独立分量分析算法及其在多用户检测中的应用
|
摘要
独立分量分析(ICA)作为统计信号处理和神经网络等领域的新方法,因具有优异的盲辨识、特征提取和表示能力,已经日益广泛地应用于通信、语音提取、图像增强和医学信号处理等领域。码分多址(CDMA)信号模型与ICA模型形式相似,将ICA适用于多用户检测问题,直接从期望用户的观测数据出发,利用ICA可以将用户信息序列从被多址干扰(MAI)污染的混合信号中分离出来。本文的主要工作如下:
1.利用矩阵理论推导了独立分量分析的克拉美罗性能界。克拉美罗性能界是估计理论中无偏参数估计方差的下界,是评价参数估计性能最常用的度量。基于瞬时ICA模型推导了分离矩阵W的Fisher信息矩阵。为了准确衡量算法的分离精度,定义了增益矩阵G,并推导了关于G的克拉美罗性能界。克拉美罗性能界为独立分量分析算法性能评价提供了一种衡量准则。
2.提出了广义高斯变量生成算法和自适应的FastICA算法。基于伽玛分布随机变量,综合运用随机变量变换法和舍选抽样法,提出了一种简便的广义高斯分布随机变量生成算法。该算法计算简单,通过调整分布参数的值,可产生具有任何形状参数和任何方差的广义高斯分布随机变量。为了克服传统FastICA算法中要依据先验信息选定合适的非线性激活函数的缺点,提出了一种自适应FastICA算法。该算法基于广义高斯模型,通过高斯模型的形状参数的优化和分离矩阵迭代结合,实现了激活函数向源信号评价函数的逼近,可以同步实现不同类型源信号的估计。并给出了算法的稳定性分析和仿真实验。
3.提出了非参数广义高斯核ICA算法。当参数ICA算法不能分离信号时,基于广义高斯核函数,提出了非参数广义高斯核ICA算法。它在源信号密度函数全“盲”情况下,能实现正确分离,解决了如何选取估计信号评价函数的难题,可用于任意分布的源信号。广义高斯核函数可以根据源信号的高阶统计自适应地改变窗宽以适应不同源信号的要求。
4.提出了基于负熵准则的FastICA盲多用户检测算法。该算法使用四次幂函数,把基于负熵的非高斯性测度转化为信号峰度的形式,降低了计算量。同时,算法充分考虑了各用户信号的统计独立性,在下行链路干扰用户的扩频码未知情况下,把目标用户的扩频码作为训练序列,并用于初始化FastICA算法的分离向量,使用随机梯度法进行优化计算,获得了优异的符号估计性能。对算法的计算复杂度的分析可以看出,计算量随着接收数据长度和用户数的增加而增加。在同步CDMA信道中与传统匹配滤波器、MMSE检测算法比较,MAI较低的时该算法检测性能与MMSE的性能接近;随着MAI增加,其性能明显优于MMSE算法。
5.提出了基于非参数似然比准则的盲多用户算法。当建立的概率密度模型不准确时,参数ICA算法算法有时不能分离源信号,为此,提出了非参数ICA的检测算法。直接由观测信号样本出发,使用高斯核函数估计分离信号的概率密度函数,计算非参数似然函数比,结合梯度下降法和似然比准则进行目标用户的信号检测。通过试验仿真,与其它算法比较,结果表明该算法抑制多址干扰的能力介于FastICA检测和MMSE检测之间。
Independent component analysis(ICA) is a new method in statistical signal processing and neural networks.As a result of its outstanding performance in blind identification and feature extraction or representation,ICA has been used wildly in various fields,for instance,communication systems,speech processing,image enhancement,and biomedical signal processing.Because the linear ICA model has the same form as the CDMA signal model,it can be used in multi-user detection.Utilizing ICA,the desired user information sequence can be separated from the mixture signals polluted by MAI.The main research works of this paper are presented as follows:
1.The Cramer-Rao lower bound of ICA is established.Cramer-Rao lower bound is the variance lower bound of unbiased parameters estimation in estimation theory and the common measurement of evaluation performance of parameters estimation.A detail derivation of the Fisher information matrix for demixing matrix w is provided. Gain matrix G is defined,which can give the accuracy measurement of the estimation of the original signals.Cramer-Rao lower bound for gain matrix is deduced in the end and can give a general performance criterion for independent component analysis.
2.Algorithm for generating generalized Gaussian distribution random variable and adaptive FastlCA algorithm are proposed.In order to simply create random variables of generalized Gaussian distribution with any shape parameter and any variance,an algorithm is proposed by combining transformations of random variable method and abandon-selection sampling method.The algorithm is derived by proper transformations based on gamma distribution random variables.The algorithm is computationally simple.Random variables of generalized Gaussian distribution with any shape parameter and any variance can be generated easily by adjusting the numerical values of these parameters.Different from traditional FastICA algorithms where the activation function is pre-designed by prior knowledge and fixed for all sources even in different types,an adaptive FastlCA algorithm is presented based on the generalized Gaussian model where the iterations for the paracmeters of the generalized Gaussian and the demixing vector are combined.The stability analysis is also given as well as computer simulation demonstrations.
3.Nonparametric generalized Gaussian kernel ICA algorithm is designed.When parametric ICA algorithms can perform suboptimally or even fail to separate the source signals,nonparametric generalized gaussian kernel ICA algorithm can be used,which is based on generalized Gaussian kernel function,and is truly blind to the source signals.Nonparametric density estimation is directly evaluated from the observed signal samples.An important problem,of choose nonlinear functions as the probability density function estimation of the sources is solved in ICA.The algorithm changes window width adaptively in terms of higher statistics so that it is able to separate a wide range of source signals.
4.A FastICA blind multi-user detection algorithm based on Neg-entropy is implemented.Function with power 4 is adopted as non-quadratic function,therefore, neg-entropy based non-Gaussianity measurement can be transformed into kurtosis form,which can decrease the computational complexity.Meanwhile,by exploiting the independence of the source signals of different users and utilizing spreading codes of target user as training sequence and initialization of unmixing matrix,excellent symbol estimation performances are obtained through stochastic gradient method while the codes of the interfering users in downlink are unknown.Analysis for computational complexity of our algorithm shows that computational complexity increases with length of receiving data and number of users.In this work,the ICA blind detection method is compared with traditional matched filter and well-known linear MMSE multi-user detector.Numerical simulations indicate that ICA based detection performance is comparable to MMSE detection when MAI is lower in synchronous CDMA channels.With the increase of MAI,the superior performance of ICA has significant improvement over exact-MMSE.
5.A novel ICA blind detection algorithm based on nonparametric likelihood ratio criterionr is improved.Classical ICA algorithms rely on simple assumptions on the source statistics.Therefore,such algorithms can not perform optimally or even fail to produce the desired source separation when the assumed statistical model is inaccurate. This method is completely blind to the sources and has ability to separate the mixed sources simultaneously.The signal of desired user is detected by using kemel function to estimate probability density function and combining gradient descent method and likelihood ratio criterion.Finally,comparing this algorithm with others,namely FastlCA detection,MMSE,RAKE,the results show that this algorithm provides MAI interference suppression between FastICA detection and MMSE.
1.利用矩阵理论推导了独立分量分析的克拉美罗性能界。克拉美罗性能界是估计理论中无偏参数估计方差的下界,是评价参数估计性能最常用的度量。基于瞬时ICA模型推导了分离矩阵W的Fisher信息矩阵。为了准确衡量算法的分离精度,定义了增益矩阵G,并推导了关于G的克拉美罗性能界。克拉美罗性能界为独立分量分析算法性能评价提供了一种衡量准则。
2.提出了广义高斯变量生成算法和自适应的FastICA算法。基于伽玛分布随机变量,综合运用随机变量变换法和舍选抽样法,提出了一种简便的广义高斯分布随机变量生成算法。该算法计算简单,通过调整分布参数的值,可产生具有任何形状参数和任何方差的广义高斯分布随机变量。为了克服传统FastICA算法中要依据先验信息选定合适的非线性激活函数的缺点,提出了一种自适应FastICA算法。该算法基于广义高斯模型,通过高斯模型的形状参数的优化和分离矩阵迭代结合,实现了激活函数向源信号评价函数的逼近,可以同步实现不同类型源信号的估计。并给出了算法的稳定性分析和仿真实验。
3.提出了非参数广义高斯核ICA算法。当参数ICA算法不能分离信号时,基于广义高斯核函数,提出了非参数广义高斯核ICA算法。它在源信号密度函数全“盲”情况下,能实现正确分离,解决了如何选取估计信号评价函数的难题,可用于任意分布的源信号。广义高斯核函数可以根据源信号的高阶统计自适应地改变窗宽以适应不同源信号的要求。
4.提出了基于负熵准则的FastICA盲多用户检测算法。该算法使用四次幂函数,把基于负熵的非高斯性测度转化为信号峰度的形式,降低了计算量。同时,算法充分考虑了各用户信号的统计独立性,在下行链路干扰用户的扩频码未知情况下,把目标用户的扩频码作为训练序列,并用于初始化FastICA算法的分离向量,使用随机梯度法进行优化计算,获得了优异的符号估计性能。对算法的计算复杂度的分析可以看出,计算量随着接收数据长度和用户数的增加而增加。在同步CDMA信道中与传统匹配滤波器、MMSE检测算法比较,MAI较低的时该算法检测性能与MMSE的性能接近;随着MAI增加,其性能明显优于MMSE算法。
5.提出了基于非参数似然比准则的盲多用户算法。当建立的概率密度模型不准确时,参数ICA算法算法有时不能分离源信号,为此,提出了非参数ICA的检测算法。直接由观测信号样本出发,使用高斯核函数估计分离信号的概率密度函数,计算非参数似然函数比,结合梯度下降法和似然比准则进行目标用户的信号检测。通过试验仿真,与其它算法比较,结果表明该算法抑制多址干扰的能力介于FastICA检测和MMSE检测之间。
Independent component analysis(ICA) is a new method in statistical signal processing and neural networks.As a result of its outstanding performance in blind identification and feature extraction or representation,ICA has been used wildly in various fields,for instance,communication systems,speech processing,image enhancement,and biomedical signal processing.Because the linear ICA model has the same form as the CDMA signal model,it can be used in multi-user detection.Utilizing ICA,the desired user information sequence can be separated from the mixture signals polluted by MAI.The main research works of this paper are presented as follows:
1.The Cramer-Rao lower bound of ICA is established.Cramer-Rao lower bound is the variance lower bound of unbiased parameters estimation in estimation theory and the common measurement of evaluation performance of parameters estimation.A detail derivation of the Fisher information matrix for demixing matrix w is provided. Gain matrix G is defined,which can give the accuracy measurement of the estimation of the original signals.Cramer-Rao lower bound for gain matrix is deduced in the end and can give a general performance criterion for independent component analysis.
2.Algorithm for generating generalized Gaussian distribution random variable and adaptive FastlCA algorithm are proposed.In order to simply create random variables of generalized Gaussian distribution with any shape parameter and any variance,an algorithm is proposed by combining transformations of random variable method and abandon-selection sampling method.The algorithm is derived by proper transformations based on gamma distribution random variables.The algorithm is computationally simple.Random variables of generalized Gaussian distribution with any shape parameter and any variance can be generated easily by adjusting the numerical values of these parameters.Different from traditional FastICA algorithms where the activation function is pre-designed by prior knowledge and fixed for all sources even in different types,an adaptive FastlCA algorithm is presented based on the generalized Gaussian model where the iterations for the paracmeters of the generalized Gaussian and the demixing vector are combined.The stability analysis is also given as well as computer simulation demonstrations.
3.Nonparametric generalized Gaussian kernel ICA algorithm is designed.When parametric ICA algorithms can perform suboptimally or even fail to separate the source signals,nonparametric generalized gaussian kernel ICA algorithm can be used,which is based on generalized Gaussian kernel function,and is truly blind to the source signals.Nonparametric density estimation is directly evaluated from the observed signal samples.An important problem,of choose nonlinear functions as the probability density function estimation of the sources is solved in ICA.The algorithm changes window width adaptively in terms of higher statistics so that it is able to separate a wide range of source signals.
4.A FastICA blind multi-user detection algorithm based on Neg-entropy is implemented.Function with power 4 is adopted as non-quadratic function,therefore, neg-entropy based non-Gaussianity measurement can be transformed into kurtosis form,which can decrease the computational complexity.Meanwhile,by exploiting the independence of the source signals of different users and utilizing spreading codes of target user as training sequence and initialization of unmixing matrix,excellent symbol estimation performances are obtained through stochastic gradient method while the codes of the interfering users in downlink are unknown.Analysis for computational complexity of our algorithm shows that computational complexity increases with length of receiving data and number of users.In this work,the ICA blind detection method is compared with traditional matched filter and well-known linear MMSE multi-user detector.Numerical simulations indicate that ICA based detection performance is comparable to MMSE detection when MAI is lower in synchronous CDMA channels.With the increase of MAI,the superior performance of ICA has significant improvement over exact-MMSE.
5.A novel ICA blind detection algorithm based on nonparametric likelihood ratio criterionr is improved.Classical ICA algorithms rely on simple assumptions on the source statistics.Therefore,such algorithms can not perform optimally or even fail to produce the desired source separation when the assumed statistical model is inaccurate. This method is completely blind to the sources and has ability to separate the mixed sources simultaneously.The signal of desired user is detected by using kemel function to estimate probability density function and combining gradient descent method and likelihood ratio criterion.Finally,comparing this algorithm with others,namely FastlCA detection,MMSE,RAKE,the results show that this algorithm provides MAI interference suppression between FastICA detection and MMSE.
引文
[1]李兴林.交通通信的现状与发展分析[J].通信世界,2005,35:50-50
[2]http://www.3gpp.org
[3]http://www.itu.org
[4]3GPP 23.002,Network Architecture
[5]Adachi F,Sawahashi M and Suda H.Wideband DS-CDMA for Next-Generation Mobile Communication Systems[J].IEEE Commnications Magazine,1998,36(9):56-69
[6]胡兴军.4G移动通信关键技术及特征[J].电信快报,2007,5:41-45
[7]徐丹,周峰,杨大成.4G技术发展与挑战[J].移动通信,2007,12:39-42
[8]杨行峻,郑君里.人工神经网络与盲信号处理[M].北京:清华大学出版社,2003
[9]Sejnowski T J.A preface to indepdent component nalysis[OL],http://www.cnl.salk.edu/-tewon/ica_cnl.html,1998
[10]Hyv(a|¨)rinen A,Karhunen J and Oja E.Independent component analysis[M].New York:Wiley-Interscience,2001
[11]焦李成,马海波,刘芳.多用户检测与独立分量分析:进展与展望[J].自然科学进展,2002,12(4):365-371
[12]Kuh A,Gong X H.Independent component analysis for blind multiuser detections[C].IEEE International Symposium on Information Theory(ISIT 2000),Sorrento,Italy,2000:246-246
[13]Comon P.Independent component analysis,a new concept[J]? Signal Processing,1994,36(3):287-314
[14]史习智.盲信号处理--理论与实践[M].上海:上海交通大学出版社,2008
[15]Amari S I and Cichocki A.Adaptive blind signal and image processing[M].New York:Wiley,2002
[16]Ristaniemi T,Joutsensalo J.Independent component analysis and CDMA[OL].http://math.tkk.fi/diderot2001/presentations/ristaniemi.pdf
[17]Herault J and Jutten C.Space or time adaptive signal processing by neural network models[C].Neural Networks for Computing,AlP Conference,New York,1986:206-211
[18]Jutten C,Heranlt J.Blind separation of Source.Part Ⅰ:An adaptive algorithm based on neuromimatic architecture[J].Signal Processing,1991,24(1):1-10
[19]Comon P,Jutten C,Heranlt J.Blind separation of Source.Part Ⅱ:problems statement[J].Signal Processing,1991,24:11-20
[20]Comon P.Independent component analysis,A New Concept[J]?Signal Processing,1994,36:287-314
[21]Tong L,Soon V,Huang Y F,et al.Indeterminacy and identifiablity of blind indetification[J].IEEE Transactions on CAS,1991,38:499-509
[22]Tong L,Inouye Y,Liu R W.Waveform preserving blind estimation of multiple independent sources[J].IEEE Transactions on Signal Processing,1994,41(7):2641-2470
[23]Jutten C,Herault J.Independent component analysis verus principal component analysis[C].4~(th) European Signal Processing Conference(EUSIPCO88),Grenoble,France,1988:643-646
[24]Bell A J,Sejnowski T.J.An information-maximization approach to blind separation and blind deconvolution[J].Neural Computation,1995,7(6):1004-1034
[25]Cichocki A,Unbehauen R,and Rummert E.Robust learning algorithm for blind separation of signals[J].Electronic Letters,1994,30(17):1386-1387
[26]Cichocki A and Unbehauen R.Robust neural networks with on-line learning for blind identification and blind separation fo sources [J].IEEE Transactions on Circuits and Systems,1996,43(11):894-906
[27]Karhunen J and Joutsensalo J.Representation and separation of signals using nonlinear PCA type learning [J].Neural Networks,1994,7(1):113-127
[28]Karhunen J,Oja E and Wang L,et al.A class of neural networks for independent component anlysis [J].IEEE Transactions on Neural Networks,1997,8(3):486-504
[29]Karhunen J,Pajunen P and Oja E.The nonlinear PCA criterion in blind source separation:Relations with other approaches [J].Neurocomputing,1998,22:5-20
[30]Karhunen J,Wang L and Vigario R.Nonlinear PCA type approaches for source separation and independent component analysis [C],IEEE International Conference of Neural Networks (ICNN'95),1995:995-1000
[31]Oja E.The nonlinear PCA learing rule in independent component analysis [J]. Neurocomputing,1997,17:25-45
[32]Pham D T,Garrat P and Jutten C.Separation of a mixture of independent sources through a maximum likelihood approach [C].Sixth European Signal Processing Conference(EUSIPCO-92),Brussels,Belgium,1992:771-774
[33]Pham D T.Blind separation of instantaneous mixture of sources via an independent component analysis [J].IEEE Transactions on Signal Processing,1996,44(11):2768-2779
[34]Pham D T and Garat P.Blind separation of mixture of independent sources through a quasi-maximum likelihood approach [J].IEEE Transaction on Signal Processing,1997,45(7):1712-1725
[35]Pearlmutter B A and Parra L C.A context sensitive generalization of ICA[C].International Conference on Neural Information Processing(ICNIP'96),1996:151-156
[36]Cardoso J F and Amari S I.Maximum likelihood source separation:equivariance and adaptivity [C].11~(th) IFAC Symposium on System Identification,1997:1063-1068
[37]Cardoso J F.Infomax and maximum likelihood for source separation [J].IEEE Letters on Signal Processing,1997,4(4):112-114
[38]Amari S I,Cichocki A and Yang H H.A new learning algorithm for blind signal separation [C].Neural Information Processing Systems Conferenence(NIPS'96),1996,8:757-763
[39]Amari S I and Cichocki A.Adaptive blind signal processing-neural network approaches [J].Proceedings of IEEE,1998,86(1):2026-2048
[40]Yang H H,Amari S I and Cichocki A.Adapative on-line learning algorithms for blind separation-maximum entropy and minimum mutal information [J].Neural Computation,1997,7(9):1457-1482
[41]Hyvarinen A and Oja E.A fast fixed-point algorithm for independent component analysis[J].Neural Computation,1997,9(7):1483-1492
[42]Hyvarinen A and Oja A.Independent component analysis by general nonlinear Hebbian like learning rules [J].Signal Processing,1998,64(3):301-313
[43]Hyvarinen A.A family of fixed-point algorithms for independent component analysis[C].IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP'97),Munich, Germany,1997:3917-3920
[44]Hyvarinen A.Fast and robust fixed-point algorithms for independent component analysis [J].IEEE Transactions on Neural Networks,1999,10(3):626-634
[45]Hyvarinen A.The fixed-point algorithm and maximum likelihood estimation for independent component analysis[J].Neural Processing Letters,1999,10(1):1-5
[46]Hyvarinen A.Survey on independent component analysis[J].Neural Computing Surveys,1999,2:94-128
[47]Cardoso J F,Laheld B.Equivariant adaptive source separation [J].IEEE Transaction on Signal Processing,1996,44(12):3.17-3030
[48]Cao X R and Liu R W.General approach to blind source separation[J].IEEE Transactions on Signal Processing,1996,44(3):562-571
[49]Obradovic D,Deco G.Blind source separation:Are Information maximization and redundancy minimization different[C]?IEEE Workshop on Neural Networks for Signal Processing,FL USA,1997:416-425
[50]Lee T W,Girolami M and Sejnowski T J.Independent component analysis using an extended Infomax algorithm for mixed subgaussian and supergaussian sources[J].Neural Computation,1999,11(2):417-441
[51]Amari S I.Natural gradient works efficiently in learning[J].Neural Computation,1998,10:251-276
[52]Amari S I.Superefficiency in blind source separation [J].IEEE Transactions on Signal Processing,1999,47(4):936-944
[53]Tichavsky P,Koldovsky Z,Yeredor A,Gomez-Herrero G and Doron E.A hybrid technique for blind separation of non-Gaussian and time-correlated sources using a multicomponent approach [J].IEEE Transactions on Neural Networks,2008,19(3):421-430
[54]Tichavsky P,Yeredor A and Nielsen J.A fast approximate joint diagonalization algorithm using a criterion with a block diagonal weight matrix [C].33rd International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2008),Las Vegas,U.S.A,2008
[55]Koldovsk(?) Z,M(?)lek J,Tichavsk(?) P,Deville Y,and Hosseini S.Extension of EFICA algorithm for blind separation of piecewise stationary non Gaussian sources[C].33rd International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2008),Las Vegas,U.S.A,2008:1913-1916
[56]Koldovsky Z and Tichavsky P.Cramer-Rao Lower Bound for Independent Component Analysis[R].Technical Report N0.2123,UTIA,AV CR,2004:1-8
[57]Doron E,Arie Yeredor A and Tichavsk(?) P.Cram(?)r-Rao-induced bound for blind separation of stationary parametric Gaussian sources [J].IEEE Signal Processing Letters,2007,14(6):417-420
[58]Koldovsky Z and Tichavsky P.Time-domain blind audio source separation using advanced ICA methods [C].Proceedings of 8th Annual Conference of the International Speech Communication Association(Interspeech 2007),Antwerp,Belgium,2007:846-849
[59]Tichavsk(?)y P,Koldovsk(?) Z and Oja E.Speed and accuracy enhancement of linear ICA techniques using rational nonlinear functions[C].Proceedings of 7~(th) International Conference on Independent Component Analysis and Signal Separation(ICA 2007),London,UK,2007:285-292
[60]Koldovsky Z.and Tichavsky P.Blind instantaneous noisy mixture separation with best interference-plus-noise rejection [C].Proceedings of 7~(th) International Conference on Independent Component Analysis and Signal Separation(ICA 2007),London,UK,2007:700-737
[61]Gomez-Herrero G,Koldovsk(?) Z,Tichavsky P and Egiazarian K.A fast algorithm for blind separation of non-Gaussian and time-correlated signals [C],15th European Signal Processing Conference(EUSIPCO 2007),Poznan,Poland,2007:1731-1735
[62]M(?)lek J,Koldovsk(?) Z,Hosseini S and Deville Y.A Variant of EFICA algorithm with adaptive parametric density estimator[C].8th International Workshop on Electronics,Control,Modelling,Measurement,and Signals(ECMS 2007),Liberec,Czech Republic,2007:79-84
[63]Tichavsk(?) P,Koldovsk(?) Z and Oja E.Performance analysis of the FastICA algorithm and Cram(?)r-Rao bounds for linear independent component analysis[J],IEEE Transactions on Signal Processing,2006,54(4):1189-1203
[64]Koldovsk(?) Z,Tichavsk(?) P and Oja E.Efficient variant of algorithm FastICA for independent component analysis attaining the Cramer-Rao lower bound[J].IEEE Transactions on Neural Networks,2006,17(5):1265-1277
[65]Koldovsk(?) Z,Nouza J and Koloren(?) J.Continuous time-frequency masking method for blind speech separation with adaptive choice of threshold aarameter using ICA[C].Proceedings of 7th Annual Conference of the International Speech Communication Association(Interspeech 2006),Pittsburgh PA,USA,2006:2578-2581
[66]Koldovsk(?) Z,Tichavsk(?) P.Methods of fair comparison of performance of linear ICA techniques in presence of additive noise[C],IEEE International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2006),Toulouse,France,2006,5:873-876
[67]Koldovsk(?) Z,Tichavsk(?) P and Oja E.Cramer-Rao lower bound for linear independent component analysis[C],IEEE International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2005),Philadelphia,2005,3:581-584
[68]Tichavsk(?),P and Koldovsk(?),Z.Optimal pairing of signal components separated by blind techniques[J].IEEE Signal Processing Letters,2004,11(2):119-122
[69]Darbellay G A and Tichavsk(?),P.Independent component analysis through direct estimation of the mutual information[C].Second International Workshop on Independent Component Analysis and Blind Signal Separation(ICA'2000),Helsinki,Finland,2000:69-75
[70]Sorouchyari E.Blind separation of sources,part Ⅲ:stability analysis[J].Signal Processing,1991,24(1):21-29
[71]Deville Y.Analysis of the convergence properties of self-normalized source separation neural networks[J].IEEE Transactions on Signal Processing,1999,47(5):1272-1287
[72]Amari S I,Chen T P,and Cichocki A.Stability analysis of adaptive blind source separation[J].Neural Networks,1997,10(8):1345-1351
[73]Bernstein I H,Teng G,and Garbin C P.Applied multivariate analysis[M].New York:Springer Verlag,1988
[74]陈阳,何振亚.一类新的独立性度量及其在盲信号分离中的应用[J].武汉大学学报(信息科学版),2004,29(1):84-88
[75]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
[76]张贤达,保铮.盲信号分离[J].电子学报,200l,29(12):1766-1771
[77]杨福生,洪波.独立分量分析的原理与应用[M].北京:清华大学出版社,2006
[78]Zhang L Q,Cichocki A,Amari S I.Self-adaptive blind source separation based on activation functions adaptation[J].IEEE Transactions on Neural Networks,2004,15(2):233-244
[79]Zhang Z L,Zhang L Q,Wu X L,Li L,et al.Two-Stage Temporally Correlated Source Extraction Algorithm with Its Application in Extraction of Event-Related Potentials[C].13th International Conference on Neural Information Processing(ICONIP 2006),2006:523-532
[80]Ma L B,Zhang L Q and Yang W L.Local Independent Factorization of Natural Scenes,Advances in Neural Networks[C].Proceedings of ISNN2006,2006,2:454-459
[81]Zhang Z L,Zhang L Q.A Two-stage based approach for extracting periodic signals[C].Proccedings of ICA 2006,2006:303-310
[82]Zhang L Q,Ma L B,Wenlu Yang W L,et al.Sparse representation and associative learning in multi-sensory integration[C],Procs of ICNN&B,2005:1622- 1626
[83]Cheung C C,Xu L.Some global and local convergence analysis on the information theoretic independent component analysis approach[J].Neurocomuting,2000,30:79-102
[84]Xu L,Cheung C C and Amari S.Further results on nonlinearity and separation capability of linear mixture in method and learning algorithm[C].Proc.of International ICSC Workshop on Independence and Artificial Neural Networks(ICANN'98),Tenerife,Spain,1998:39-44.
[85]Liu Z Y,Chiu K C and Xu L.One bit matching conjecture for independent component analysis[J].Neural Computation,2004,16(2):383-399
[86]Ma J W,Liu Z Y,Xu L.A further result on the ICA one bit matching conjecture[J].Neural Computation,2005,17(2):331-334
[87]Xu L.One-bit-matching theorem for ICA,convex-concave programming on polyhedral set and distribution approximation for combinatorics[J].Neural Computation,2007,19:546-569
[88]傅予力,谢胜利,何昭水.盲信号分离模型的混叠矩阵估计算法[J].华中科技大学学报(自然科学版),2007,35(9):94-97
[89]谭北海,谢胜利.基于源信号数目估计的欠定盲分离[J].电子与信息学报,2008,30(4):863-867
[90]王刚,胡德文.独立分量分析对相关信号源的盲辨识性能分析[J].计算机工程与应用, 2005,4:23-25
[91]刘琚,梅良模,何振亚.一种忙信号分离的信息理论方法[J].山东大学学报,1998,33(4):398-403
[92]张安清,邱天爽,章新华.卷积混合信号频域盲分离技术研究[J].大连理工大学学报,2004,44(5):723-728
[93]张旭秀,邱天爽.基于源信号统计独立性的ICA方法的不确定性研究[J].系统工程与电子技术,2004,26(4):556-559
[94]史振威,钟明军,唐焕文,等.基于投影方法的约束独立成分分析[J].运筹与管理,2004,13(5):1-6
[95]王法松,李宏伟,何水明.基于自适应评价函数的独立成分分析算法[J].系统仿真学报,2005,17(9):2222-2225
[96]王法松,李宏伟,朱培民.基于Parzen核估计的ICA算法及其性能分析[J].武汉理工大学学报,2005,27(9):93-96
[97]张发启.盲信号处理及应用[M].西安:西安电子科技大学出版社,2006
[98]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
[99]Xu L,Cheung C C,Amari S.Learned parametric mixture based ICA algorithm[J].Neurocomputing,1998,22:69-80
[100]Erikon J,Karhunen J,Koivunen V.Source distribution adaptive maximum likelihood estimation of ICA model[C].International Workshop on Independent Component Analysis (ICA2000),2000:227-232
[101]Douglas S.Blind source separation and independent component analysis:a crossroads of tools and ideas[C].4~(th) International Symposium on Independent Component Analysis and Blind Signal Separation(ICA2003),Nara,Japan,2003:1-10
[102]Gelle G,Colas M,Serviere C.Blind source separation:a new pre-processing tool for rotating machines monitoring[J].IEEE Transactions on Instrumentation and Measurement,2003,52(3):790-795
[103]Knaak M,Kunter M,Filberi D.Blind source separation for acoustical machine diagnosis[C].14~(th) International Conference on Digital Signal Processing,2002,1:159-162
[104]Lin Q H,Yin F L.Image cryptosystems based on blind source separation[C].Proceedings of the 2003 International Conference on Neural Networks and Signal Processing,2003,2:1366-1369
[105]Ananthanag K V,Sahambi J S.Investigation of blind source separation methods for extraction of fetal ECG[C].International Conference on Electrical and Computer Engineering,2003,3:2021-2024
[106]Huang G M,Yang L X,Su G Q.Blind source separation used for radar anti-jamming[C].Proceedings of the 2003 Internatinal Conference on Neural Networks and Signal Processing,2003,2:1382-1385
[107]Xu H J,Liu J.ICA based beam space-time block coding with transmit antenna array selection[C].Advances in Neural Networks(ISNN2004),2004,1:317-323
[108]Huovinen T,Ristaniemi T.Comparison of nonlinear interference and blind source separation techniques in the Ds-CDMA uplink[C].14~(th) IEEE Proceedings on Personal,Indoor and Mobile Radio Communications,2003,1:989-993
[109]Kiviluoto K,Oja E.Independent component analysis for paralle financial time series [C].Proceedings of International Conference on Neuro Network and Information Processing (ICONIP'98),1998:895-898
[110]Bartlett M S.Face Recognition by independent component analysis[J].IEEE Transactions on Neural Networks,2002,13(6):765-781
[111]Deniz O,Castrillon M,Hernandz M.Face Recognition using independent component analysis and support vector machine[J].Pattern Recognition Letters,2003,24:2153-2157
[112]Markus S,Frithjof K,Habib B.ICA of fMRI group study Data[J].NeuroImage,2002,16:551-563
[113]Ikeda S,Toyama K.Independent component analysis for noisy data--MEG data analysis[J].Neural Network,2000,13:1063-1073
[114]Cichocki A,Amari S.Apative blind signal and image processing:learning algorithms and applications[M].Wiley,2003
[115]Delfosse D,Loubaton P.Adaptive blind separation of independent sources:a deflation approach[J].Signal Processing,1995,45(1):59-83
[116]Dapena A,Castedo L,Escudero C.An unconstrained signal stage criterion for blind source separation[C].Proceeding of ICASSP,1996,5:2706-2709
[117]Schneider K S.Optimum detection of code division multiplexed signals[J].IEEE Transactions onAerop.Electronical System,1979,15:181-185
[118]Verdu S.Computational complexity of optimum multiuser detection[J].Algorithmica,1989,4:302-312
[119]Verdu S.Multiuser detection in advances in statistical signal processing:signal detection[M].JAI Press,1993
[120]Lupas R,Verdu S.Near far resistance of multiuser detectors in asynchronous channels[J].IEEE Transactions on Communication,1990,38:496-508
[121]Madhow U,Honig M L.MMSE interference suppression for direct sequence spread spectrum CDMA[J].IEEE Transactions on Communication,1994,42:3178-3188
[122]Uppala S V,Sahr J D.Recursive structures and finite impulse response implementations of linear multiuser detectors for an ssynchronous CDMA system[J].IEEE Journal Selected Areas on Communication,1998,16:1736-1746
[123]Honig M L,Madhow U,Verdu S.Blind Adaptive Multiuser Detection[J].IEEE Transactions on Information Theory,1995,41(4):944-960
[124]Wang X,Poor H V.Blind multiuser detection:a subspace approach[J].IEEE Transactions on Information Theory,1998,44:91-103
[125]Kuh A,Gong X H.Independent component analysis for blind multiuser dections[C].ISIT 2000,2000:156-157
[126]Ristaniemi T,Joutsensalo J.Advanced ICA-base receivers for block fading DS-CDMA channels[J].Signal Processing,2002,82:417-431
[127]Khamy S E,Lotfy M,Badawy A S,et al.On the blind multiuser detection of DS-CDMA signals using the independent component analysis[C].Proceedings of the 20~(th) National Radio Science Conference 2003(NRSC2003),2003,34:1-9
[128]Gupta M,Santhanam B.ICA based blind adaptive MAI suppression in DS-CDMA systems[C].Proceedings of IEEE DSP Workshop,2004,2:201-205
[129]Gupta M.Prior ICA based blind multiuser detection in DS-CDMA systems[C].IEEE Asilomar Conference on Signals,Systems,and Computers,2004,2:2155-2159
[130]Overbye D,Priemer R.A neural network based multiuser detector for CDMA communications systems[C].15th International Conference on Systemes Engineering,2002:237-243
[131]Overbye D,Priemer R.Blind multiuser detection for DS-CDMA using independent component analysis neural network[J].International Journal of Smart Engineering System Design,2003,5:555-564
[132]Overbye D.Incorporation of sparse priors in long code blind multiuser detection for DS-CDMA communication[C].2005 IEEE International Conference on Electro Information Technology,2005:1627-1632
[133]Leong W Y,Homer J.Implementing ICA in blind multiuser detection[C].International Sympsium on Communications and Information Technologies 2004(ISCIT2004),2004:947-952
[134]Leong W Y,Homer,J.Blind multiuser receiver for DS-CDMA wireless system[J],IEE Proceedings Communications,2006,153(5):733-739
[135]Shen L,Li S J,Chen F N,et al.Blind multi-user detection in DS-CDMA downlink under Gaussian noise using independent component analysis[C].ICSP 2006 Proceedings,2006:647-651
[136]任燕,何培宇,段文峰.DS-CDMA盲多用户检测算法性能实验研究[J].四川大学学报(自然科学版),2008,45(1):59-64
[137]席聪,张太镒,刘枫.基于核独立成分分析的盲多用户检测算法[J].西安交通大学学报,2004,38(4):373-376
[138]李晓辉,吴小培,吴蓓.基于独立分量分析的DS-CDMA下行信道延迟估计[J].系统仿真学报,2005,17(4):954-956
[139]范嘉乐,方勇.DS-CDMA通信系统中基于独立分量分析的盲多用户检测[J].信号处理,2004,20(4):416-419
[140]王勇,尤肖虎,陈明,程时昕.一种多入多出DS-CDMA系统中的半盲多用户检测算法[J].电子与信息学报,2001,23(9):847-853
[141]徐长江,酆广增.基于高阶累积量的盲自适应多用户检测[J].电子学报,2000,28(7): 48-50
[142]杨恒,张贤达.基于奇异值和奇异向量的盲自适应多用户检测方法[J].清华大学学报(自然科学版),2001,41(3):101-103
[143]王少尉,季晓勇.最优多用户检测问题研究[J].电子学报,2007,35(12):2339-2342Wang S W,Ji X Y.A study of optimum multi-user detection problem[J].Acta Electronica Sinica,2007,35(12):2339-2342.(in Chinese)
[144]高宁泊,赵晓晖,孟宪夫.基于偏差移除独立分量分析的DS-CDMA通信系统盲多用户检测[J].吉林大学学报(工学版),2007,37(6):1415-1419
[145]付卫红,杨小牛,刘乃安,曾兴雯.基于独立分量分析的通信信号盲侦察技术[J].四川大学学报(自然科学版),2007,44(6):1245-1249
[146]Hyvarinen A,Oja E.Independent component analysis:a tutorial[J].Neural Networks,2000,13(45):411-430
[147]张洪渊,史习智.一种任意信号源分离的高效算法[J].电子学报,2001,29(10):1392-1396
[148]孙守宇,郑君里,赵敏,等.不同幅度通信信号的盲源分离[J].通信学报,2004,25(6):132-138
[149]杨金成,张南.独立成分分析技术综述[J].舰船科学技术,2007,29(2):83-86
[150]李小军,楼顺天,张贤达.基于估计概率密度函数的独立分量分析方法[J].西安电子科技大学学报(自然科学版),2005,32(4):574-578
[151]吴小培,叶中付,郭晓静,等.基于滑动窗口的独立分量分析算法[J].计算机研究与发展,2007,44(1):185-191
[152]汤影,李建平.利用参数表示任意维数正交矩阵的ICA新算法[J].自动化学报,2008,34(1):31-39
[153]张贤达,保铮.通信信号处理[M].北京:国防工业出版社,2000
[154]Cardoso J F,Laheld B H.Equivariant adaptive source separation.IEEE Trans.On Signal Processing,1996,44(12):3017-3030
[155]Cover T M,Thomas J A.Elements of information theory.New York:John Wiley & Sons,LTD,1991
[156]张贤达.现代信号处理(第二版).北京:清华大学出版社,2002年,263-265
[157]Hyvarinen A.Fast and robust fixed-point algorithms for independent component analysis[J].IEEE Transaction on Neural Networks,1999,10(3):626-634
[158]Hyvarinen A.,Oja E.Independent component analysis:algorithms and applications[J].Neural Networks,2000,13:411-430
[159]徐明彪,朱维彰.关于信号盲分离分离效果评判指标的分析[J].杭州电子工业学院学报,2002,22(3):63-66
[160]Delfosse N,Loubaton P.Adaptive blind separation of independent source:A Deflation approach[J].Signal Processing,1995,45(1):59-83
[161]Amari S,Cardoso J F.Blind souce separation-semiparametric statistical approach[J].IEEE Transaction on Signal Processing,1997,45:2692-2700
[162]Waheed K,Salem M.Blind information theoretic multiuser detection algorithm for DS-CDMA and WCDMA downlink systems[J].IEEE Transactions on Neural Networks,2005,16(4):937-948
[163]Boscolo R,Pan H and Roychowdhury V P.Independent component analysis based on nonparametric density estimation[J].IEEE Transactions on Neural Networks,2004,15(1):55-65
[164]Jones M C,Sheather S J.A brief survey of bandwidth selection for density estimation[J].Journal of the American Statistical Association,1996,91(433):401-407
[165]Jones M C,Marron J S,Sheather S J.Progress in data-based bandwidth selection for kernel density estimation[J].Computational Statistics,1996,11:337-381
[166]Moon T K,Stirling W C.Mathematical methods and algorithms for signal processing[M].Prentice Hall,New Jersey,2000
[167]K.Kokkinakis,A.K.Nandi.A,K.Exponent parameter estimation for a generalized Gaussian probability density functions with application to speech modeling[J].Signal Processing,2005,85:1852-1858
[168]Ollila E,Kim H J,Koivunen V.Compact cram(?)r-rao bound expression for independent component analysis[J].IEEE Transactions on Signal Processing,2008,56(4):1421-1428
[169]吴宇新,余松煜.广义高斯分布随机变量生成算法[J].数据采集与处理,1999,14(4): 443-446
[170]张强,马润年,许进.广义高斯分布随机变量的仿真[J].西安电子科技大学学报,2001,28(4):549-552
[171]赵倩,李宏伟,沈远彤.一种产生广义高斯分布随机数的新算法[J].应用数学,2004,17(Supp):64-69
[172]N.Wolfgang.Generalized Gaussian modeling of correlated signal source[J].IEEE Transactions on Signal Processing,1999,47(1):217-219
[2]http://www.3gpp.org
[3]http://www.itu.org
[4]3GPP 23.002,Network Architecture
[5]Adachi F,Sawahashi M and Suda H.Wideband DS-CDMA for Next-Generation Mobile Communication Systems[J].IEEE Commnications Magazine,1998,36(9):56-69
[6]胡兴军.4G移动通信关键技术及特征[J].电信快报,2007,5:41-45
[7]徐丹,周峰,杨大成.4G技术发展与挑战[J].移动通信,2007,12:39-42
[8]杨行峻,郑君里.人工神经网络与盲信号处理[M].北京:清华大学出版社,2003
[9]Sejnowski T J.A preface to indepdent component nalysis[OL],http://www.cnl.salk.edu/-tewon/ica_cnl.html,1998
[10]Hyv(a|¨)rinen A,Karhunen J and Oja E.Independent component analysis[M].New York:Wiley-Interscience,2001
[11]焦李成,马海波,刘芳.多用户检测与独立分量分析:进展与展望[J].自然科学进展,2002,12(4):365-371
[12]Kuh A,Gong X H.Independent component analysis for blind multiuser detections[C].IEEE International Symposium on Information Theory(ISIT 2000),Sorrento,Italy,2000:246-246
[13]Comon P.Independent component analysis,a new concept[J]? Signal Processing,1994,36(3):287-314
[14]史习智.盲信号处理--理论与实践[M].上海:上海交通大学出版社,2008
[15]Amari S I and Cichocki A.Adaptive blind signal and image processing[M].New York:Wiley,2002
[16]Ristaniemi T,Joutsensalo J.Independent component analysis and CDMA[OL].http://math.tkk.fi/diderot2001/presentations/ristaniemi.pdf
[17]Herault J and Jutten C.Space or time adaptive signal processing by neural network models[C].Neural Networks for Computing,AlP Conference,New York,1986:206-211
[18]Jutten C,Heranlt J.Blind separation of Source.Part Ⅰ:An adaptive algorithm based on neuromimatic architecture[J].Signal Processing,1991,24(1):1-10
[19]Comon P,Jutten C,Heranlt J.Blind separation of Source.Part Ⅱ:problems statement[J].Signal Processing,1991,24:11-20
[20]Comon P.Independent component analysis,A New Concept[J]?Signal Processing,1994,36:287-314
[21]Tong L,Soon V,Huang Y F,et al.Indeterminacy and identifiablity of blind indetification[J].IEEE Transactions on CAS,1991,38:499-509
[22]Tong L,Inouye Y,Liu R W.Waveform preserving blind estimation of multiple independent sources[J].IEEE Transactions on Signal Processing,1994,41(7):2641-2470
[23]Jutten C,Herault J.Independent component analysis verus principal component analysis[C].4~(th) European Signal Processing Conference(EUSIPCO88),Grenoble,France,1988:643-646
[24]Bell A J,Sejnowski T.J.An information-maximization approach to blind separation and blind deconvolution[J].Neural Computation,1995,7(6):1004-1034
[25]Cichocki A,Unbehauen R,and Rummert E.Robust learning algorithm for blind separation of signals[J].Electronic Letters,1994,30(17):1386-1387
[26]Cichocki A and Unbehauen R.Robust neural networks with on-line learning for blind identification and blind separation fo sources [J].IEEE Transactions on Circuits and Systems,1996,43(11):894-906
[27]Karhunen J and Joutsensalo J.Representation and separation of signals using nonlinear PCA type learning [J].Neural Networks,1994,7(1):113-127
[28]Karhunen J,Oja E and Wang L,et al.A class of neural networks for independent component anlysis [J].IEEE Transactions on Neural Networks,1997,8(3):486-504
[29]Karhunen J,Pajunen P and Oja E.The nonlinear PCA criterion in blind source separation:Relations with other approaches [J].Neurocomputing,1998,22:5-20
[30]Karhunen J,Wang L and Vigario R.Nonlinear PCA type approaches for source separation and independent component analysis [C],IEEE International Conference of Neural Networks (ICNN'95),1995:995-1000
[31]Oja E.The nonlinear PCA learing rule in independent component analysis [J]. Neurocomputing,1997,17:25-45
[32]Pham D T,Garrat P and Jutten C.Separation of a mixture of independent sources through a maximum likelihood approach [C].Sixth European Signal Processing Conference(EUSIPCO-92),Brussels,Belgium,1992:771-774
[33]Pham D T.Blind separation of instantaneous mixture of sources via an independent component analysis [J].IEEE Transactions on Signal Processing,1996,44(11):2768-2779
[34]Pham D T and Garat P.Blind separation of mixture of independent sources through a quasi-maximum likelihood approach [J].IEEE Transaction on Signal Processing,1997,45(7):1712-1725
[35]Pearlmutter B A and Parra L C.A context sensitive generalization of ICA[C].International Conference on Neural Information Processing(ICNIP'96),1996:151-156
[36]Cardoso J F and Amari S I.Maximum likelihood source separation:equivariance and adaptivity [C].11~(th) IFAC Symposium on System Identification,1997:1063-1068
[37]Cardoso J F.Infomax and maximum likelihood for source separation [J].IEEE Letters on Signal Processing,1997,4(4):112-114
[38]Amari S I,Cichocki A and Yang H H.A new learning algorithm for blind signal separation [C].Neural Information Processing Systems Conferenence(NIPS'96),1996,8:757-763
[39]Amari S I and Cichocki A.Adaptive blind signal processing-neural network approaches [J].Proceedings of IEEE,1998,86(1):2026-2048
[40]Yang H H,Amari S I and Cichocki A.Adapative on-line learning algorithms for blind separation-maximum entropy and minimum mutal information [J].Neural Computation,1997,7(9):1457-1482
[41]Hyvarinen A and Oja E.A fast fixed-point algorithm for independent component analysis[J].Neural Computation,1997,9(7):1483-1492
[42]Hyvarinen A and Oja A.Independent component analysis by general nonlinear Hebbian like learning rules [J].Signal Processing,1998,64(3):301-313
[43]Hyvarinen A.A family of fixed-point algorithms for independent component analysis[C].IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP'97),Munich, Germany,1997:3917-3920
[44]Hyvarinen A.Fast and robust fixed-point algorithms for independent component analysis [J].IEEE Transactions on Neural Networks,1999,10(3):626-634
[45]Hyvarinen A.The fixed-point algorithm and maximum likelihood estimation for independent component analysis[J].Neural Processing Letters,1999,10(1):1-5
[46]Hyvarinen A.Survey on independent component analysis[J].Neural Computing Surveys,1999,2:94-128
[47]Cardoso J F,Laheld B.Equivariant adaptive source separation [J].IEEE Transaction on Signal Processing,1996,44(12):3.17-3030
[48]Cao X R and Liu R W.General approach to blind source separation[J].IEEE Transactions on Signal Processing,1996,44(3):562-571
[49]Obradovic D,Deco G.Blind source separation:Are Information maximization and redundancy minimization different[C]?IEEE Workshop on Neural Networks for Signal Processing,FL USA,1997:416-425
[50]Lee T W,Girolami M and Sejnowski T J.Independent component analysis using an extended Infomax algorithm for mixed subgaussian and supergaussian sources[J].Neural Computation,1999,11(2):417-441
[51]Amari S I.Natural gradient works efficiently in learning[J].Neural Computation,1998,10:251-276
[52]Amari S I.Superefficiency in blind source separation [J].IEEE Transactions on Signal Processing,1999,47(4):936-944
[53]Tichavsky P,Koldovsky Z,Yeredor A,Gomez-Herrero G and Doron E.A hybrid technique for blind separation of non-Gaussian and time-correlated sources using a multicomponent approach [J].IEEE Transactions on Neural Networks,2008,19(3):421-430
[54]Tichavsky P,Yeredor A and Nielsen J.A fast approximate joint diagonalization algorithm using a criterion with a block diagonal weight matrix [C].33rd International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2008),Las Vegas,U.S.A,2008
[55]Koldovsk(?) Z,M(?)lek J,Tichavsk(?) P,Deville Y,and Hosseini S.Extension of EFICA algorithm for blind separation of piecewise stationary non Gaussian sources[C].33rd International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2008),Las Vegas,U.S.A,2008:1913-1916
[56]Koldovsky Z and Tichavsky P.Cramer-Rao Lower Bound for Independent Component Analysis[R].Technical Report N0.2123,UTIA,AV CR,2004:1-8
[57]Doron E,Arie Yeredor A and Tichavsk(?) P.Cram(?)r-Rao-induced bound for blind separation of stationary parametric Gaussian sources [J].IEEE Signal Processing Letters,2007,14(6):417-420
[58]Koldovsky Z and Tichavsky P.Time-domain blind audio source separation using advanced ICA methods [C].Proceedings of 8th Annual Conference of the International Speech Communication Association(Interspeech 2007),Antwerp,Belgium,2007:846-849
[59]Tichavsk(?)y P,Koldovsk(?) Z and Oja E.Speed and accuracy enhancement of linear ICA techniques using rational nonlinear functions[C].Proceedings of 7~(th) International Conference on Independent Component Analysis and Signal Separation(ICA 2007),London,UK,2007:285-292
[60]Koldovsky Z.and Tichavsky P.Blind instantaneous noisy mixture separation with best interference-plus-noise rejection [C].Proceedings of 7~(th) International Conference on Independent Component Analysis and Signal Separation(ICA 2007),London,UK,2007:700-737
[61]Gomez-Herrero G,Koldovsk(?) Z,Tichavsky P and Egiazarian K.A fast algorithm for blind separation of non-Gaussian and time-correlated signals [C],15th European Signal Processing Conference(EUSIPCO 2007),Poznan,Poland,2007:1731-1735
[62]M(?)lek J,Koldovsk(?) Z,Hosseini S and Deville Y.A Variant of EFICA algorithm with adaptive parametric density estimator[C].8th International Workshop on Electronics,Control,Modelling,Measurement,and Signals(ECMS 2007),Liberec,Czech Republic,2007:79-84
[63]Tichavsk(?) P,Koldovsk(?) Z and Oja E.Performance analysis of the FastICA algorithm and Cram(?)r-Rao bounds for linear independent component analysis[J],IEEE Transactions on Signal Processing,2006,54(4):1189-1203
[64]Koldovsk(?) Z,Tichavsk(?) P and Oja E.Efficient variant of algorithm FastICA for independent component analysis attaining the Cramer-Rao lower bound[J].IEEE Transactions on Neural Networks,2006,17(5):1265-1277
[65]Koldovsk(?) Z,Nouza J and Koloren(?) J.Continuous time-frequency masking method for blind speech separation with adaptive choice of threshold aarameter using ICA[C].Proceedings of 7th Annual Conference of the International Speech Communication Association(Interspeech 2006),Pittsburgh PA,USA,2006:2578-2581
[66]Koldovsk(?) Z,Tichavsk(?) P.Methods of fair comparison of performance of linear ICA techniques in presence of additive noise[C],IEEE International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2006),Toulouse,France,2006,5:873-876
[67]Koldovsk(?) Z,Tichavsk(?) P and Oja E.Cramer-Rao lower bound for linear independent component analysis[C],IEEE International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2005),Philadelphia,2005,3:581-584
[68]Tichavsk(?),P and Koldovsk(?),Z.Optimal pairing of signal components separated by blind techniques[J].IEEE Signal Processing Letters,2004,11(2):119-122
[69]Darbellay G A and Tichavsk(?),P.Independent component analysis through direct estimation of the mutual information[C].Second International Workshop on Independent Component Analysis and Blind Signal Separation(ICA'2000),Helsinki,Finland,2000:69-75
[70]Sorouchyari E.Blind separation of sources,part Ⅲ:stability analysis[J].Signal Processing,1991,24(1):21-29
[71]Deville Y.Analysis of the convergence properties of self-normalized source separation neural networks[J].IEEE Transactions on Signal Processing,1999,47(5):1272-1287
[72]Amari S I,Chen T P,and Cichocki A.Stability analysis of adaptive blind source separation[J].Neural Networks,1997,10(8):1345-1351
[73]Bernstein I H,Teng G,and Garbin C P.Applied multivariate analysis[M].New York:Springer Verlag,1988
[74]陈阳,何振亚.一类新的独立性度量及其在盲信号分离中的应用[J].武汉大学学报(信息科学版),2004,29(1):84-88
[75]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
[76]张贤达,保铮.盲信号分离[J].电子学报,200l,29(12):1766-1771
[77]杨福生,洪波.独立分量分析的原理与应用[M].北京:清华大学出版社,2006
[78]Zhang L Q,Cichocki A,Amari S I.Self-adaptive blind source separation based on activation functions adaptation[J].IEEE Transactions on Neural Networks,2004,15(2):233-244
[79]Zhang Z L,Zhang L Q,Wu X L,Li L,et al.Two-Stage Temporally Correlated Source Extraction Algorithm with Its Application in Extraction of Event-Related Potentials[C].13th International Conference on Neural Information Processing(ICONIP 2006),2006:523-532
[80]Ma L B,Zhang L Q and Yang W L.Local Independent Factorization of Natural Scenes,Advances in Neural Networks[C].Proceedings of ISNN2006,2006,2:454-459
[81]Zhang Z L,Zhang L Q.A Two-stage based approach for extracting periodic signals[C].Proccedings of ICA 2006,2006:303-310
[82]Zhang L Q,Ma L B,Wenlu Yang W L,et al.Sparse representation and associative learning in multi-sensory integration[C],Procs of ICNN&B,2005:1622- 1626
[83]Cheung C C,Xu L.Some global and local convergence analysis on the information theoretic independent component analysis approach[J].Neurocomuting,2000,30:79-102
[84]Xu L,Cheung C C and Amari S.Further results on nonlinearity and separation capability of linear mixture in method and learning algorithm[C].Proc.of International ICSC Workshop on Independence and Artificial Neural Networks(ICANN'98),Tenerife,Spain,1998:39-44.
[85]Liu Z Y,Chiu K C and Xu L.One bit matching conjecture for independent component analysis[J].Neural Computation,2004,16(2):383-399
[86]Ma J W,Liu Z Y,Xu L.A further result on the ICA one bit matching conjecture[J].Neural Computation,2005,17(2):331-334
[87]Xu L.One-bit-matching theorem for ICA,convex-concave programming on polyhedral set and distribution approximation for combinatorics[J].Neural Computation,2007,19:546-569
[88]傅予力,谢胜利,何昭水.盲信号分离模型的混叠矩阵估计算法[J].华中科技大学学报(自然科学版),2007,35(9):94-97
[89]谭北海,谢胜利.基于源信号数目估计的欠定盲分离[J].电子与信息学报,2008,30(4):863-867
[90]王刚,胡德文.独立分量分析对相关信号源的盲辨识性能分析[J].计算机工程与应用, 2005,4:23-25
[91]刘琚,梅良模,何振亚.一种忙信号分离的信息理论方法[J].山东大学学报,1998,33(4):398-403
[92]张安清,邱天爽,章新华.卷积混合信号频域盲分离技术研究[J].大连理工大学学报,2004,44(5):723-728
[93]张旭秀,邱天爽.基于源信号统计独立性的ICA方法的不确定性研究[J].系统工程与电子技术,2004,26(4):556-559
[94]史振威,钟明军,唐焕文,等.基于投影方法的约束独立成分分析[J].运筹与管理,2004,13(5):1-6
[95]王法松,李宏伟,何水明.基于自适应评价函数的独立成分分析算法[J].系统仿真学报,2005,17(9):2222-2225
[96]王法松,李宏伟,朱培民.基于Parzen核估计的ICA算法及其性能分析[J].武汉理工大学学报,2005,27(9):93-96
[97]张发启.盲信号处理及应用[M].西安:西安电子科技大学出版社,2006
[98]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
[99]Xu L,Cheung C C,Amari S.Learned parametric mixture based ICA algorithm[J].Neurocomputing,1998,22:69-80
[100]Erikon J,Karhunen J,Koivunen V.Source distribution adaptive maximum likelihood estimation of ICA model[C].International Workshop on Independent Component Analysis (ICA2000),2000:227-232
[101]Douglas S.Blind source separation and independent component analysis:a crossroads of tools and ideas[C].4~(th) International Symposium on Independent Component Analysis and Blind Signal Separation(ICA2003),Nara,Japan,2003:1-10
[102]Gelle G,Colas M,Serviere C.Blind source separation:a new pre-processing tool for rotating machines monitoring[J].IEEE Transactions on Instrumentation and Measurement,2003,52(3):790-795
[103]Knaak M,Kunter M,Filberi D.Blind source separation for acoustical machine diagnosis[C].14~(th) International Conference on Digital Signal Processing,2002,1:159-162
[104]Lin Q H,Yin F L.Image cryptosystems based on blind source separation[C].Proceedings of the 2003 International Conference on Neural Networks and Signal Processing,2003,2:1366-1369
[105]Ananthanag K V,Sahambi J S.Investigation of blind source separation methods for extraction of fetal ECG[C].International Conference on Electrical and Computer Engineering,2003,3:2021-2024
[106]Huang G M,Yang L X,Su G Q.Blind source separation used for radar anti-jamming[C].Proceedings of the 2003 Internatinal Conference on Neural Networks and Signal Processing,2003,2:1382-1385
[107]Xu H J,Liu J.ICA based beam space-time block coding with transmit antenna array selection[C].Advances in Neural Networks(ISNN2004),2004,1:317-323
[108]Huovinen T,Ristaniemi T.Comparison of nonlinear interference and blind source separation techniques in the Ds-CDMA uplink[C].14~(th) IEEE Proceedings on Personal,Indoor and Mobile Radio Communications,2003,1:989-993
[109]Kiviluoto K,Oja E.Independent component analysis for paralle financial time series [C].Proceedings of International Conference on Neuro Network and Information Processing (ICONIP'98),1998:895-898
[110]Bartlett M S.Face Recognition by independent component analysis[J].IEEE Transactions on Neural Networks,2002,13(6):765-781
[111]Deniz O,Castrillon M,Hernandz M.Face Recognition using independent component analysis and support vector machine[J].Pattern Recognition Letters,2003,24:2153-2157
[112]Markus S,Frithjof K,Habib B.ICA of fMRI group study Data[J].NeuroImage,2002,16:551-563
[113]Ikeda S,Toyama K.Independent component analysis for noisy data--MEG data analysis[J].Neural Network,2000,13:1063-1073
[114]Cichocki A,Amari S.Apative blind signal and image processing:learning algorithms and applications[M].Wiley,2003
[115]Delfosse D,Loubaton P.Adaptive blind separation of independent sources:a deflation approach[J].Signal Processing,1995,45(1):59-83
[116]Dapena A,Castedo L,Escudero C.An unconstrained signal stage criterion for blind source separation[C].Proceeding of ICASSP,1996,5:2706-2709
[117]Schneider K S.Optimum detection of code division multiplexed signals[J].IEEE Transactions onAerop.Electronical System,1979,15:181-185
[118]Verdu S.Computational complexity of optimum multiuser detection[J].Algorithmica,1989,4:302-312
[119]Verdu S.Multiuser detection in advances in statistical signal processing:signal detection[M].JAI Press,1993
[120]Lupas R,Verdu S.Near far resistance of multiuser detectors in asynchronous channels[J].IEEE Transactions on Communication,1990,38:496-508
[121]Madhow U,Honig M L.MMSE interference suppression for direct sequence spread spectrum CDMA[J].IEEE Transactions on Communication,1994,42:3178-3188
[122]Uppala S V,Sahr J D.Recursive structures and finite impulse response implementations of linear multiuser detectors for an ssynchronous CDMA system[J].IEEE Journal Selected Areas on Communication,1998,16:1736-1746
[123]Honig M L,Madhow U,Verdu S.Blind Adaptive Multiuser Detection[J].IEEE Transactions on Information Theory,1995,41(4):944-960
[124]Wang X,Poor H V.Blind multiuser detection:a subspace approach[J].IEEE Transactions on Information Theory,1998,44:91-103
[125]Kuh A,Gong X H.Independent component analysis for blind multiuser dections[C].ISIT 2000,2000:156-157
[126]Ristaniemi T,Joutsensalo J.Advanced ICA-base receivers for block fading DS-CDMA channels[J].Signal Processing,2002,82:417-431
[127]Khamy S E,Lotfy M,Badawy A S,et al.On the blind multiuser detection of DS-CDMA signals using the independent component analysis[C].Proceedings of the 20~(th) National Radio Science Conference 2003(NRSC2003),2003,34:1-9
[128]Gupta M,Santhanam B.ICA based blind adaptive MAI suppression in DS-CDMA systems[C].Proceedings of IEEE DSP Workshop,2004,2:201-205
[129]Gupta M.Prior ICA based blind multiuser detection in DS-CDMA systems[C].IEEE Asilomar Conference on Signals,Systems,and Computers,2004,2:2155-2159
[130]Overbye D,Priemer R.A neural network based multiuser detector for CDMA communications systems[C].15th International Conference on Systemes Engineering,2002:237-243
[131]Overbye D,Priemer R.Blind multiuser detection for DS-CDMA using independent component analysis neural network[J].International Journal of Smart Engineering System Design,2003,5:555-564
[132]Overbye D.Incorporation of sparse priors in long code blind multiuser detection for DS-CDMA communication[C].2005 IEEE International Conference on Electro Information Technology,2005:1627-1632
[133]Leong W Y,Homer J.Implementing ICA in blind multiuser detection[C].International Sympsium on Communications and Information Technologies 2004(ISCIT2004),2004:947-952
[134]Leong W Y,Homer,J.Blind multiuser receiver for DS-CDMA wireless system[J],IEE Proceedings Communications,2006,153(5):733-739
[135]Shen L,Li S J,Chen F N,et al.Blind multi-user detection in DS-CDMA downlink under Gaussian noise using independent component analysis[C].ICSP 2006 Proceedings,2006:647-651
[136]任燕,何培宇,段文峰.DS-CDMA盲多用户检测算法性能实验研究[J].四川大学学报(自然科学版),2008,45(1):59-64
[137]席聪,张太镒,刘枫.基于核独立成分分析的盲多用户检测算法[J].西安交通大学学报,2004,38(4):373-376
[138]李晓辉,吴小培,吴蓓.基于独立分量分析的DS-CDMA下行信道延迟估计[J].系统仿真学报,2005,17(4):954-956
[139]范嘉乐,方勇.DS-CDMA通信系统中基于独立分量分析的盲多用户检测[J].信号处理,2004,20(4):416-419
[140]王勇,尤肖虎,陈明,程时昕.一种多入多出DS-CDMA系统中的半盲多用户检测算法[J].电子与信息学报,2001,23(9):847-853
[141]徐长江,酆广增.基于高阶累积量的盲自适应多用户检测[J].电子学报,2000,28(7): 48-50
[142]杨恒,张贤达.基于奇异值和奇异向量的盲自适应多用户检测方法[J].清华大学学报(自然科学版),2001,41(3):101-103
[143]王少尉,季晓勇.最优多用户检测问题研究[J].电子学报,2007,35(12):2339-2342Wang S W,Ji X Y.A study of optimum multi-user detection problem[J].Acta Electronica Sinica,2007,35(12):2339-2342.(in Chinese)
[144]高宁泊,赵晓晖,孟宪夫.基于偏差移除独立分量分析的DS-CDMA通信系统盲多用户检测[J].吉林大学学报(工学版),2007,37(6):1415-1419
[145]付卫红,杨小牛,刘乃安,曾兴雯.基于独立分量分析的通信信号盲侦察技术[J].四川大学学报(自然科学版),2007,44(6):1245-1249
[146]Hyvarinen A,Oja E.Independent component analysis:a tutorial[J].Neural Networks,2000,13(45):411-430
[147]张洪渊,史习智.一种任意信号源分离的高效算法[J].电子学报,2001,29(10):1392-1396
[148]孙守宇,郑君里,赵敏,等.不同幅度通信信号的盲源分离[J].通信学报,2004,25(6):132-138
[149]杨金成,张南.独立成分分析技术综述[J].舰船科学技术,2007,29(2):83-86
[150]李小军,楼顺天,张贤达.基于估计概率密度函数的独立分量分析方法[J].西安电子科技大学学报(自然科学版),2005,32(4):574-578
[151]吴小培,叶中付,郭晓静,等.基于滑动窗口的独立分量分析算法[J].计算机研究与发展,2007,44(1):185-191
[152]汤影,李建平.利用参数表示任意维数正交矩阵的ICA新算法[J].自动化学报,2008,34(1):31-39
[153]张贤达,保铮.通信信号处理[M].北京:国防工业出版社,2000
[154]Cardoso J F,Laheld B H.Equivariant adaptive source separation.IEEE Trans.On Signal Processing,1996,44(12):3017-3030
[155]Cover T M,Thomas J A.Elements of information theory.New York:John Wiley & Sons,LTD,1991
[156]张贤达.现代信号处理(第二版).北京:清华大学出版社,2002年,263-265
[157]Hyvarinen A.Fast and robust fixed-point algorithms for independent component analysis[J].IEEE Transaction on Neural Networks,1999,10(3):626-634
[158]Hyvarinen A.,Oja E.Independent component analysis:algorithms and applications[J].Neural Networks,2000,13:411-430
[159]徐明彪,朱维彰.关于信号盲分离分离效果评判指标的分析[J].杭州电子工业学院学报,2002,22(3):63-66
[160]Delfosse N,Loubaton P.Adaptive blind separation of independent source:A Deflation approach[J].Signal Processing,1995,45(1):59-83
[161]Amari S,Cardoso J F.Blind souce separation-semiparametric statistical approach[J].IEEE Transaction on Signal Processing,1997,45:2692-2700
[162]Waheed K,Salem M.Blind information theoretic multiuser detection algorithm for DS-CDMA and WCDMA downlink systems[J].IEEE Transactions on Neural Networks,2005,16(4):937-948
[163]Boscolo R,Pan H and Roychowdhury V P.Independent component analysis based on nonparametric density estimation[J].IEEE Transactions on Neural Networks,2004,15(1):55-65
[164]Jones M C,Sheather S J.A brief survey of bandwidth selection for density estimation[J].Journal of the American Statistical Association,1996,91(433):401-407
[165]Jones M C,Marron J S,Sheather S J.Progress in data-based bandwidth selection for kernel density estimation[J].Computational Statistics,1996,11:337-381
[166]Moon T K,Stirling W C.Mathematical methods and algorithms for signal processing[M].Prentice Hall,New Jersey,2000
[167]K.Kokkinakis,A.K.Nandi.A,K.Exponent parameter estimation for a generalized Gaussian probability density functions with application to speech modeling[J].Signal Processing,2005,85:1852-1858
[168]Ollila E,Kim H J,Koivunen V.Compact cram(?)r-rao bound expression for independent component analysis[J].IEEE Transactions on Signal Processing,2008,56(4):1421-1428
[169]吴宇新,余松煜.广义高斯分布随机变量生成算法[J].数据采集与处理,1999,14(4): 443-446
[170]张强,马润年,许进.广义高斯分布随机变量的仿真[J].西安电子科技大学学报,2001,28(4):549-552
[171]赵倩,李宏伟,沈远彤.一种产生广义高斯分布随机数的新算法[J].应用数学,2004,17(Supp):64-69
[172]N.Wolfgang.Generalized Gaussian modeling of correlated signal source[J].IEEE Transactions on Signal Processing,1999,47(1):217-219