欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2014, Vol. 31 ›› Issue (4): 530-536.DOI: 10.7523/j.issn.2095-6134.2014.04.013

• 信息与电子科学 • 上一篇    下一篇

基于非线性函数和简化粒子群优化的盲源分离算法

贾志成1, 王娜娜1, 陈雷2, 张艳1   

  1. 1. 河北工业大学信息工程学院, 天津 300401;
    2. 天津商业大学信息工程学院, 天津 300134
  • 收稿日期:2013-07-10 修回日期:2013-10-17 发布日期:2014-07-15
  • 通讯作者: 王娜娜,E-mail:wangnanasj@126.com
  • 基金资助:

    国家自然科学基金(61203245,11127202)资助

A blind source separation algorithm based on nonlinear function and simple particle swarm optimization

JIA Zhicheng1, WANG Nana1, CHEN Lei2, ZHANG Yan1   

  1. 1. School of Information Engineering, Hebei University of Technology, Tianjin 300401, China;
    2. School of Information Engineering, Tianjin University of Commerce,Tianjin 300134, China
  • Received:2013-07-10 Revised:2013-10-17 Published:2014-07-15

摘要:

针对现有盲源分离方法存在的源信号类型和高斯信号个数受限制问题,提出一种基于非线性函数和简化粒子群优化的盲源分离新算法.算法采用依据源信号类型选取的非线性函数作为目标函数,运用简化粒子群优化算法对目标函数进行优化,实现多类型源信号同时混合的盲源分离.仿真结果表明,本算法能够有效实现源信号为多类型和含有2路高斯信号的盲源分离.与其他算法相比,本算法收敛速度更快,分离精度更高.

关键词: 多类型源信号, 非线性函数, 简化粒子群优化, 盲源分离

Abstract:

A new blind source separation algorithm based on nonlinear function and simple particle swarm optimization was proposed, contraposing limitation problems for the source signal types and gaussian signal numbers. Nonlinear function was used as objective function based on source signal types, and then the simple particle swarm optimization was uesd to optimize the function. Simulation results show that the algorithm achieves the efficient separation for the blind source having various types of source signals and containing two gaussian signals. Compared with other algorithms, the proposed algorithm has fast convergence speed and high separation accuracy.

Key words: various types of source signal, nonlinear function, simple particle swarm optimization, blind source separation

中图分类号: