Independent component analysis algorithm for blind separation of fMRI signals

Li Li Pan; Zhen Wei Shi; Huan Wen Tang; Yi Yuan Tang; Wei Wei Zhang

Independent component analysis algorithm for blind separation of fMRI signals

Li Li Pan, Zhen Wei Shi, Huan Wen Tang, Yi Yuan Tang, Wei Wei Zhang

Research output: Contribution to journal › Article › peer-review

Abstract

An optimization model for independent component analysis (ICA) is built. A new gradient algorithm based on the model is presented, which is called Orth-ExtBS algorithm. This algorithm combines the advantages of the FastICA and ExtBS algorithms, which is easy to use in simple form and is able to separate blindly mixed signals with sub-Gaussian and super-Gaussian source distributions. The accuracy of the Orth-ExtBS algorithm is high and its convergence speed is fast. Applying the Orth-ExtBS algorithm and two other algorithms (FastICA and ExtBS) to fMRI data, the results show that the new algorithm is superior to the other two on accuracy of estimating the temporal dynamics of activations by comparison.

Original language	English (US)
Pages (from-to)	607-611
Number of pages	5
Journal	Dalian Ligong Daxue Xuebao/Journal of Dalian University of Technology
Volume	45
Issue number	4
State	Published - Jul 2005
Externally published	Yes

Keywords

Blind source separation
Functional magnetic resonance imaging
Gradient algorithm
Independent component analysis

ASJC Scopus subject areas

Engineering(all)
Physics and Astronomy(all)
Applied Mathematics

Cite this

@article{63fd4e19057b425cbf134f2b290099f1,

title = "Independent component analysis algorithm for blind separation of fMRI signals",

abstract = "An optimization model for independent component analysis (ICA) is built. A new gradient algorithm based on the model is presented, which is called Orth-ExtBS algorithm. This algorithm combines the advantages of the FastICA and ExtBS algorithms, which is easy to use in simple form and is able to separate blindly mixed signals with sub-Gaussian and super-Gaussian source distributions. The accuracy of the Orth-ExtBS algorithm is high and its convergence speed is fast. Applying the Orth-ExtBS algorithm and two other algorithms (FastICA and ExtBS) to fMRI data, the results show that the new algorithm is superior to the other two on accuracy of estimating the temporal dynamics of activations by comparison.",

keywords = "Blind source separation, Functional magnetic resonance imaging, Gradient algorithm, Independent component analysis",

author = "Pan, {Li Li} and Shi, {Zhen Wei} and Tang, {Huan Wen} and Tang, {Yi Yuan} and Zhang, {Wei Wei}",

year = "2005",

month = jul,

language = "English (US)",

volume = "45",

pages = "607--611",

journal = "Dalian Ligong Daxue Xuebao/Journal of Dalian University of Technology",

issn = "1000-8608",

publisher = "Dalian University of Technology",

number = "4",

}

TY - JOUR

T1 - Independent component analysis algorithm for blind separation of fMRI signals

AU - Pan, Li Li

AU - Shi, Zhen Wei

AU - Tang, Huan Wen

AU - Tang, Yi Yuan

AU - Zhang, Wei Wei

PY - 2005/7

Y1 - 2005/7

N2 - An optimization model for independent component analysis (ICA) is built. A new gradient algorithm based on the model is presented, which is called Orth-ExtBS algorithm. This algorithm combines the advantages of the FastICA and ExtBS algorithms, which is easy to use in simple form and is able to separate blindly mixed signals with sub-Gaussian and super-Gaussian source distributions. The accuracy of the Orth-ExtBS algorithm is high and its convergence speed is fast. Applying the Orth-ExtBS algorithm and two other algorithms (FastICA and ExtBS) to fMRI data, the results show that the new algorithm is superior to the other two on accuracy of estimating the temporal dynamics of activations by comparison.

AB - An optimization model for independent component analysis (ICA) is built. A new gradient algorithm based on the model is presented, which is called Orth-ExtBS algorithm. This algorithm combines the advantages of the FastICA and ExtBS algorithms, which is easy to use in simple form and is able to separate blindly mixed signals with sub-Gaussian and super-Gaussian source distributions. The accuracy of the Orth-ExtBS algorithm is high and its convergence speed is fast. Applying the Orth-ExtBS algorithm and two other algorithms (FastICA and ExtBS) to fMRI data, the results show that the new algorithm is superior to the other two on accuracy of estimating the temporal dynamics of activations by comparison.

KW - Blind source separation

KW - Functional magnetic resonance imaging

KW - Gradient algorithm

KW - Independent component analysis

UR - http://www.scopus.com/inward/record.url?scp=25144460729&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=25144460729&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:25144460729

SN - 1000-8608

VL - 45

SP - 607

EP - 611

JO - Dalian Ligong Daxue Xuebao/Journal of Dalian University of Technology

JF - Dalian Ligong Daxue Xuebao/Journal of Dalian University of Technology

IS - 4

ER -

Independent component analysis algorithm for blind separation of fMRI signals

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this