A novel method for block ambiguities of independent component analysis using previous demixing matrices

Zhiyong Zhou; Mingxi Guo; Hao Duan; Shengyu Nie; Wei Zhao

doi:10.1117/12.2245309

29 August 2016 A novel method for block ambiguities of independent component analysis using previous demixing matrices

Zhiyong Zhou, Mingxi Guo, Hao Duan, Shengyu Nie, Wei Zhao

Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 1003354 (2016) https://doi.org/10.1117/12.2245309
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China

Abstract

This manuscript deals with the permutation and scaling ambiguities inherent to an Independent Component Analysis (ICA) framework when continuously mixed signals are split in time and processed in a block-by-block manner. For each adjacent block, we choose the demixing matrix of the previous block as the initialization matrix for separating the subsequent block. By using the demixing matrices of the previous blocks, the separation process of the subsequent blocks is largely simplified, and the corresponding computational cost is thereby significantly reduced. Therefore, compared with previous similar methods, our proposed method is much more efficient in terms of computational speed, which is particularly striking when a large number of blocks is applied. We conducted simulations to validate the effectiveness of our proposed method.

Citation Download Citation

Zhiyong Zhou, Mingxi Guo, Hao Duan, Shengyu Nie, and Wei Zhao "A novel method for block ambiguities of independent component analysis using previous demixing matrices", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 1003354 (29 August 2016); https://doi.org/10.1117/12.2245309

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available