Title :
New BSS Algorithm of Four Order Cyclic Cumulant
Author :
Li Deng-Ao ; Ju-Min, Zhao ; Zhang Hai-yan ; Ma Qing-lun
Author_Institution :
Inst. of Electron. Inf. Eng., Taiyuan Univ. of Technol., Taiyuan, China
Abstract :
According to the nature of high order cumulant, defines the four order cyclic cumulant to solve the signal separation problem. If the mixed signals are independent of each other, its four order cyclic cumulant matrix is diagonal matrix. Taking use of this performance to modify the iterative learning rate of the objective function can separate the cyclostationary signals from the mixed signals effectively, simulation results prove the effection.
Keywords :
blind source separation; iterative methods; matrix algebra; BSS algorithm; cyclostationary signals; diagonal matrix; iterative learning rate; order cyclic cumulant matrix; signal separation problem; Blind source separation; Computational modeling; Data models; Modulation; Random processes; Signal processing algorithms;
Conference_Titel :
Pervasive Computing Signal Processing and Applications (PCSPA), 2010 First International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-8043-2
Electronic_ISBN :
978-0-7695-4180-8
DOI :
10.1109/PCSPA.2010.152