Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Efficient source adaptivity in independent component analysis.

N Vlassis¹, Y Motomura

¹RWCP, Autonomous Learning Functions SNN, Department of Computer Science, University of Amsterdam, Kruislaan 403, 1098 SJ Amsterdam, The Netherlands. vlassis@science.uva.nl

IEEE Transactions on Neural Networks

|February 6, 2008

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Calcineurin inhibitors exacerbate coronary arteritis via the MyD88 signalling pathway in a murine model of Kawasaki disease.

Clinical and experimental immunology·2017

Same author

Evaluation of circadian phenotypes utilizing fibroblasts from patients with circadian rhythm sleep disorders.

Translational psychiatry·2017

Same author

Kawasaki disease: a matter of innate immunity.

Clinical and experimental immunology·2016

Same author

Pretherapeutic evaluation of buried bumper syndrome by endoscopic ultrasonography.

Endoscopy·2012

Same author

Capsule endoscopic detection of bleeding Meckel's diverticulum, with capsule retention in the diverticulum.

Endoscopy·2010

Same author

Endoscopic submucosal dissection of early colorectal tumors using a grasping-type scissors forceps: a preliminary clinical study.

Endoscopy·2010

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

This study introduces a novel method for independent component analysis (ICA) that directly estimates source score functions from data. This source-adaptive approach improves accuracy over existing methods, especially for large datasets.

Area of Science:

Signal Processing
Machine Learning
Statistical Analysis

Background:

Independent Component Analysis (ICA) relies on accurate modeling of source score functions.
Traditional ICA methods often use approximations for score functions, limiting accuracy.
Large datasets present challenges for existing ICA score function estimation techniques.

Purpose of the Study:

To develop a source-adaptive ICA method for improved accuracy.
To enable direct estimation of true source score functions from data.
To enhance ICA performance on large datasets.

Main Methods:

Extending Silverman's fast density estimation method for score function estimation.
Implementing an efficient scheme for direct estimation of source score functions.

Related Experiment Videos

Utilizing real and synthetic data for validation.

Main Results:

The proposed method achieves "source adaptivity" by estimating true score functions.
Demonstrated improved accuracy compared to state-of-the-art methods.
Performance gains are notable when optimization is near the global minimum.

Conclusions:

Direct estimation of source score functions offers a significant advantage in ICA.
The developed method provides a more accurate and efficient ICA solution.
This approach is particularly beneficial for large-scale data analysis in signal processing.