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

Information fusion methods based on physical laws.

Nageswara S V Rao1, David B Reister, Jacob Barhen

  • 1Center for Engineering Science Advanced Research, Computer Science and Mathematics Division, Oak Ridge National Laboratory, Mailstop 6061, Bldg. 5600, Oak Ridge, TN 37831, USA. raons@ornl.gov

IEEE Transactions on Pattern Analysis and Machine Intelligence
|January 5, 2005
PubMed
Summary

This study introduces a novel data fusion method that combines sensor measurements and estimations by minimizing violations of physical laws. This approach enhances parameter accuracy, outperforming individual measurements and estimates in methane hydrate exploration.

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

Optimal resource allocation for flexible-grid entanglement distribution networks.

Optics express·2022
Same author

Defense Strategies for Asymmetric Networked Systems with Discrete Components.

Sensors (Basel, Switzerland)·2018
Same author

Defense of Cyber Infrastructures Against Cyber-Physical Attacks Using Game-Theoretic Models.

Risk analysis : an official publication of the Society for Risk Analysis·2015
Same author

Quasiperiodic route to chaotic dynamics of internet transport protocols.

Physical review letters·2005
Same author

Covalent attachment of gold nanoparticles to DNA templates.

Journal of nanoscience and nanotechnology·2003

Area of Science:

  • Geophysics
  • Data Science
  • Sensor Fusion

Background:

  • Parameter estimation in complex systems is challenged by measurement errors (systematic and random).
  • Existing sample-based fusion methods are inapplicable when true parameter values are unknown, as is common in sensor networks.

Purpose of the Study:

  • To develop a robust data fusion method for combining sensor measurements and parameter estimations.
  • To ensure fused estimates adhere to known physical laws governing system parameters.
  • To provide performance guarantees for the proposed fusion method.

Main Methods:

  • A novel fusion method is proposed that minimizes the violation of physical laws relating system parameters.
  • The method accommodates both direct sensor measurements and prior estimations.

Related Experiment Videos

  • Asymptotic convergence and distribution-free performance bounds are derived under general conditions.

    • Main Results:

    • The proposed fusion method demonstrates asymptotic convergence.
    • Distribution-free performance bounds are established for finite samples.
    • The fused estimate is shown to be probabilistically superior to the best individual measurement or estimate.

    Conclusions:

    • The developed fusion method effectively integrates diverse data sources while respecting physical constraints.
    • This approach offers a significant improvement over existing methods for systems with unknown true parameter values.
    • The method's efficacy is validated through its application to well-log data fusion in methane hydrate exploration.