基于随机梯度的变动量因子自适应白化算法

欧世峰; 高颖; 赵晓晖

doi:10.3724/SP.J.1004.2012.01370

基于随机梯度的变动量因子自适应白化算法

doi: 10.3724/SP.J.1004.2012.01370

1.
烟台大学光电信息科学技术学院烟台 264005;
2.
吉林大学通信工程学院长春 130012

详细信息

通讯作者:
高颖

计量
- 文章访问数: 1681
- HTML全文浏览量: 66
- PDF下载量: 929
- 被引次数: 0
出版历程
- 收稿日期: 2011-03-31
- 修回日期: 2011-10-18
- 刊出日期: 2012-08-20

Stochastic Gradient Based Variable Momentum Factor Algorithm for Adaptive Whitening

1.
Institute of Science and Technology for Opto-electronic Information, Yantai University, Yantai 264005;
2.
College of Communication Engineering, Jilin University, Changchun 130012

摘要

摘要: 针对自适应白化技术中算法的收敛速度问题, 通过融入具有变动量因子特性的动量项,提出了一种快速的自适应白化算法. 该算法利用动量项来加速系统的收敛速度,并基于随机梯度方法对动量因子进行自适应更新,有效提升了白化系统的整体性能. 仿真实验表明本文算法在平稳和非平稳环境下具有良好的性能.
- 白化 /
- 动量项 /
- 自适应 /
- 盲源分离
Abstract: In view of the convergence speed in adaptive whitening technique, by adding a momentum term with a variable momentum factor, a fast adaptive whitening algorithm is proposed. First, the presented algorithm incorporates a momentum term into the adaptive whitening algorithm to accelerate the convergence speed. Then, a variable momentum factor to improve the allover performance of the whitening system is obtained based on the stochastic gradient of the cost function. Experimental results demonstrate the good performance of the proposed fast algorithm both in stationary and non-stationary conditions.
- Whitening /
- momentum term /
- adaptive /
- blind source separation

HTML全文

参考文献(1)

[1]

Cichocki A, Amari S. Adaptive Blind Signal and Image Processing: Learning Algorithms and Application. New York: John Wiley and Sons, 2002. 129-175[2] Choi S, Cichocki A, Park H M, Lee S Y. Blind source separation and independent component analysis: a review. Neural Information Processing —Letters and Reviews, 2005, 6(1): 1-57[3] Tang Ying, Li Jian-Ping. A new algorithm of ICA: using the parametrized orthogonal matrixes of any dimensions. Acta Automatica Sinica, 2008, 34(1): 31-39(汤影, 李建平. 利用参数表示任意维数正交矩阵的ICA新算法. 自动化学报, 2008, 34(1): 31-39)[4] Feng D Z, Zheng W X, Cichochi A. Matrix-group algorithm via improved whitening process for extracting statistically independent sources from array signals. IEEE Transactions on Signal Processing, 2007, 55(3): 962-977[5] Mollah M N, Eguchi S, Minami M. Robust prewhitening for ICA by minimizing β -divergence and its application to fastICA. Neural Processing Letters, 2007, 25(2): 91-110[6] Kocinski J, Libiszewski P, Sek A. Spatial efficiency of blind source separation based on decorrelation —subjective and objective assessment. Speech Communication, 2011, 53(3): 390-402[7] Coviello C M, Yoon P A, Sibul L H. Source separation and tracking for time-varying systems. IEEE Transactions on Aerospace and Electronic Systems, 2008, 44(3): 1198-1214[8] Douglas S C, Cichocki A. Adaptive step size techniques for decorrelation and blind source separation. In: Proceedings of the 32th Asilomar Conference on Signals, Systems, and Computers. Pacific Grove, USA: IEEE, 1998. 1191-1195[9] Ou S F, Zhao X H, Gao Y. Variable step size technique for adaptive blind decorrelation. In: Proceedings of the 8th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing. Qingdao, China: IEEE, 2007. 823-826[10] Yuan L X, Wang W W, Chambers J A. Variable step-size sign natural gradient algorithm for sequential blind source separation. IEEE Signal Processing Letters, 2005, 12(8): 589-592[11] Hsieh S T, Sun T Y, Lin C L, Liu C C. Effective learning rate adjustment of blind source separation based on an improved particle swarm optimizer. IEEE Transactions on Evolutionary Computation, 2008, 12(2): 242-251[12] Arenas-Garcia J, Gomez-Verdejo V, Figueiras-Vidal A R. New algorithms for improved adaptive convex combination of LMS transversal filters. IEEE Transactions on Instrumentation and Measurement, 2005, 54(6): 2239-2249[13] Mkadem F, Boumaiza S. Physically inspired neural network model for RF power amplifier behavioral modeling and digital predistortion. IEEE Transactions on Microwave Theory and Techniques, 2011, 59(4): 913-923[14] Zhang Z, Cui C, Liu K. Iterative hard-threshold algorithm with momentum. Electronics Letters, 2011, 47(4): 257-259[15] Xia C L, Guo C, Shi T N. A neural-network-identifier and fuzzy-controller-based algorithm for dynamic decoupling control of permanent-magnet spherical motor. IEEE Transactions on Industrial Electronics, 2010, 57(8): 2868-2878[16] Craven B D, Mond B. Linear programming with matrix variables. Linear Algebra and Its Applications, 1981, 38: 73-80[17] Qian N. On the momentum term in gradient descent learning algorithms. Neural Networks, 1999, 12(1): 145-151

施引文献

资源附件(0)

访问统计