Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Blind source separation by sparse decomposition in a signal dictionary.

M Zibulevsky1, B A Pearlmutter

  • 1Department of Computer Science, University of New Mexico, Albuquerque, NM 87131, USA.

Neural Computation
|March 20, 2001
PubMed
Summary

This study introduces a novel two-stage method for blind source separation, enhancing signal extraction from mixed data. The technique leverages sparse signal representation for improved accuracy in various applications.

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

Sparsity-based single-shot subwavelength coherent diffractive imaging.

Nature materials·2012
Same author

A 12-channel, real-time near-infrared spectroscopy instrument for brain-computer interface applications.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2009
Same author

The design and implementation of COSEM, an iterative algorithm for fully 3-D listmode data.

IEEE transactions on medical imaging·2001
Same author

Time-Skew Hebb rule in a nonisopotential neuron.

Neural computation·1995
Same author

Gradient calculations for dynamic recurrent neural networks: a survey.

IEEE transactions on neural networks·1995
Same author

Comments on ;Dynamic programming approach to optimal weight selection in multilayer neural networks' [with reply].

IEEE transactions on neural networks·1992

Area of Science:

  • Signal Processing
  • Machine Learning

Background:

  • Blind source separation aims to recover original signals from mixed inputs when the mixing process is unknown.
  • This is a prevalent challenge in diverse fields like acoustics, medical imaging, and hyperspectral imaging.

Purpose of the Study:

  • To develop an effective two-stage approach for blind source separation.
  • To improve signal recovery accuracy by utilizing sparse signal properties.

Main Methods:

  • A two-stage separation process involving a priori dictionary selection (e.g., wavelet frames, learned dictionaries).
  • Exploiting sparse representability of source signals for unmixing.
  • Developing algorithms for both overcomplete and non-overcomplete dictionary cases, including scenarios with more sources than mixtures.

Related Experiment Videos

Main Results:

  • Demonstrated significantly improved separation performance compared to existing methods.
  • Experimental validation using artificial signals and musical audio data.

Conclusions:

  • The proposed method offers superior performance in blind source separation tasks.
  • The approach is effective across different signal types and dictionary conditions.