A Concrete Independent Component Analysis Algorithm Based on the Estimating Function

Author

Xue, Yunfeng ; Han, Yujie ; Wang, Yuja

Author_Institution

Sch. of Electron. & Electr. Eng., Shanghai Second Polytech. Univ., Shanghai, China

fYear

2010

fDate

25-27 June 2010

Firstpage

4590

Lastpage

4593

Abstract

A concrete independent component analysis algorithm is proposed in this paper. The algorithm is based on the concept of estimating functions. Newton´s method is used to solve the estimating equation iteratively, To achieve the source adaptivity, the density functions as well as their first and second derivatives are estimated by kernel density method. Empirical comparisons with several popular ICA algorithms confirm the efficiency and accuracy of the proposed algorithm.

Keywords

Newton method; estimation theory; independent component analysis; signal processing; ICA algorithm; Newton method; density function; estimating function; first derivative; independent component analysis; kernel density method; second derivative; signal processing; source adaptivity; Algorithm design and analysis; Concrete; Equations; Kernel; Mathematical model; Newton method; Signal processing algorithms; Newton´s method; estimating function; independent component analysis; kernel density estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Control Engineering (ICECE), 2010 International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-6880-5

Type

conf

DOI

10.1109/iCECE.2010.1108

Filename

5631903