一种低信噪比下的有噪独立分量分析算法
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
针对目前大多数独立分量分析(independent component analysis,ICA)算法无噪或者弱噪声假设的局限性,提出一种适用于低信噪比情况的有噪独立分量分析算法。该算法以分离信号的负熵为目标函数,采用高斯分布密度模型作为非线性函数来估计负熵,并建立了模型参数的确定准则,能够较好地抑制低信噪比下噪声的影响,最后采用人工蜂群算法对混合矩阵进行全局寻优。仿真结果表明,与其他算法相比,提出的算法可以更为精确地估计混合矩阵,能够较好地解决低信噪比下的有噪ICA问题。
Aiming at the limitation that most ICA algorithms are based on the noise-free or weak noise model, a noisy independent component analysis algorithm which is suitable for low signal-noise ratio is proposed. The negentropy of the separated signals is utilized as the objective function. The Gaussian-distribution density model is selected as the nonlinear function to estimate the negentropy. Meanwhile, a confirm rule of the model parameters is established, which can suppress the noise effects in low SNR. Finally, the mixing matrix is optimized by the artificial bee colony algorithm. Simulation results illustrate that compared with other algorithms, the proposed method can estimate the mixing matrix parameters more accurately and solve the noisy ICA problems better.
引文
[1]Hyvarinen A,Karhunen J,Oja E著.周宗潭,董国华,徐昕,译.独立成分分析[M].北京:电子工业出版社,2007.Hyvarinen A,Karhunen J,Oja E.Zhou Z T,Dong G H,Xu X,transl Independent components analysis[M].Beijing:Publishing House of Electronics Industry,2007.
    [2]Yang F S,Hong B.The theory and application of independence component analysis[M].Beijing:Tsinghua University Press,2006.
    [3]杨俊美,余华,韦岗.独立分量分析及其在信号处理中的应用[J].华南理工大学学报:自然科学版,2012,40(11):1-12.Yang J M,Yu H,Wei G.Independent component analysis and its application to signal processing[J].Journal of South China University of Technology(Natural Science Edition),2012,40(11):1-12.
    [4]Knyazev G G,Bocharov A V,Pylkova L V.Extraversion and fronto-posterior EEG spectral power gradient:an independent component analysis[J].Biological psychology,2012,89(2):515-524.
    [5]张华,冯大政,庞继勇.基于二阶统计量的语音信号时域卷积盲分离算法[J].电子与信息学报,2010,32(5):1083-1087.Zhang H,Feng D Z,Pang J Y.A time-domain blind convolutive separation algorithm for speech signals based on second-order statistic[J].Journal of Electronics&Information Technology,2010,32(5):1083-1087.
    [6]Hatam M,Sheikhi A,Masnadi-shirazi M A.Target detection in pulse-train mimo radars applying ica algorithms[J].Progress In Electromagnetics Research,2012,122:413-435.
    [7]张银雪,田学民.基于改进PSO-ICA的地震信号去噪方法[J].石油地球物理勘探,2012,47(1):56-62.Zhang Y X,Tian X M.The noise elimination processing of seismic signal based on improved PSO-ICA[J].Oil Geophysical Prospecting,2012,47(1):56-62.
    [8]Hyvarine A.Fast and robust fixed-point algorithms for independent component analysis[J].Neural Networks,IEEE Transactions on,1999,10(3):626-634.
    [9]Hyvarinen A.Gaussian moments for noisy independent component analysis[J].Signal Processing Letters,IEEE,1999,6(6):145-147.
    [10]Douglas S C,Cichocki A,Amari S.Bias removal technique for blind source separation with noisy measurements[J].Electronics Letters,1998,34(14):1379-1380.
    [11]张和发,李立萍.含噪独立分量分析的期望最大化算法[J].电子科技大学学报,2012,41(4):527-531.Zhang H F,Li L P.Expectation-maximization algorithm for noisy independent component analysis[J].Journal of University of Electronic Science and Technology of China,2012,41(4):527-531.
    [12]Davies M.Identifiability issues in noisy ICA[J].Signal Processing Letters,IEEE,2004,11(5):470-473.
    [13]Karaboga D.An idea based on honey bee swarm for numerical optimization[M].Techn.Rep.TR06,Erciyes Univ.Press,Erciyes,2005.
    [14]Li G Q,Niu P F,Xiao X J.Development and investigation of efficient artificial bee colony algorithm for numerical function optimization[J].Applied Soft Computing,2012,12(1):320-332.
    [15]Xu Y F,Ping F,Ling Y.A simple and efficient artificial bee colony algorithm[J].Mathematical Problems in Engineering,2013,20(13):1-9.
    [16]张延良,楼顺天,张伟涛.非正交联合对角化盲分离算法的可辨识性研究[J].电子与信息学报,2010,32(5):1066-1070.Zhang Y L,Lou S T,Zhang W T.A study of identifiability for blind signal separation via nonorthogonal joint diagonalization[J].Journal of Electronics&Information Technology,2010,32(5):1066-1070.

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