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

Title: Multimodal Fusion of Clinical and Imaging Data for Early Prediction of Massive Transfusion in Trauma.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

Design, Synthesis, Anti-Oomycete, Antifungal, and Nematicidal Activities of 2'-Acyloxyfenjuntong Derivatives.

Chemistry & biodiversity·2026
Same author

Leveraging Natural Language Processing and Structured Scoring to Evaluate Operative Note Quality in Surgical Training.

Journal of surgical education·2026
Same author

RescueGPT: An Automated System for Detecting Adverse Safety Events in Prehospital Emergency Medical Service Notes With a Zero-Shot Approach With Large Language Models: A Proof-of-Concept Study.

Learning health systems·2026
Same author

Gdf15 expression in thermogenic adipocytes regulates diet-induced weight gain in a sex-dependent manner.

Molecular medicine (Cambridge, Mass.)·2026
Same author

Erratum: Alpha-ketoglutarate alleviates acute pancreatitis by restoring energy metabolism.

iScience·2026
Same journal

MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback.

Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting·2026
Same journal

Capturing Human Cognitive Styles with Language: Towards an Experimental Evaluation Paradigm.

Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting·2025
Same journal

Pedagogically Aligned Objectives Create Reliable Automatic Cloze Tests.

Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting·2025
Same journal

PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning.

Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting·2025
Same journal

Protein2Text: Resampling Mechanism to Translate Protein Sequences into Human-Interpretable Text.

Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting·2025
Same journal

ALBA: Adaptive Language-Based Assessments for Mental Health.

Proceedings of the conference. Association for Computational Linguistics. North American Chapter. Meeting·2025
See all related articles

Related Experiment Video

Updated: Nov 7, 2025

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

741

A Multi-Context Character Prediction Model for a Brain-Computer Interface.

Shiran Dudy1, Steven Bedrick1, Shaobin Xu2

  • 1Center for Spoken, Language Understanding, Oregon Health & Science University, Portland, OR, USA.

Proceedings of the Conference. Association for Computational Linguistics. North American Chapter. Meeting
|May 3, 2021
PubMed
Summary
This summary is machine-generated.

Brain-computer interfaces present unique language modeling challenges due to noisy electroencephalogram (EEG) signals. Our Online-Context Language Model (OCLM) improves prediction accuracy by considering word information and ambiguous histories.

More Related Videos

Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.4K
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

2.8K

Related Experiment Videos

Last Updated: Nov 7, 2025

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

741
Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.4K
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

2.8K

Area of Science:

  • Neuroscience
  • Computer Science
  • Biomedical Engineering

Background:

  • Brain-computer interfaces (BCIs) and augmentative and alternative communication (AAC) devices face distinct language modeling challenges.
  • Noisy electroencephalogram (EEG) signals in BCIs complicate the deciphering of user intent.
  • Existing character-entry methods struggle with the inherent ambiguity of BCI data.

Purpose of the Study:

  • To develop a more robust prediction system for BCIs and AAC devices.
  • To address the challenge of noisy EEG signals and ambiguous user intent.
  • To introduce the Online-Context Language Model (OCLM) for improved language modeling.

Main Methods:

  • Proposed an Online-Context Language Model (OCLM) that maintains ambiguous history for each time step.
  • Integrated word information alongside the traditional character language model.
  • Compared OCLM performance against current algorithms used in BCI settings.

Main Results:

  • Evaluated the OCLM using perplexity and predictive accuracy metrics.
  • Demonstrated promising results in handling ambiguous histories.
  • Showcased improved next-character prediction distribution for BCI front-ends.

Conclusions:

  • The OCLM offers a more robust approach to language modeling in noisy BCI environments.
  • Considering ambiguous histories and word information enhances prediction accuracy.
  • OCLM shows potential for improving user experience and efficiency in BCI and AAC applications.