Signal Extraction Based on Modified nc-FastICA

摘要：

The complex fast independent component analysis (c-FastICA) algorithm is one of the most popular methods for solving the ICA problems with complex-valued data. Novey and Adali extend the Complex FastICA algorithm to noncircular sources, named noncircular FastICA (nc-FastICA). In this paper, we modify the noncircular FastICA to another form, termed as modified noncircular FastICA (mnc-FastICA), by minimizing the cost function with the constrained condition by another approach, which can solve the blind source separation problem of the instantaneous mixture case when the noncircular sources power ratio is unknown. Simulations are presented to demonstrate the effectiveness of our method.

关键词： blind source separation independent component analysis noncircular signals Newton method fixed-point update

作者: Hefa Zhang Wenshu Xiao Wanchun Li Liping Li

作者单位: School of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu, Nanjing Research Institute of Electronic Technology, Nanjing, China

会议类型: 国际会议

会议名称: 2010 International Conference on Image Analysis and Signal Processing(2010 图像分析与信号处理国际会议 IASP 10)

会议地点: 厦门

会议语种:英文

页码: 237-240

在线出版日期: 2010-04-12（万方平台首次上网日期，不代表论文的发表时间）