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

Brain Imaging01:14

Brain Imaging

Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans),  magnetic resonance imaging (MRI),  functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).
Storage01:23

Storage

A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze each...

You might also read

Related Articles

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

Sort by
Same journal

HDDI-Net: Hierarchical dual-domain interaction network for robust and efficient ultrasound lesion segmentation.

Medical & biological engineering & computing·2026
Same journal

Nonhomogeneous smoke mitigation in laparoscopic images using a hybrid physical-neural model.

Medical & biological engineering & computing·2026
Same journal

Individualized multimodal integration of optimized dual fluoroscopic imaging registration and finite element modeling for knee joint stress during stair ascent.

Medical & biological engineering & computing·2026
Same journal

Thorax shape reconstruction from limited CT-digitized palpable landmarks using statistical shape modeling.

Medical & biological engineering & computing·2026
Same journal

A coarse-to-fine machine-learning framework for identifying functional connectivity markers of cognitive impairment in Parkinson's disease.

Medical & biological engineering & computing·2026
Same journal

Design and clinical evaluation of a virtual reality-based system for automated ocular deviation measurement.

Medical & biological engineering & computing·2026

Related Experiment Video

Updated: Jul 1, 2026

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

15.1K

ThinkSTra: a transformer-driven architecture for decoding imagined speech from EEG with spatial-temporal dynamics.

Emrullah Şahin1, Durmuş Özdemir2

  • 1Faculty of Engineering, Department of Software Engineering, Kütahya Dumlupinar University, Kütahya, Türkiye. emrullah.sahin@dpu.edu.tr.

Medical & Biological Engineering & Computing
|November 12, 2025
PubMed
Summary

A new Transformer-based framework, ThinkSTra, decodes inner speech from brain signals with high accuracy. This advance in brain-computer interfaces offers new communication possibilities for individuals with motor impairments.

Keywords:
BCIEEGImagined speech classificationT-SNETransformer

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.4K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

12.2K

Related Experiment Videos

Last Updated: Jul 1, 2026

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

15.1K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.4K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

12.2K

Area of Science:

  • Neuroscience
  • Computer Science
  • Biomedical Engineering

Background:

  • Brain-Computer Interfaces (BCIs) offer communication pathways for individuals with motor impairments.
  • BCIs are valuable tools in clinical interventions and cognitive neuroscience research.

Purpose of the Study:

  • Introduce ThinkSTra, a novel Transformer-based framework for classifying inner speech commands from electroencephalography (EEG) signals.
  • Enhance EEG signal representation by jointly capturing temporal dynamics and spatial distributions.

Main Methods:

  • Developed ThinkSTra, a Transformer-based framework for inner speech classification.
  • Evaluated ThinkSTra on TSEEG and Kumar EEG datasets (sentence, character, digit, visual object tasks).
  • Conducted contribution analyses, pretraining, cross-validation, and t-SNE visualization for robustness assessment.

Main Results:

  • ThinkSTra achieved high accuracies: 100% (sentence-level), 98.10% (character), 98.34% (digit), and 99.5% (visual object).
  • Demonstrated superior performance compared to existing state-of-the-art methods.
  • Identified contributions of distinct cortical regions to inner speech decoding.

Conclusions:

  • ThinkSTra represents a robust advancement in inner speech decoding using EEG.
  • The framework provides methodological and neuroscientific insights for future BCIs.
  • Highlights the potential for improved communication and cognitive research through advanced BCIs.