用户名: 密码: 验证码:
水声信号处理的盲信号分离方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
水声被动信号处理中,往往由于实际水声环境复杂多变,干扰和噪声又难以确定,由水听器(或水听器阵)直接观测到的信号,大多是多源目标信号经多途传输后在接收点叠加并与干扰背景噪声(海洋环境噪声)混合的一种复杂信号,严重影响着后期的目标定位、检测、识别等方面的性能和精度。盲信号处理技术可以无需源信号先验知识而仅仅利用接收信号和某些统计假设条件获取期望信息,比较适合应用于水声被动信号处理,盲信号分离技术作为其中一个重要分支内容,它的目标是获得多个源信号的最佳估计,在需要准确获得水下目标的真实源信号时具有重要应用需求。论文主要研究内容包括三方面:欠定情况下源数目估计方法;单波束信号内多源信号的盲分离方法及含噪波束信号的净化方法;适合单矢量传感器的盲信号分离方法。
     实现盲信号有效分离的前提条件是源数目的准确估计,所以论文首先研究了源数目的估计问题。众多的源数目估计方法中,盖尔圆(GDE)准则法既适用于高斯白噪声背景,又适用于色噪声背景,具有重要的应用价值。但传统GDE准则法存在一定的弊端:低信噪比或者小快拍数条件下的检测性能不尽如人意,而且需要人为确定调整因子。论文在传统GDE准则基础上提出了一种改进盖尔圆准则(MGDE)方法,该方法主要利用盖尔圆圆心信息压缩盖尔圆半径,使噪声盖尔圆进一步远离信号盖尔圆,从而更有利于低信噪比或者小快拍数条件下源数目的准确估计;同时,针对GDE准则设计中存在人为确定调整因子的问题,论文设计了一种由盖尔圆信息自动确定调整因子的方法,GDE准则使用该调整因子,不但检测性能得到改善,而且避免了人为因素的影响。
     欠定条件下源数目估计问题是盲信号分离问题中的难点之一,论文选用相空间重构法拓展观测信号个数,将欠定条件转换为超定条件。原相空间重构法只能增加与阵元数目相同的重构信号,针对这一局限,给出了可重构多个信号的改进相空间重构方法,使用该方法,并结合适当的源数目估计方法可以从单阵元信号中正确估计大于两个源的数目。
     许多水声信号处理方法和理论都建立在高斯噪声模型基础上,多数情况下这种假设是合理有效的,但研究表明:水声环境噪声、舰船辐射噪声等常常具有α稳定分布(α-Stable Distribution)的特性:其概率密度函数具有比较厚重的拖尾,表现在时间波形上就是具有显著的脉冲特性,这种情况下基于高斯噪声模型的处理算法性能退化,甚至不能得到正确结果。针对这一情况,论文初步探讨了服从α稳定分布的随机向量的源数目估计和DOA估计问题。一方面提出使用协共变矩阵代替协方差矩阵,从而实现超定源数目估计,并仿真验证了源数目估计性能;另一方面:对二维单矢量水听器的振速向量采用经验函数法和投影法两种谱测度估计方法进行源数目估计和DOA估计,仿真表明:前者只能实现单个声源的DOA估计,后者可以实现多源的数目估计和DOA估计。
     论文使用盲信号分离的手段进一步对波束信号进行分析处理,目的是解决两方面问题:一是分离波束内来自同一方位、或者相互靠得很近的多个源信号;二是进一步净化含有噪声的波束信号,因为仅仅依靠波束形成无法实现这样的目的。论文首先从增加波束域信号维数的角度,主要运用相空间重构法对波束域信号升维;然后在最大化负熵的基础上,推导了最小化边缘熵准则,给出了基于概率密度估计的独立边缘熵计算方法,以该最小化边缘熵为分离准则,采用正定盲分离技术进一步分离或净化单波束信号。研究表明:将盲信号分离技术用作波束形成的后置信号处理方法是合理有效的,它既可以辅助波束形成法分离波束内来自同一方位、或相互靠得很近的多个源信号,也可以对含有噪声的单源波束信号进行净化处理。另外,从盲信号分离的角度考虑,将其与波束形成法结合,可以减小盲分离算法的阶数,降低盲分离算法的复杂度。
     使用盲信号分离技术从单矢量水听器接收信号中准确获知多个目标的参数信息,是近几年兴起的研究课题。为此,论文根据矢量水听器观测信号的特点,给出了两种适合单矢量水听器的盲信号分离方法——基于混合矩阵的盲分离方法和基于二阶统计量的解析方程法,这两种方法都可以实现非相干源信号分离和DOA估计,仿真分析了算法的性能和各种影响因素。
In passive underwater acoustics signal processing, observed directly signals from thehydrophone (or hydrophone array) are a complex mixture signal which is a superposition ofmulti-sources via multipath propagation and interference noise or ocean backgroundnoise,because the actual acoustic environment is complex and changeable, interference andnoise are also difficult to be determined. Those affect seriously the performance and accuracyof target location, the detection and identification. Blind signal processing technology issuitable for application in passive underwater acoustic signal processing, because it can onlymake use of received signals and some statistical assumptions to gain expected information,without prior knowledge of source signals. The goal of blind separation as one of theimportant branches is to get the best estimation of multiple source signals, so blind separationtechnology has great application value in the many fields with the need to get the accurateunderwater source signals. The paper includes three main research contents.These areestimation method about the number of source under under-determined condition, blindmulti-source separation method from single beam signal or purification method in the light ofnoisy beam signal, and blind signal separation method suitable for single vector sensor.
     A prerequisite realizing blind signal separation is the accurate estimation of sourcenumbers, so the paper studies estimation problem of source number. In many estimationmethods, Gerschgorin Criterion method has important application value, because it can applyto both the Gauss white noise background and colored noise background. But the traditionalGDE criterion method has some disadvantages. Detection performance is not just as onewishes under low SNR condition or a small number of snapshots, and adjustment factor needto determine by people. According to this, a modified method of Gerschgorin radii wasintroduced based on the original Gerschgorin Criterion method. That modified method(MGDE) lessened independently Gerschgorin radii using center information of Gerschgorincircle in order to compression speed of noise Gerschgorin radii faster than that of signalGerschgorin radii, so the noise Gerschgorin disks could be kept as remote from the signalGerschgorin disks as possible. Therefore, the source number could be easily determined underlow SNR condition or a small number of snapshots. Meanwhile, in view of the existingproblems which adjustment factor need to determined by people, this paper proposes amethod, in which can determine automatically the adjustment factor by Gerschgorin disksinformation. And GDE criterion not only improved the detection performance but also avoiding the influence of artificial factors through use of proposed adjustment factor.
     Source number estimation problem under under-determined condition is one of thedifficulties in blind signal separation problem.According to this, we convert under-determinedcondition into overdetermined conditions by phase space reconstruction method to expand theobserved signal dimensions.For limiting of phase space reconstruction method can onlyreconstruct a signal, we will present a modified phase space reconstruction method which canreconstruct multiple times signals by modifying the original method.We can estimationcorrectly the number of sources more than2from single array signal combining with theappropriate source number estimation method.
     A lot of methods and theory of underwater acoustic signal processing are establishedbased on the Gauss noise model.In most cases, this assumption is reasonable and effective.But research show: acoustic environment noise and warship radiated noise often haveα-stable distribution characteristics. Probability density function has a relatively thick tail,that is In time waveform they have significant pulse characteristics.So algorithmsperformance degrade based on the Gauss noise models, even it can't get the right result. Inview of this situation, the paper initially explores source number estimation and DOAestimation of random vector obeying to α-stable distribution. On the one hand sourcenumber is estimated using diagonal covariance matrix instead of the covariance matrix, andthe simulation results verify the source number estimation performance.On the other hand,wemake use of two spectral measure(empirical function method and the projection method) toestimate the number of sources and DOA. The former can only achieve single sound sourceDOA estimation. The latter can realize DOA estimation of multi-sources.
     This paper make use of blind signal separation means to analyze and process furtherbeam signal. The purposes are to solve the two aspects problems because rely solely onbeamforming cannot achieve these objectives. One is that more source signals can be separatefrom single beam signal, when they come from the same direction, or they are closer eachother. The other is the beam signal can be purified further containing noise. From the aspectof increasing signal dimensions in this paper, phase space reconstruction method is used toincrease signal dimensions. Then the determined blind separation technology further can beadopted to separate or purified single beam signal.Research show: it is reasonable andeffective that blind signal separation technology be used as post signal processing method ofbeamforming. It can not only separate more source signals from single beam signal when theycome from the same direction or they are closer each other, but also clear beam signalpolluted by noises. In addition, from the point of view of blind signal separation, it can reduce orders of blind separation algorithm, and reduce the complexity of the algorithms.
     It is a new hot research topic in recent years that parameter informations of multipletargets can be obtained accurately from signal of a single vector hydrophone using blindseparation technology. Therefore, two blind separation methods are propose based on thevector hydrophone signal characteristics. They are blind separation method based on hybridmatrix and blind separation method based on two order statistics analytic equation method.They are suitable for noncoherent source.And simulations analyzed performance and affectionfactors of separation algorithm.
引文
[1] Herault J,Jutten C.Space or time adaptive signal processing by neural networkmodels[J].International Conference on Neural Networks for Computing,Snowbird,USA.1986:206-211
    [2] Herault J,Jutten C.Blind separation of sources.PartⅠ:an adaptive algorithm basedon neuromimetic architecture[J].Signal Processing.1991;24(1):1-10
    [3] Comon P.Blind separation of sources,PartⅡ:Problem statement.Signal Processing[J].1991,24(1):11-20
    [4] Sorouchyari E.Blind separation of sources,Part Ⅲ:Stability Analysis[J].SignalProcessing,1991,24(1):21-29
    [5] Comon P.Independent component analysis,a new concept?[J].Signal Processing,1994,36(3):287-314
    [6] Cichocki A,Unbehauen R,Rummert E.Robust learning algorithm for blind separationof signals[J].Electronics Letters.1994,30(17):1386-1387
    [7] Bell A J,Sejnowski T J.An information-maximization approach to blind separation andblind deconvolution[J].Neural Computation.1995,7(1):1129-1159
    [8] Tuan P D.Blind separation of mixture of independent source through a quasi-maximumlikelihood approach[J].IEEE Transaction on Signal Processing.1997,45(7):1712-1725
    [9] Theis F J,Bauer C,Elmar W L.Comparison of maximum entropy and minimal mutualinformation in a nonlinear setting[J].Signal Processing,2002,82(7):971-980
    [10] Amari S,Cichocki A,Yang H H.A new learning algorithm for blind signalseparation[J].In Advance in Neural Information Processing Systems,Cambridge:MA,MIT Press,1996,8:657-663
    [11] Yang H,Amari S.Adaptive online learning algorithms for blind separation:maximumentropy and minimum mutual information[J].Neural Computation,1997,9:457-1482
    [12] Karhunen J,Joutsensalo J.Representation and separation of signals using nonlinear PCAtype learning[J].Neural Networks,1994,7:113-127
    [13] Matsuoka K.A neural net for blind separation of nonstationary signals[J].NeuralNetwork,1995,3:311-419
    [14] Amari SI,Cichocki A,Yang H H.A New Learning Algorithm for Blind SignalSeparation[J].In Advance in Neural Information Processing Systems1996,8:757-763
    [15] Cardoso J F,Laheld B.Equivariant adaptive source separation[J].IEEE Trans.on SignalProcessing.1996,44(12):3017-3030
    [16] Oja E,Karhunen J,Wang L ec.Principle and independent components in neuralnetworks-Recent developments[A].In Proc7th Italian Workshop Neural Networks,WIRN’95Vietri,Italy,1995:20-26
    [17] Girolami M,Fyfe C.Kurtosis extrema and identification of independent components:a neural network approach[A].In Proc.ICASSP’97[C],1997,4:3329-3333
    [18] Hyv rinen A.and Oja E.A Fast Fixed-Point Algorithm for Independent ComponentAnalysis[J].Neural Computation.1997,9(7):1483-1492
    [19] Amari S,Cichocki A.Adaptive blind signal processing-neural network approaches[J].Processing of the IEEE,1998,86(10):2026-2046
    [20] Cardoso J F.Blind signal separation:statistical principles[J].Processing of the IEEE,1998,86(10):2009-2025
    [21] Hyv rinen A.Fast and Robust Filed-Point Algorithms for Independent ComponentAnalysis[J].IEEE Transactions on Neural Networks1999,10(3):626-634
    [22] Hesse C W,James C J.The FastICA algorithm with spatial constaints[J].IEEEsignalprocessing letters.2005,12(11):792-795
    [23] Zbynek K,Petr T,Oja E.Efficient variant of algorithm fastICA for independentcomponent analysis attaining the cramer-rao lower bound[J].IEEE trans on neuralnetworks.2006,17(8):1256-1277
    [24] Warrender C,Forrest S,Pearlmutter B.Detecting in trusions using system calls:alternative data models[J].1999IEEE Symposium on Security and Privacy,Oakland,USA,1999:133-145
    [25] Valpola H.Nonlinear independent component analysis using ensemeble learning:Theory[A].In:Proc.ICA2000[C],Helsinki,Finland,2000,251-256
    [26] Valpola H,Giannakopoulos X,Honkela A.Nonlinear independent component analysisusing ensemeble learning:Experiments and discussion[A].In:Proc.ICA2000[C],Helsinki, Finland,2000,251-256
    [27] Cho K S,Lee S Y.Implementation of informax ICA algorithm with analog CMOScircuits[A].In:Proc.ICA2001[C],San,Diego,USA,2001,70-73
    [28] Cardoso J F,Delabrouille J,Patanchon G.Independent component analysis of the cosmicmicrowave background[A].In:Proc.ICA2003[C],Nara,Japan,2003,1111-1116
    [29] Yuan Z J,Oja E.A fastICA algorithm for non-negative independent componentanalysis[A].In:Proc.ICA2004[C],Granada,Spain,2004,1-8
    [30]汪军,何振亚.瞬时混叠信号盲分离[J].电子学报,1997,25(4):1-5
    [31]汪军,何振亚.卷积混叠信号盲分离[J].电子学报,1997,25(7):7-11
    [32]刘据,梅良模,何振亚.一种盲源分离的信息理论方法[J].山东大学学报,1998,33(4):398-403
    [33]刘据,顾明亮,何振亚.一种新的瞬时混迭信号盲源分离的自适应方法[J].电路与系统学报.1998,3(4):66-71
    [34]王惠刚,马远良.水声信号源的盲分离原理及自适应算法[J].1998全国声学学术会议论文集,成都科技大学出版社,1998
    [35]张贤达.盲信号处理几个关键问题的研究[J].深圳大学学报理工版,2004,21(3):196-200
    [36]张贤达,保铮.盲信分离[J].电子学报,2001,29(12A):1766-1771
    [37]谢胜利,谭北海,傅予力.基于平面聚类算法的欠定混叠盲信号分离[J].自然科学进展,2007,17(6):795-800
    [38]谭北海,杨祖元,周郭许等.欠定盲分离中源的个数估计和分离算法[J].中国科学F辑:信息科学,2009,39(3):349-356
    [39]刘琨,杜利民,王劲林.基于时频域单源主导区的盲源欠定分离方法[J].中国科学(E辑),2008,38(8):1284-1301
    [40]孙晖,朱善安.调制故障源信号盲分离的经验模态分解法[J].浙江大学学报(工学版),2006,40(2):258-261
    [41]李志农,吕亚平,范涛等.基于经验模态分解的机械故障欠定盲源分离方法[J].航空动力学报,2009,24(8):1886-1892
    [42]王惠刚,马远良.水声信号源的盲分离原理及自适应算法[C].98全国声学学术会议论文集,成都科技大学出版社,1998,9
    [43]章新华,张安清.信号源数目估计的盲估计方法[C].声纳技术研讨会论文集,声纳技术国防科技重点实验室主办,杭州,2000,120-123
    [44]倪晋平,马远良,孙超等.用独立成份分析算法实现水声信号盲分离[J].声学学报,2002,27(4):321-326
    [45]倪晋平,马远良,杨坤德.水声信号盲分离的实数算法与复数算法[J].西北工业大学学报,2002,20(1):44-484
    [46]倪晋平,马远良,孙超等.基于峰度自然对数最大化的信号盲分拣算法和盲波束形成[J].电子与信息学报,2003,25(2):187-194
    [47]张安清,章新华.基于信息理论的舰船噪声盲分离算法[J].系统工程与电子技术.2003,25(9):1058-1060
    [48]张安清,章新华,邱天爽等.基于线谱点的一种频域盲分离方法[J].系统工程与电子技术.2006,28(9):1307-1310
    [49]李军,章新华,王凯等.基于高阶统计的水声信道盲辨识[J].应用声学.2009,28(1):42-46
    [50]张安清,邱天爽,章新华.基于盲均衡的水声信号波形恢复[J].信号处理,2003:297-300
    [51]康春玉,章新华,韩东.一种基于盲源分离的DOA估计方法[J].自动化学报,2008,34,(10):1324-1326
    [52]康春玉,章新华,韩东.盲源分离与高分辨融合的DOA估计与信号恢复方法[J].自动化学报,2010,36,(3):442-445
    [53]章新华,范文涛,康春玉等.波束形成与独立分量分析融合的宽带高分辨方位估计方法[J].声学学报,2009,34,(4):303-310
    [54]许策,赵相霞,章新华等.混响背景下主动声纳接收信号的可分离性探讨[J].声学技术.2010,6,29(3):310-327
    [55]张之猛.一种水声多途信号的快速盲解卷积算法[J].数据采集与处理.2009,24(2):134-139
    [56] K.G.Sabra and D.R.Dowling:Blind deconvolution in ocean waveguides usingartificial time reversal J.Acoust.Soc.Am.2004,116(1):262-271
    [57]姜卫东,陆佶人,张宏滔.基于单个频点的水声信号盲源分离[J].电子与信息学报.2006,27(3):32-36
    [58]岳剑平,王德俊,惠俊英等.单矢量传感器的互谱估计与方位估计.哈尔滨工程大学学报,2004,25(3):299-304
    [59]马建仓,牛奕龙,陈海洋.盲信号处理[M].北京:国防工业出版社,2006
    [60] Wax M,Kailath T.Detection of signals by information theoretic criteria[J].IEEE TransASSP,1985,33(2):387-392.
    [61] He Haimin.The application research of underwater acoustic source numbers estimationby blind separation algorithm[C].Proceedings-2009International Conference onComputational Intelligence and Software Engineering,2009,1-4
    [62] Eran Fishler,Michael Grosmann,Hagit Messer.Detection of signals by informationtheoretic criteria:general asymptotic performance analysis[J].IEEE Transaction onsignal processing,2002,50(5):1027-1036
    [63] Q T Zhang,K M Wong P C Yip.Statistical analysis of the performance of informationtheoretic criteria in the detection of the number of signals in array processing[J].IEEETrans Acoust Speech Signal Processing,1989,37:1557-1567
    [64] Q T Zhang,K M Wong P C Yip.Statistical analysis of the performance of informationtheoretic criteria in the detection of the number of signals in array processing[J].IEEETrans Acoust Speech Signal Processing,1989,37:1557-1567
    [65]谢纪岭,司锡才.基于协方差矩阵对角加载的信源数估计方法[J].系统工程与电子技术,2008,30(1):46-49
    [66] Wu H T,Yang J F,Chen F K.Source number estimation using transformed Gerschgorinradii[J].IEEE Transactions on Signal Processing,1995,43(6):1325-1333
    [67] Wu H T,Chen F K.A new Gerschgorin radii method for Source number estimation[C].Proc10th IEEE2000:104-107
    [68] Zhong Zhi-feng,Wen Bi-yang,Wang Qian-de et al. A new method using Gerschgorindisks for source number estimation[J].Proceding of the third international conference onmachine learning and cybernetics,2004:26-29
    [69] Wu H T,Chen F K.A new Gerschgorin radii method for source number estimation[C].Proc10th IEEE2000:104-107
    [70] Yiwang Huang,Qunyan Ren,Ting Li.A geometric model for the spatial correlation ofan acoustic vector field in surface-generated noise[J].Journal of Marine Science andApplication,2012,11(1):119-125
    [71]李元峰,赵玫.基于奇异谱分析的混沌序列降噪[J].上海交通大学学报,2003,37(5):778-780
    [72] Gabriel B M,Gilmore R.Topological analysis and synthesis of chaotic time series[J].Physica D,1992,58:229-242
    [73]张小明,刘建敏,乔新勇.时间序列关联维数快速算法及实现.装甲兵工程学院学报,2007,21(6):58-61
    [74]张淑清,贾健,高敏等.混沌时间序列重构相空间参数选取研究.物理学报,2010,59(3):1576-1582
    [75]吕金虎,陆君安,陈士华.混沌时间序列分析及其应用[M].武汉大学出版社,2002.
    [76]申永军,杨绍普,孔德顺.基于奇异值分解的欠定盲信号分离新方法及应用[J].机械工程学报,2009,45(8):64-70
    [77]任云,吴立新,李整林等.南中国海存在孤立子内波条件下的声场时间相关半径[J].声学学报,2010,35(5):515-522
    [78]邱天爽,张旭秀,李小兵等.统计信号处理-非高斯信号处理及其应用[M].电子工业出版社,2004,6
    [79] G A Tsihrintzis,C L Nikias.Data-adaptive algorithm for signal detection in sub-Gaussian impulsive interference[J].IEEE Trans on Signal Processing,45(7):1997,1873-1878
    [80]孙永梅,邱天爽.α稳定分布噪声下自适应信号处理的研究进展[J].信号处理,2004,20(6):618-622
    [81] Xinyu Ma,Chrysostomos L Nikkias.Parameter Estimation and channel identification inimpulsive signal enxironments[J].IEEE Transactions on signal processing,1995,43(12):2884-2897
    [82]查代奉.基于稳定分布白噪声的信号处理新方法研究[C].大连理工大学,2006:8-13
    [83]李旭涛.Alpha稳定分布模型及其应用研究[D].华中科技大学博士学位论文,2006
    [84] M.Shao,C L Nikias.Signal processing with fractional lower order moments:Stableprocesses and their applications.Proceedings of the IEEE,1993,81(7):986-1010
    [85] C L Nikias, M Shao.Signal Processing with Alpha-Stable Distribution andapplication[J].New York:John Wiley&Sons,Inc,1995
    [86] G Samorodnitsky,M S Taqqu. Stable non-Gaussian random processes[M].Chapman&Hall,1994
    [87]郭文强,邱天爽,查代奉.基于Borel测度峰值判定的欠定混合盲语音信号分离[J].通信学报,2007,28(9):22-26
    [88] J.Huston Mcculloch.Estimation of the bi-variate stable spectral representation by theprojection method[J].Computational Economics,2000,16:47-62
    [89] J.P.Nolan,A.K.Panorska,J.H.Mcculloch.Estimation of stable spectralmeasures[J].Athematical and computer modeling.2001,34:1113-1122
    [90] Hardin Clyde D,Samorodnitsky Gennagy,Taqqu Murad S.Nonlinear regression ofstable random variables[J].Annals of Applied Probability,1991,1:582-612
    [91]董姝敏,梁国龙,付进.基于α分布的单矢量传感器多目标方位估计.计算机工程,2010,37(11):267-268
    [92]李旭涛.Alpha稳定分布模型及其应用研究[M].华中科技大学,2006
    [93] Ali Mansour,Christian Jutten,Philippe Loubaton.Adaptive subspace algorithm for blindseparation of independent sources in convolutive mixture[J].IEEE Transactions onSignal processing,2000,48(2):583-586
    [94]华容,苏中义.基于遗传算法过程信号的盲分离[J].上海交通大学学报,2001,35(2):319-322
    [95] Bai L,Huang X.Observer-based beamforming algorithm for acoustic array signalprocessing[J].Acoust Soc Am,2011,130(6):3803
    [96]杨益新,孙超.波束域加权子空间拟合算法[J].声学学报,2000,25(2):142-145
    [97] Zhang,Youwen;Sun,Dajun;Zhang,Dianlun, Robust adaptive acoustic vector sensorbeamforming using automated diagonal loading[J].Applied Acoustics,2009,70(8):1029-1033
    [98] Ning LI,Yan GUO,Qi-Hui WU.DOA estimation methods based on covariancedifferencing under a colored noise environment[J],2011,E94-B(3):735-741
    [99]赵永波,张守宏.存在相干信号时的最优波束形成[J].通信学报,2002,23(2):113-121
    [100]张安清,邱天爽.波束域的信号盲分离方法[J].系统工程与电子技术,2008,30(9):1628-1631
    [101]冯西安,严胜刚,黄建国.宽带波数域高分辨方位估计的阵增益分析[J].鱼雷技术,2006,14(1):43-46
    [102]王英志,章新华,范文涛.一种波束域子带盲源分离新方法[J].计算机应用,2008,28(11):2987-2990
    [103] Te-Won Lee,Michael S.Lewicki, Terrence J.Sejnowski.Blind source separationof more sources than mixtures using overcomplete representations[J].IEEE SignalProcessing Letters,1999,6(4):87-90
    [104]谢胜利,何昭水,傅予力.基于稀疏元分析的欠定混叠自适应盲分离方法[J].中国科学E辑:信息科学,2007,37(8):1086-1098
    [105]范志攀;吴瑛;韩昭;张莉;恒模特性在DOA中的新应用及其克拉美-罗界研究[J].现代雷达,2005,57-62
    [106]邱天爽,毕晓辉.稀疏分量分析在欠定盲源分离问题中的研究进展及应用[J].信号处理,2008,24(6):966-970
    [107]范文涛,章新华,徐莉.波束域盲源分离与MUSIC融合的方位估计算法[J].声学技术,2008,27(5):446-447
    [108]侯颖妮,黄建国,冯西安.基于多波束系统的波数域方位估计方法研究[J].弹箭与制导学报,2007,27(3):80-83
    [109]陈希儒,柴跟象.非参数统计教程[M].上海:华东师范大学出版社,1993,247-255
    [110]董姝敏,李尧,乔双.适合盲提取的自适应遗传算法.计算机工程与应用,2010,46(18):142-145
    [111]姚直象,惠俊英,殷敬伟等.基于单矢量水听器四种方位估计方法[J].海洋工程,2006,24(1):122-128
    [112]岳剑平,王德俊,惠俊英等.单矢量传感器的互谱估计与方位估计[J].哈尔滨工程大学学报,2004,25(3):299-304
    [113]CHOI S,CICHOCKI A,PARK H M,et al.Blind source separation and independentcomponent analysis:a review[J].Neural Information Processing-Letters and Reviews,2005,6(1):1-57
    [114]Diamantaras K I,Papadimitriou T.Applying PCA neural models for the blind separationof signals[J].Neural Computing,2009,73:3-9
    [115]BELL A J,SWJINOWSKI T J.An information maximization approach to blindseparation and blind deconvolution[J].Neural Computation,1995,7(6):1129-1159
    [116]马建仓,牛奕龙,陈海洋.盲信号处理[M].北京:国防工业出版社,2006
    [117]杨士莪.单矢量传感器多目标分辨的一种方法[J].哈尔滨工程大学学报,2003,24(6):591-595
    [118]惠俊英,惠娟.矢量声信号处理基础[M].北京:国防工业出版社,2009

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700