Document Detail


A spectral clustering approach to underdetermined postnonlinear blind source separation of sparse sources.
MedLine Citation:
PMID:  16722185     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
This letter proposes a clustering-based approach for solving the underdetermined (i.e., fewer mixtures than sources) postnonlinear blind source separation (PNL BSS) problem when the sources are sparse. Although various algorithms exist for the underdetermined BSS problem for sparse sources, as well as for the PNL BSS problem with as many mixtures as sources, the nonlinear problem in an underdetermined scenario has not been satisfactorily solved yet. The method proposed in this letter aims at inverting the different nonlinearities, thus reducing the problem to linear underdetermined BSS. To this end, first a spectral clustering technique is applied that clusters the mixture samples into different sets corresponding to the different sources. Then, the inverse nonlinearities are estimated using a set of multilayer perceptrons (MLPs) that are trained by minimizing a specifically designed cost function. Finally, transforming each mixture by its corresponding inverse nonlinearity results in a linear underdetermined BSS problem, which can be solved using any of the existing methods.
Authors:
Steven Van Vaerenbergh; Ignacio Santamaría
Related Documents :
9339335 - Two-dimensional cancellation neglect a review and suggested method of analysis.
18428735 - Analyzing and visualizing expression data with spotfire.
17155095 - Subdimension-based similarity measure for dna microarray data clustering.
20825395 - Likelihood methods for binary responses of present components in a cluster.
10642785 - A three-dimensional model of the mouse at embryonic day 9.
23990765 - Stochasticity, bistability and the wisdom of crowds: a model for associative learning i...
Publication Detail:
Type:  Letter; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  17     ISSN:  1045-9227     ISO Abbreviation:  -     Publication Date:  2006 May 
Date Detail:
Created Date:  2006-05-25     Completed Date:  2006-06-20     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  101211035     Medline TA:  IEEE Trans Neural Netw     Country:  United States    
Other Details:
Languages:  eng     Pagination:  811-4     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms*
Artificial Intelligence*
Cluster Analysis*
Information Storage and Retrieval / methods*
Neural Networks (Computer)
Nonlinear Dynamics
Pattern Recognition, Automated / methods*
Systems Theory

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  A comparison between habituation and conscience mechanism in self-organizing maps.
Next Document:  Stability analysis for stochastic Cohen-Grossberg neural networks with mixed time delays.