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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Multimodal Data Approaches for Examining the 2024-2025 Highly Pathogenic Avian Influenza Outbreak in the United States: Descriptive Study.

JMIR public health and surveillance·2026
Same author

Unified framework for the ingestion of early epidemic data for downstream data analytics.

Wellcome open research·2026
Same author

Vitamin D May Increase the Number of CD4-CD8+ NKT-like Cells in Humans-A Novel Insight into Potential Immunomodulatory Action.

Nutrients·2025
Same author

An impact of type 2 diabetes mellitus on NKT-like cell population in humans: a new insight into impaired immune response in hyperglycemia.

Frontiers in endocrinology·2025
Same author

AI-Driven Innovations in Neuroradiology and Neurosurgery: Scoping Review of Current Evidence and Future Directions.

Cancers·2025
Same author

The role of nuclear energy in low carbon energy transition: evidence from panel data approach in EU.

Environmental science and pollution research international·2023

Related Experiment Video

Updated: Sep 19, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.7K

Supervised factor selection in tensor decomposition of EEG signal.

Stanisław Zakrzewski1, Bartłomiej Stasiak1, Adam Wojciechowski1

  • 1Institute of Information Technology, Lodz University of Technology, al. Politechniki 8, Lodz, 93-590, Poland.

Computer Methods and Programs in Biomedicine
|June 8, 2025
PubMed
Summary

This study introduces a novel tensor decomposition method for electroencephalography (EEG) data classification. The approach enhances motor imagery classification accuracy and provides interpretable results by statistically analyzing EEG signal components.

Keywords:
EEG analysisMotor imageryPARAFACTensor decomposition

More Related Videos

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

2.2K
Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.5K

Related Experiment Videos

Last Updated: Sep 19, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.7K
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

2.2K
Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.5K

Area of Science:

  • Multidimensional data analysis
  • Biomedical signal processing
  • Neuroscience

Background:

  • Tensor decomposition is valuable for analyzing complex data, including electroencephalography (EEG) signals.
  • Supervised training for EEG classification is hindered by the unsupervised nature of standard tensor factorization algorithms.

Purpose of the Study:

  • To develop a supervised learning method for EEG-based motor imagery classification using tensor decomposition.
  • To address limitations of unsupervised tensor factorization in brain-computer interface applications.

Main Methods:

  • Applied Parallel Factor Analysis (PARAFAC) to EEG data for motor imagery classification.
  • Utilized statistical analysis of PARAFAC factors to identify relevant signal components.
  • Developed a novel score function based on cosine similarity for optimal rank selection in tensor decomposition.

Main Results:

  • Significantly improved classification accuracy for high-performing subjects with suitable EEG signal length.
  • Demonstrated heatmap visualization of significant components for interpreting event-related synchronization/desynchronization.
  • Reduced input space dimensionality while maintaining high accuracy.

Conclusions:

  • The proposed method effectively combines tensor decomposition with statistical analysis for accurate and explainable EEG classification.
  • This approach offers a promising solution for brain-computer interfaces requiring high-dimensional EEG data analysis.
  • The method enhances interpretability and reduces computational complexity.