A novel algorithm for blind sources separation based on adaptive Givens rotations

摘要：

Blind Source Separation problems generally can be deduced to an optimization model with orthogonal constraints, and natural gradient algorithms are the main choices to tackle it by far. These algorithms converge relatively slowly and its separation speed and accuracy are sensitive to step parameter. Combining the merits of Givens rotations and natural gradient ingeniously, adaptive Givens rotations algorithm proposed by this article converges very fast and neednt any parameters. Simulations show the proposed algorithm is a robust and promising method in BSS and other similar problems.

作者: Guoxu Zhou Min Zhao

作者单位: School of Electronic and Information Engineering South China University of Technology Guangzhou, P.R.China 510641

会议类型: 国际会议

会议名称: Fourth International Conference on Impulsive and Hybrid Dynamical Systems(ICIHDS 2007)(第四届国际脉冲和混合动力系统学术会议)

会议地点: 南宁

会议语种:英文

在线出版日期: 2007-07-20（万方平台首次上网日期，不代表论文的发表时间）