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

Test-retest reliability and feature selection in physiological time series classification.

Steinn Gudmundsson1, Thomas Philip Runarsson, Sven Sigurdsson

  • 1Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, School of Engineering and Natural Science, University of Iceland, Hjardarhagi 2-6, 107 Reykjavik, Iceland. steinng@hi.is

Computer Methods and Programs in Biomedicine
|September 25, 2010
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

Convolutional Neural Networks for Seizure Detection: A Study on Training Strategies.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

A genome-scale metabolic reconstruction provides insight into the metabolism of the thermophilic bacterium Rhodothermus marinus.

FEMS microbiology ecology·2024
Same author

Temperature Dependence of Platelet Metabolism.

Metabolites·2024
Same author

Transdermal Drug Delivery: Determining Permeation Parameters Using Tape Stripping and Numerical Modeling.

Pharmaceutics·2022
Same author

Ensemble Learning Using Individual Neonatal Data for Seizure Detection.

IEEE journal of translational engineering in health and medicine·2022
Same author

Argininosuccinate lyase is a metabolic vulnerability in breast development and cancer.

NPJ systems biology and applications·2021
Same journal

MMFVS-Net: A triple-symmetric cross-attention network for multimodal optical image fusion and high-accuracy virtual staining of breast cancer tissues.

Computer methods and programs in biomedicine·2026
Same journal

A novel Milstein-stochastic epidemiologically-informed neural network for approaching epidemic dynamics: Application to Mpox disease.

Computer methods and programs in biomedicine·2026
Same journal

Accounting for approximation errors using surrogate-based parameter estimation of cardiac mechanics digital twins.

Computer methods and programs in biomedicine·2026
Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026
Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026
Same journal

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026
See all related articles

Feature test-retest reliability can help select relevant features for time series classification. This method avoids accuracy loss by excluding unreliable features before training classification models.

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Signal Processing

Background:

  • Feature selection is crucial for effective time series classification.
  • Test-retest reliability is a potential metric for evaluating feature relevance.

Purpose of the Study:

  • To investigate the utility of feature test-retest reliability for feature selection in physiological time series classification.
  • To determine if low reliability can be used to exclude irrelevant features and improve classifier performance.

Main Methods:

  • Examined three sets of physiological time series: electroencephalogram (EEG), electrocardiogram (ECG), and neck movement.
  • Compared reliability estimates from test-retest studies with feature importance measures from classification tasks.

Related Experiment Videos

Main Results:

  • Low feature reliability was identified as an indicator of irrelevant features.
  • Excluding features with low reliability helped prevent unnecessary degradation of classifier accuracy.

Conclusions:

  • Feature test-retest reliability is a valuable criterion for excluding irrelevant features in time series classification.
  • Utilizing reliability metrics can enhance the efficiency and accuracy of classification models by pre-emptively removing suboptimal features.