混沌海杂波背景下的微弱信号检测混合算法

行鸿彦; 张强; 徐伟

doi:10.7498/aps.64.040506

摘要

基于经验模态分解理论, 提出了一种基于粒子群算法的支持向量机预测方法. 采用总体平均经验模式分解法将混沌信号分解为若干固有模态函数和趋势分量, 将复杂的非线性信号转化为具有不同尺度特征的平稳分量. 利用粒子群算法对支持向量机的惩罚系数和核函数进行优化, 结合支持向量机建立混沌序列的单步预测模型. 从预测误差中检测淹没在混沌背景中的微弱信号(包括瞬态信号和周期信号). 对Lorenz系统和实测IPIX雷达数据进行仿真实验, 结果表明, 该方法能够有效地从混沌背景噪声中检测出微弱目标信号, Lorenz系统得到的均方根误差0.000000339 (-102.8225 dB时)比传统支持向量机方法的均方根误差0.049 (-54.60 dB时)降低了5个数量级, 从海杂波中检测出具有谐波特性的微弱信号, 表明预测模型具有更低的门限和误差.

关键词:

Abstract

According to the empirical mode decomposition (EMD) theory, a prediction method of support vector machine (SVM) is proposed based on particle swarm optimization. The ensemble EMD method is used to decompose the signal into some intrinsic mode function components which are taken as the input of the SVM to predict the data. All the predicted values are combined, and the weak signals submerged in chaos background, including the transient signal and periodic signal, are detected from the prediction error. Lorenz attractor and the data from the McMaster IPIX radar sea clutter database are used in the simulation. The results show that the proposed method can effectively detect the weak target from chaotic signal. When the signal-to-noise ratio is 102.8225 dB in the chaotic noise background, by using the new method the root mean square error can be reduced by five orders of magnitude, reaching 0.00000033092, while the conventional SVM can reach only 0.049 under the condition of -54.60 dB and the weak target detected in sea clutter has the harmonic characteristics, which shows the prediction model has a lower threshold and error.

Keywords:

作者及机构信息

1.
南京信息工程大学, 气象灾害预报预警与评估协同创新中心, 江苏省气象探测与信息处理重点实验室, 南京 210044

基金项目: 国家自然科学基金(批准号: 61072133)、江苏普通高校研究生实践创新计划(批准号: SJZZ_0112)、江苏省产学研联合创新资金计划(批准号: BY2013007-02, BY2011112)、江苏省高校科研成果产业化推进项目(批准号: JHB2011-15)、江苏省“信息与通信工程”优势学科和江苏省“六大人才高峰”计划资助的课题.

Authors and contacts

1.
Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Key Laboratory of Meteorological Observation and Information Processing of Jiangsu Province, Nanjing University of Information Science and Technology, Nanjing 210044, China

Funds: Project supported by the National Natural Science Foundation of China (Grant No. 61072133), the Practice Innovation Program of Colleges and Universities Postgraduates of Jiangsu Province, China (Grant No. SJZZ_0112), the Production, Learning and Research Joint Innovation Program of Jiangsu Province, China (Grant Nos. BY2013007-02, BY2011112), the Industrialization of Research Findings Promotion Program of Institution of Higher Education of Jiangsu Province, China (Grant No. JHB2011-15), the Advantage Discipline “Information and Communication Engineering” of Jiangsu Province, China, and the “Summit of the Six Top Talents” Program of Jiangsu Province, China.

参考文献

[1]	Fradkov A L, Evans R J 2005 Annu. Rev. Control 29 33
[2]	Vicha T, Dohnal M 2008 Chaos Soliton. Fract. 38 70
[3]	Koh C L, Ushio T 1997 IEEE Trans. Circuits Syst. I 44 383
[4]	Haykin S, Li X B 1995 Proc. IEEE 83 95
[5]	Lo T, Leung H 1993 IEE Proc. F 140 243
[6]	Ma X Y, Huang X B, Zhang X D 2003 Acta Electron. Sin. 31 907 (in Chinese) [马晓岩, 黄晓斌, 张贤达 2003 电子学报 31 907]
[7]	Xiang Z, Zhang T Y, Sun J C 2005 Acta Photon. Sin. 34 1756 (in Chinese) [相征, 张太镒, 孙建成 2005 光子学报 34 1756]
[8]	Xue B W, Zhang Z F, Cong W 2010 IEEE the 2nd International Conference on Computer and Automation Engineering Singapore City, Singapore, February 26-28, 2010 p466
[9]	Huang N E 1998 Proc. R. Soc. Lond. 45 903
[10]	Cortes C,Vapnik V 1995 Mach. Learn. 20 273
[11]	Birx D L, Pipenberg S J 1992 IEEE International Joint Conference on Networks Baltimore, USA, June 7-11, 1992 p886
[12]	Leung H 1998 IEEE Trans. Circuits Syst. I 45 314
[13]	Cui W Z, Zhu C C, Bao W X, Liu J H 2004 Acta Phys. Sin. 53 3303 (in Chinese) [崔万照, 朱长纯, 保文星, 刘君华 2004 物理学报 53 3303]
[14]	Gao F, Tong H Q 2006 Acta Phys. Sin. 55 3307 (in Chinese) [高飞, 童恒庆 2006 物理学报 55 3307]
[15]	Xing H Y, Xu W 2007 Acta Phys. Sin. 56 3771 (in Chinese) [行鸿彦, 徐伟 2007 物理学报 56 3771]
[16]	Xing H Y, Hou J Y 2009 IEEE 2nd International Conference on Biomedical Engineering and Informatics Tianjin, China, October 17-19, 2009 p3
[17]	Xing H Y, Cheng Y Y, Xu W, Gong P 2013 IET International Conference on Information and Communications Technologies Beijing, China, April 27-29, 2013 p333
[18]	Hu A J, Sun J J, Xiang L 2011 J. Vib. Meas. Diagn. 31 432 (in Chinese) [胡爱军, 孙敬敬, 向玲 2011振动·测试与诊断 31 432]
[19]	Wu Z, Huang N E 2009 Adv. Adapt. Data Anal. 1 20
[20]	Meng Q F, Chen Y H, Peng Y H 2009 Chin. Phys. B 18 2194
[21]	Tanaka T, Toumiya T, Suzuki T 1997 Renew. Energ. 12 387
[22]	Lu J, Wang H B, Sun G C 2009 Chin. Phys. B 18 1598
[23]	Eberhart R C, Kennedy J 1995 Proceedings of the Sixth International Symposium on Micro Machine and Human Science Washington, USA, October 4-6, 1995 p40
[24]	Parsopoulos K E, Vrahatis M N 2002 Nat. Comput. 1 247
[25]	Gao F, Li Z Q, Tong H Q 2008 Chin. Phys. B 17 11967
[26]	Wang F Y, Yuan G N, Xie Y J, Qiao X W 2009 Radar Sci. Technol. 7 53 (in Chinese) [王福友, 袁赣南, 谢燕军, 乔相伟 2009 雷达科学与技术7 53]

施引文献

[1]	Fradkov A L, Evans R J 2005 Annu. Rev. Control 29 33
[2]	Vicha T, Dohnal M 2008 Chaos Soliton. Fract. 38 70
[3]	Koh C L, Ushio T 1997 IEEE Trans. Circuits Syst. I 44 383
[4]	Haykin S, Li X B 1995 Proc. IEEE 83 95
[5]	Lo T, Leung H 1993 IEE Proc. F 140 243
[6]	Ma X Y, Huang X B, Zhang X D 2003 Acta Electron. Sin. 31 907 (in Chinese) [马晓岩, 黄晓斌, 张贤达 2003 电子学报 31 907]
[7]	Xiang Z, Zhang T Y, Sun J C 2005 Acta Photon. Sin. 34 1756 (in Chinese) [相征, 张太镒, 孙建成 2005 光子学报 34 1756]
[8]	Xue B W, Zhang Z F, Cong W 2010 IEEE the 2nd International Conference on Computer and Automation Engineering Singapore City, Singapore, February 26-28, 2010 p466
[9]	Huang N E 1998 Proc. R. Soc. Lond. 45 903
[10]	Cortes C,Vapnik V 1995 Mach. Learn. 20 273
[11]	Birx D L, Pipenberg S J 1992 IEEE International Joint Conference on Networks Baltimore, USA, June 7-11, 1992 p886
[12]	Leung H 1998 IEEE Trans. Circuits Syst. I 45 314
[13]	Cui W Z, Zhu C C, Bao W X, Liu J H 2004 Acta Phys. Sin. 53 3303 (in Chinese) [崔万照, 朱长纯, 保文星, 刘君华 2004 物理学报 53 3303]
[14]	Gao F, Tong H Q 2006 Acta Phys. Sin. 55 3307 (in Chinese) [高飞, 童恒庆 2006 物理学报 55 3307]
[15]	Xing H Y, Xu W 2007 Acta Phys. Sin. 56 3771 (in Chinese) [行鸿彦, 徐伟 2007 物理学报 56 3771]
[16]	Xing H Y, Hou J Y 2009 IEEE 2nd International Conference on Biomedical Engineering and Informatics Tianjin, China, October 17-19, 2009 p3
[17]	Xing H Y, Cheng Y Y, Xu W, Gong P 2013 IET International Conference on Information and Communications Technologies Beijing, China, April 27-29, 2013 p333
[18]	Hu A J, Sun J J, Xiang L 2011 J. Vib. Meas. Diagn. 31 432 (in Chinese) [胡爱军, 孙敬敬, 向玲 2011振动·测试与诊断 31 432]
[19]	Wu Z, Huang N E 2009 Adv. Adapt. Data Anal. 1 20
[20]	Meng Q F, Chen Y H, Peng Y H 2009 Chin. Phys. B 18 2194
[21]	Tanaka T, Toumiya T, Suzuki T 1997 Renew. Energ. 12 387
[22]	Lu J, Wang H B, Sun G C 2009 Chin. Phys. B 18 1598
[23]	Eberhart R C, Kennedy J 1995 Proceedings of the Sixth International Symposium on Micro Machine and Human Science Washington, USA, October 4-6, 1995 p40
[24]	Parsopoulos K E, Vrahatis M N 2002 Nat. Comput. 1 247
[25]	Gao F, Li Z Q, Tong H Q 2008 Chin. Phys. B 17 11967
[26]	Wang F Y, Yuan G N, Xie Y J, Qiao X W 2009 Radar Sci. Technol. 7 53 (in Chinese) [王福友, 袁赣南, 谢燕军, 乔相伟 2009 雷达科学与技术7 53]

[1]	张涛, 陈万忠, 李明阳. 基于频率切片小波变换和支持向量机的癫痫脑电信号自动检测. 物理学报, 2016, 65(3): 038703. doi: 10.7498/aps.65.038703
[2]	赵志刚, 张纯杰, 苟向锋, 桑虎堂. 基于粒子群优化支持向量机的太阳电池温度预测. 物理学报, 2015, 64(8): 088801. doi: 10.7498/aps.64.088801
[3]	行鸿彦, 朱清清, 徐伟. 一种混沌海杂波背景下的微弱信号检测方法. 物理学报, 2014, 63(10): 100505. doi: 10.7498/aps.63.100505
[4]	孟庆芳, 陈珊珊, 陈月辉, 冯志全. 基于递归量化分析与支持向量机的癫痫脑电自动检测方法. 物理学报, 2014, 63(5): 050506. doi: 10.7498/aps.63.050506
[5]	刘瑞兰, 王徐亮, 唐超. 基于粒子群算法的有机半导体NPB传输特性辨识. 物理学报, 2014, 63(2): 028105. doi: 10.7498/aps.63.028105
[6]	于洋, 郝中骐, 李常茂, 郭连波, 李阔湖, 曾庆栋, 李祥友, 任昭, 曾晓雁. 支持向量机算法在激光诱导击穿光谱技术塑料识别中的应用研究. 物理学报, 2013, 62(21): 215201. doi: 10.7498/aps.62.215201
[7]	赵永平, 张丽艳, 李德才, 王立峰, 蒋洪章. 过滤窗最小二乘支持向量机的混沌时间序列预测. 物理学报, 2013, 62(12): 120511. doi: 10.7498/aps.62.120511
[8]	范剑, 赵文礼, 王万强. 基于Duffing振子的微弱周期信号混沌检测性能研究. 物理学报, 2013, 62(18): 180502. doi: 10.7498/aps.62.180502
[9]	行鸿彦, 祁峥东, 徐伟. 基于选择性支持向量机集成的海杂波背景中的微弱信号检测. 物理学报, 2012, 61(24): 240504. doi: 10.7498/aps.61.240504
[10]	阎晓妹, 刘丁. 基于最小二乘支持向量机的分数阶混沌系统控制. 物理学报, 2010, 59(5): 3043-3048. doi: 10.7498/aps.59.3043
[11]	行鸿彦, 金天力. 基于对偶约束最小二乘支持向量机的混沌海杂波背景中的微弱信号检测. 物理学报, 2010, 59(1): 140-146. doi: 10.7498/aps.59.140
[12]	王校锋, 薛红军, 司守奎, 姚跃亭. 基于粒子群算法和OGY方法的混沌系统混合控制. 物理学报, 2009, 58(6): 3729-3733. doi: 10.7498/aps.58.3729
[13]	张军峰, 胡寿松. 基于多重核学习支持向量回归的混沌时间序列预测. 物理学报, 2008, 57(5): 2708-2713. doi: 10.7498/aps.57.2708
[14]	蔡俊伟, 胡寿松, 陶洪峰. 基于选择性支持向量机集成的混沌时间序列预测. 物理学报, 2007, 56(12): 6820-6827. doi: 10.7498/aps.56.6820
[15]	张家树, 党建亮, 李恒超. 时空混沌序列的局域支持向量机预测. 物理学报, 2007, 56(1): 67-77. doi: 10.7498/aps.56.67
[16]	叶美盈. 基于最小二乘支持向量机建模的混沌系统控制. 物理学报, 2005, 54(1): 30-34. doi: 10.7498/aps.54.30
[17]	叶美盈, 汪晓东, 张浩然. 基于在线最小二乘支持向量机回归的混沌时间序列预测. 物理学报, 2005, 54(6): 2568-2573. doi: 10.7498/aps.54.2568
[18]	崔万照, 朱长纯, 保文星, 刘君华. 基于模糊模型支持向量机的混沌时间序列预测. 物理学报, 2005, 54(7): 3009-3018. doi: 10.7498/aps.54.3009
[19]	刘涵, 刘丁, 任海鹏. 基于最小二乘支持向量机的混沌控制. 物理学报, 2005, 54(9): 4019-4025. doi: 10.7498/aps.54.4019
[20]	崔万照, 朱长纯, 保文星, 刘君华. 混沌时间序列的支持向量机预测. 物理学报, 2004, 53(10): 3303-3310. doi: 10.7498/aps.53.3303

计量

文章访问数: 5782
PDF下载量: 342
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

搜索

留言板