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

Objective selection of hyperparameter for EIT.

B M Graham1, A Adler

  • 1School of Information Technology and Engineering, University of Ottawa, Canada. graham.bm@sympatico.ca

Physiological Measurement
|April 26, 2006
PubMed
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

Using electrical impedance tomography to estimate tidal volume in bottlenose dolphins and cape fur seals in seawater and on land.

The Journal of experimental biology·2026
Same author

First Measurement of the |t| Dependence of Incoherent J/ψ Photonuclear Production.

Physical review letters·2024
Same author

ψ(2S) Suppression in Pb-Pb Collisions at the LHC.

Physical review letters·2024
Same author

Measurements of Groomed-Jet Substructure of Charm Jets Tagged by D^{0} Mesons in Proton-Proton Collisions at sqrt[s]=13  TeV.

Physical review letters·2023
Same author

Measurement of the Lifetime and Λ Separation Energy of _{Λ}^{3}H.

Physical review letters·2023
Same author

Measurement of the J/ψ Polarization with Respect to the Event Plane in Pb-Pb Collisions at the LHC.

Physical review letters·2023
Same journal

Continuous tracking of aortic aneurysm diameter with peripheral pulse waves: a computational framework combining sequential Markov chain Monte Carlo with Kalman filtering.

Physiological measurement·2026
Same journal

The 2026 global roadmap for textile-integrated wearable technologies in health.

Physiological measurement·2026
Same journal

Augmenting single-lead ECG interpretation through QRS waveform decomposition and rotation.

Physiological measurement·2026
Same journal

Dynamic Beat-to-Beat Blood Pressure Estimation using a Multi-modal Wearable Deep Learning Approach.

Physiological measurement·2026
Same journal

Dual warm-start fusion versus attention-based fusion in low-label ECG-PCG classification: a controlled ablation study.

Physiological measurement·2026
Same journal

Inter-patient multi-label ECG classification via low-rank adaptation fine-tuned large language models with dynamic graph convolutional network.

Physiological measurement·2026
See all related articles

A new method, BestRes, objectively selects hyperparameters for electrical impedance tomography (EIT) image reconstruction, yielding stable results comparable to expert choices. This improves EIT imaging accuracy and reliability.

Area of Science:

  • Medical Imaging
  • Computational Science
  • Electrical Engineering

Background:

  • Electrical Impedance Tomography (EIT) is an ill-posed inverse problem requiring regularization for stable image reconstruction.
  • Hyperparameters control the balance between data fidelity and prior knowledge in EIT.
  • Objective hyperparameter selection remains a critical challenge for reliable EIT.

Purpose of the Study:

  • To propose and evaluate a novel algorithm for objective hyperparameter selection in linearized one-step EIT.
  • To compare the proposed method against existing hyperparameter selection strategies.
  • To assess the reliability and stability of EIT image reconstructions using different selection methods.

Main Methods:

  • Development of a calibration-based objective hyperparameter selection method termed BestRes.

Related Experiment Videos

  • Evaluation of five distinct hyperparameter selection strategies, including heuristic, generalized cross-validation, and L-curve approaches.
  • Comparative analysis of image reconstruction quality and stability across different methods.

    • Main Results:

    • Heuristic hyperparameter selections demonstrate inconsistency among experts.
    • Generalized cross-validation and L-curve methods yield suboptimal or unreliable EIT reconstructions.
    • The proposed BestRes method produces stable and repeatable EIT images comparable to expert-selected hyperparameters.
    • Analysis of reconstruction parameters enables reliable detection of inverse crime.

    Conclusions:

    • BestRes offers a robust and objective approach to hyperparameter selection for EIT.
    • The proposed method enhances the reliability and consistency of EIT image reconstruction.
    • Objective hyperparameter selection is crucial for accurate and trustworthy EIT analysis.