Blind Extraction Based on Fractional Lower-Order Statistics
The conventional method to extract interesting source signals sequentially is based on the secondorder or higher-order statistics of signals, however, it fails for impulsive sources because of the degeneration of the second-order and higher-order statistics. Based on the best compression-reconstruction principle, a new contrast function is proposed in this work, together with the corresponding algorithm. It is the first method used for blind extraction of sources which distribute from alpha stable process. Simulations are given to illustrate availability and robustness of our algorithm.
Zuyuan Yang Caiyun Chen
School of Electrics & Information Engineering South China University of Technology Guangzhou,510641 P.R.China
国际会议
南宁
英文
2007-07-20（万方平台首次上网日期，不代表论文的发表时间）