电子学报 ›› 2014, Vol. 42 ›› Issue (5): 992-997.DOI: 10.3969/j.issn.0372-2112.2014.05.025

• 科研通信 • 上一篇    下一篇

基于四阶累积张量方法的欠定盲源信号分离

葛素楠, 韩敏   

  1. 大连理工大学电子信息与电气工程学部, 辽宁大连 116024
  • 收稿日期:2012-06-05 修回日期:2014-01-17 出版日期:2014-05-25
    • 作者简介:
    • 葛素楠 女,1984年12月出生,山东滕州人,现为大连理工大学电子信息与电气工程学部在读博士研究生.研究方向为信号处理、脑电信号特征提取以及伪迹去除. E-mail:gesunan@mail.dlut.edu.cn韩 敏 女,1959年8月出生,吉林延吉人,教授、博士、博士生导师,大连理工大学模糊信息处理与机器智能研究所副所长.从事神经网络理论及其应用,复杂系统建模及自适应控制、智能技术及优化算法的研究. E-mail:minhan@dlut.edu.cn
    • 基金资助:
    • 国家自然科学基金 (No.61374154,No.61074096); 中央高校基本科研业务费专项 (No.DUT13JB08)

Fourth-Order Cumulant of Tensor Decomposition Method for Blind Identification of Underdetermined Separation

GE Su-nan, HAN Min   

  1. Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning 116024, China
  • Received:2012-06-05 Revised:2014-01-17 Online:2014-05-25 Published:2014-05-25
    • Supported by:
    • National Natural Science Foundation of China (No.61374154, No.61074096); Fundamental Research Funds for the Central Universities (No.DUT13JB08)

摘要: 针对瞬时欠定盲源信号分离问题,提出一种四阶累积张量分解算法.首先构建观察信号四阶累积协方差,依据源信号具有相互独立且均值为零的性质,对累积协方差化简并扩展到张量域,得到四阶累积张量.采用分层交替最小二乘算法对四阶累积张量进行非负库克分解,求得非负库克模型的参数,同时获得非负混合矩阵并求其伪逆,最终估计出源信号.选用真实的语音信号和生物信号进行仿真实验,结果表明该方法提高了源信号和非负混合矩阵的估计性能.

关键词: 欠定盲源信号分离, 分层交替最小二乘, 四阶累积张量分解, 库克分解

Abstract: This paper proposes a fourth order cunmulant of tensor decomposition method to solve the problem for blind identification of underdetermined separation.First,the fourth order cumulant of covariance is constructed based on observe signals.By assuming that the source signals are independent,and are of zero mean,the hierarchical alternating least squares method is used to decompose fourth order cumulant of tensor into the nonnegative Tucker.Then,the mixture matrix is acquired by the parameters of nonnegative Tucker model.The source is also acquired by solving the pseudo-inverse of mixture matrix.Finally,by using the speech signals and the biomedical signals,two numerical examples are conducted to demonstrate the effectiveness of the proposed method.

Key words: underdetermined source blind separation, hierarchical alternating least squares, fourth order cumulant of tensor decomposition, Tucker decomposition

中图分类号: