基于Volterra级数的核爆地震参数化非线性特征提取方法
|
摘要
地震时间序列的模型参数可以作为核爆地震信号识别的特征。现有基于ARMA(autoregressive moving average)模型参数的地震信号特征提取方法是一种线性方法,且只利用了信号的二阶统计信息,识别精度不高。为此,利用地震波的混沌特性,提出了一种核爆地震非线性特征提取方法:首先对地震波信号进行相空间重构,然后利用Volterra级数在重构的相空间内建立自适应预测模型,最后提取模型参数作为特征。在核爆地震分类实验中,非线性特征与线性特征相比,表现出更好的分类性能。研究结果表明:综合利用地震波信号的线性、非线性以及高阶统计信息对于核爆地震识别是非常重要的。
ARMA parameters can be used as features for discrimination between nuclear explosions and earthquakes.Current methods for feature extraction are linear and only takes advantage of the second-order statistic,so the classification accuracy of is not high.To solve this problem,a method for extracting nonlinear features of nuclear explosions and earthquakes was proposed based on the chaotic feature of seismic waves.Firstly,the phase space of seismic waves was reconstructed.Secondly,the adaptive prediction model based on Volterra series was established in the phase space.Finally,the model parameters were taken as the features of seismic samples.In the classification experiment of of nuclear explosions and earthquakes,nonlinear features obtained better performance than linear features.Investigated results show that the combination of linear,nonlinear and higher-order statistical information is critical for the classification of nuclear explosions and earthquakes.
ARMA parameters can be used as features for discrimination between nuclear explosions and earthquakes.Current methods for feature extraction are linear and only takes advantage of the second-order statistic,so the classification accuracy of is not high.To solve this problem,a method for extracting nonlinear features of nuclear explosions and earthquakes was proposed based on the chaotic feature of seismic waves.Firstly,the phase space of seismic waves was reconstructed.Secondly,the adaptive prediction model based on Volterra series was established in the phase space.Finally,the model parameters were taken as the features of seismic samples.In the classification experiment of of nuclear explosions and earthquakes,nonlinear features obtained better performance than linear features.Investigated results show that the combination of linear,nonlinear and higher-order statistical information is critical for the classification of nuclear explosions and earthquakes.
引文
[1]Hafemeister D.Progress in CTBT monitoring since its 1999 senate defeat[J].Science and Global Security,2007,15:151-183.
[2]Sakkalis V,Cassar T,Zervakis M,et al.Parametric and nonparametric EEG analysis for the evaluation of EEG activity inyoung children with controlled epilepsy[J].Computational Intelligence and Neuroscience,2008,doi:10.1155/2008/462593.
[3]Carden E P,Brownjohn J M W.ARMA modelled time-series classification for structural health monitoring of civil infra-structure[J].Mechanical Systems and Signal Processing,2008,22(2):295-314.
[4]李夕海,刘刚,刘代志,等.基于最近邻支撑向量特征线融合算法的核爆地震识别[J].地球物理学报,2009,52(7):1816-1824.LI Xi-hai,LIU Gang,LIU Dai-zhi,et al.Discrimination of nuclear explosions and earthquakes using the nearest supportvector feature line fusion classification algorithm[J].Chinese Journal of Geophysics,2009,52(7):1816-1824.
[5]Arrowsmith M D,Arrowsmith S J,Stump B W,et al.A suite of discriminants for ground-truth mining events in the west-ern US and its implications for discrimination capability in Russia[C]∥Proceedings of 2008 Monitoring Research Review:Ground-Based Nuclear Explosion Monitoring Technologies.Portsmouth,Virginia,USA,2008:544-553.
[6]Benbrahim M,Benjelloun K,Ibenbrahim A,et al.A new approaches for seismic signals discrimination[J].Proceedingsof World Academy of Science,Engineering and Technology,2007,21:183-186.
[7]Piotr F,Hernando O.Consistent classification of non-stationary time series using stochastic wavelet representations[J].Journal of the American Statistical Association,2009,104(485):299-312.
[8]Cercone J A,Foster V S,Clark W M.Application of neural networks to seismic signal discrimination research findings[R].PL-TR-94-2122,1994.
[9]邢贞贞,韩立国,王宇,等.高阶统计量方法在地震信号分析中的应用[J].吉林大学学报(地球科学版),2007,37增刊:139-142.XING Zhen-zhen,HAN Li-guo,WANG Yu,et al.Application of higher-order statistics in seismic signal analysis[J].Journal of Jilin University(Earth Science Edition),2007,37 suppl:139-142.
[10]Liu D,Red S,Wei Y,et al.Attractor analysis and its applications to seismic pattern recognition of nuclear explosion[C]∥3rd International Conference on Signal Processing.Beijing,China,1996:1324-1329.
[11]刘代志,邹红星,韦荫康,等.分形分析与核爆地震模式识别[J].模式识别与人工智能,1997,10(2):153-158.LIU Dai-zhi,ZOU Hong-xing,WEI Yin-kang,et al.Fractal analysis with applications to seismic pattern recognition ofnuclear explosion[J].Pattern Recognition and Artificial Intelligence,1997,10(2):153-158.
[12]Kalli R R.Nonlinear modeling of radio frequency circuits to estimate third-order nonlinear distortions[D].Florida:Flor-ida International University,2008.
[13]许小可.海杂波的非线性分析与建模[D].大连:大连海事大学,2007.
[2]Sakkalis V,Cassar T,Zervakis M,et al.Parametric and nonparametric EEG analysis for the evaluation of EEG activity inyoung children with controlled epilepsy[J].Computational Intelligence and Neuroscience,2008,doi:10.1155/2008/462593.
[3]Carden E P,Brownjohn J M W.ARMA modelled time-series classification for structural health monitoring of civil infra-structure[J].Mechanical Systems and Signal Processing,2008,22(2):295-314.
[4]李夕海,刘刚,刘代志,等.基于最近邻支撑向量特征线融合算法的核爆地震识别[J].地球物理学报,2009,52(7):1816-1824.LI Xi-hai,LIU Gang,LIU Dai-zhi,et al.Discrimination of nuclear explosions and earthquakes using the nearest supportvector feature line fusion classification algorithm[J].Chinese Journal of Geophysics,2009,52(7):1816-1824.
[5]Arrowsmith M D,Arrowsmith S J,Stump B W,et al.A suite of discriminants for ground-truth mining events in the west-ern US and its implications for discrimination capability in Russia[C]∥Proceedings of 2008 Monitoring Research Review:Ground-Based Nuclear Explosion Monitoring Technologies.Portsmouth,Virginia,USA,2008:544-553.
[6]Benbrahim M,Benjelloun K,Ibenbrahim A,et al.A new approaches for seismic signals discrimination[J].Proceedingsof World Academy of Science,Engineering and Technology,2007,21:183-186.
[7]Piotr F,Hernando O.Consistent classification of non-stationary time series using stochastic wavelet representations[J].Journal of the American Statistical Association,2009,104(485):299-312.
[8]Cercone J A,Foster V S,Clark W M.Application of neural networks to seismic signal discrimination research findings[R].PL-TR-94-2122,1994.
[9]邢贞贞,韩立国,王宇,等.高阶统计量方法在地震信号分析中的应用[J].吉林大学学报(地球科学版),2007,37增刊:139-142.XING Zhen-zhen,HAN Li-guo,WANG Yu,et al.Application of higher-order statistics in seismic signal analysis[J].Journal of Jilin University(Earth Science Edition),2007,37 suppl:139-142.
[10]Liu D,Red S,Wei Y,et al.Attractor analysis and its applications to seismic pattern recognition of nuclear explosion[C]∥3rd International Conference on Signal Processing.Beijing,China,1996:1324-1329.
[11]刘代志,邹红星,韦荫康,等.分形分析与核爆地震模式识别[J].模式识别与人工智能,1997,10(2):153-158.LIU Dai-zhi,ZOU Hong-xing,WEI Yin-kang,et al.Fractal analysis with applications to seismic pattern recognition ofnuclear explosion[J].Pattern Recognition and Artificial Intelligence,1997,10(2):153-158.
[12]Kalli R R.Nonlinear modeling of radio frequency circuits to estimate third-order nonlinear distortions[D].Florida:Flor-ida International University,2008.
[13]许小可.海杂波的非线性分析与建模[D].大连:大连海事大学,2007.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心