,2017,46(3):845-855.
[20]ZHANG Y Z,LIU Y X,SONYA C,et al.Joint transfer component analysis and metric learning for person re-identification[J].Electronics Letters,2018,54(13):821-823.
[21]PAN S J,KWOK J T,YANG Q.Transfer learning via dimensionality reduction[C]∥Proc.of the AAAI Conference on Artificial Intelligence,2008:677-682.
[22]XUE Y,ZHANG N,YIN X R,et al.Sufficient dimension reduction using Hilbert-Schmidt independence criterion[J].Computational Statistics and Data Analysis,2017,115(11):67-78.
[23]HE H L.A network traffic classification method using support vector machine with feature weighted-degree[J].Journal of Digital Information Management,2017,15(2):76-83.
[24]SUN F F,XU P H,DING X M.Multi-core SVM optimized visual word package model for garment style classification[J].Cluster Computing,2018(4):1-7.
[25]ZHANG W X,SUN F L,WANG B.Radar signal intra-pulse feature extraction based on improved wavelet transform algorithm[J].International Journal of Communications Network&System Sciences,2017,10(8):118-127.
[26]XU W,PAN Y C,HAN J,et al.Radar signal sorting based on resemblance coefficient of Welch power spectrum[C]∥Proc.of the International Conference on Systems and Informatics,2017:1120-1125.
[27]WU L W,ZHAO Y Q,WANG Z,et al.Specific emitter identification using fractal features based on box-counting dimension and variance dimension[C]∥Proc.of the International Symposium on Signal Processing and Information Technology,2017:226-231.
[28]SKOLNIK M I.雷达手册[M].北京:电子工业出版社,2010:188-192.SKOLNIK M I.Radar handbook[M].Beijing:Publishing House of Electronics Industry,2010:188-192.
[29]中航工业雷达与电子设备研究院.机载雷达手册[M].4版.北京:国防工业出版社,2013:137-167.Avic Industrial Radar and Electronic Equipment Research Institute.Airborne radar handbook[M].4th ed.Beijing:National Defense Industry Press,2013:137-167.
[30]SHIEH C S,LIN C T.A vector neural network for emitter identification[J].IEEE Trans.on Antennas&Propagation,2002,50(8):1120-1127.
[2]GUO Y Q,WU Y M,LIU H.Construction of waveform library in cognitive radar[J].Polish Maritime Research,2017,24(s2):22-29.
[3]HAYKIN S.Cognitive radar:a way of the future[J].IEEE Signal Processing Magazine,2006,23(1):30-40.
[4]KWON G,PARK J Y,HWANG K C.Design of a subarray configuration for multifunction radars using a nested optimization scheme[J].Electromagnetics,2016,36(4):276-285.
[5]SAMEER A.Cognitive electronic warfare system[C]∥Proc.of the Cognitive Radio Network,2016.
[6]DABCEVIC K,MUGHAL M O,MARCENARO L,et al.Cognitive radio as the facilitator for advanced communications electronic warfare solutions[J].Journal of Signal Processing Systems,2016,83(1):29-44.
[7]LESTER A M,KALLE R K,JOSEPH K C.A concept for the application of artificial intelligence technology to battlefield spectrum management[C]∥Proc.of the Military Communications Conference Crisis Communications:the Promise and Reality,1987:161-166.
[8]DARPA.Adaptive radar countermeasures[EB/OL].[2012-08-27].https:∥www.fbo.gov.
[9]DARPA.Behavior learning for adaptive electronic warfare[EB/OL].[2010-10-06].https:∥www.fbo.gov.
[10]Air Force.Cognitive jammer[EB/OL].[2010-1-20].https:∥www.fbo.gov.
[11]DARPA.Communications under extreme RF spectrum conditions[R/OL].[2010-9-10].https:∥www.fbo.gov.
[12]唐文龙,张剑云,王冰川,等.干扰样式选择方法研究[J].现代雷达,2017,39(1):72-76.TANG W L,ZHANG J Y,WANG B C,et al.A study on jamming style selecting[J].Modern Radar,2017,39(1):72-76.
[13]李云杰,朱云鹏,高梅国.基于Q-学习算法的认知雷达对抗过程设计[J].北京理工大学学报,2015,35(11):1194-1199.LI Y J,ZHU Y P,GAO M G.Design of cognitive radar jamming based on Q-learning algorithm[J].Transaction of Beijing Institute of Technology,2015,35(11):1194-1199.
[14]陈凯.对相控阵雷达的智能干扰决策技术研究[D].西安:西安电子科技大学,2012:39-47.CHEN K.Research on intelligent jamming decision making technology against phased array radar[D].Xi’an:Xidian University,2012:39-47.
[15]YAN H L,DING Y K,LI P H,et al.Mind the class weight bias:weighted maximum mean discrepancy for unsupervised domain adaptation[C]∥Proc.of the IEEE Conference on Computer Vision and Pattern Recognition,2017:945-954.
[16]DONG R P,MENG H,LONG Z G,et al.Dimensionality reduction by soft-margin support vector machine[C]∥Proc.of the IEEE International Conference on Agents,2017:154-156.
[17]GRUBINGER T,BIRLUTIU A,SCHNER H,et al.Multidomain transfer component analysis for domain generalization[J].Neural Processing Letters,2017,46(3):1-11.
[18]GOUSSIES N A,UBALDE S,MEJAIL M.Transfer learningdecision forests for gesture recognition[J].Journal of Machine Learning Research,2017,15(1):3667-3690.
[19]GRUBINGER T,BIRLUTIU A,SCHNER H,et al.Multi-domain transfer component analysis for domain generalization[J].Neural Processing Letters,2017,46(3):845-855.
[20]ZHANG Y Z,LIU Y X,SONYA C,et al.Joint transfer component analysis and metric learning for person re-identification[J].Electronics Letters,2018,54(13):821-823.
[21]PAN S J,KWOK J T,YANG Q.Transfer learning via dimensionality reduction[C]∥Proc.of the AAAI Conference on Artificial Intelligence,2008:677-682.
[22]XUE Y,ZHANG N,YIN X R,et al.Sufficient dimension reduction using Hilbert-Schmidt independence criterion[J].Computational Statistics and Data Analysis,2017,115(11):67-78.
[23]HE H L.A network traffic classification method using support vector machine with feature weighted-degree[J].Journal of Digital Information Management,2017,15(2):76-83.
[24]SUN F F,XU P H,DING X M.Multi-core SVM optimized visual word package model for garment style classification[J].Cluster Computing,2018(4):1-7.
[25]ZHANG W X,SUN F L,WANG B.Radar signal intra-pulse feature extraction based on improved wavelet transform algorithm[J].International Journal of Communications Network&System Sciences,2017,10(8):118-127.
[26]XU W,PAN Y C,HAN J,et al.Radar signal sorting based on resemblance coefficient of Welch power spectrum[C]∥Proc.of the International Conference on Systems and Informatics,2017:1120-1125.
[27]WU L W,ZHAO Y Q,WANG Z,et al.Specific emitter identification using fractal features based on box-counting dimension and variance dimension[C]∥Proc.of the International Symposium on Signal Processing and Information Technology,2017:226-231.
[28]SKOLNIK M I.雷达手册[M].北京:电子工业出版社,2010:188-192.SKOLNIK M I.Radar handbook[M].Beijing:Publishing House of Electronics Industry,2010:188-192.
[29]中航工业雷达与电子设备研究院.机载雷达手册[M].4版.北京:国防工业出版社,2013:137-167.Avic Industrial Radar and Electronic Equipment Research Institute.Airborne radar handbook[M].4th ed.Beijing:National Defense Industry Press,2013:137-167.
[30]SHIEH C S,LIN C T.A vector neural network for emitter identification[J].IEEE Trans.on Antennas&Propagation,2002,50(8):1120-1127.