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

Determination of the Mechanisms of Terbium(III) Biosorption by <i>Bacillus</i> Strains with Adsorption Selectivity for Heavy Rare Earth Elements.

Microorganisms·2025
Same author

Significant weight gain benefits of nanocrystalline megestrol acetate for patients with cancer anorexia-cachexia syndrome.

Translational cancer research·2025
Same author

Evaluating high-resolution aviation emissions using real-time flight data.

The Science of the total environment·2024
Same author

Assessing the particulate matter emission reduction characteristics of small turbofan engine fueled with 100 % HEFA sustainable aviation fuel.

The Science of the total environment·2024
Same author

A convolutional neural network prediction model for aviation nitrogen oxides emissions throughout all flight phases.

The Science of the total environment·2024
Same author

Ligulariatinside A, a new sesquiterpene glycoside from roots of <i>Ligularia veitchiana</i>.

Natural product research·2023

Related Experiment Video

Updated: Sep 27, 2025

Using an EEG-Based Brain-Computer Interface for Virtual Cursor Movement with BCI2000
12:07

Using an EEG-Based Brain-Computer Interface for Virtual Cursor Movement with BCI2000

Published on: July 29, 2009

17.9K

A Noninvasive BCI System for 2D Cursor Control Using a Spectral-Temporal Long Short-Term Memory Network.

Kang Pan1, Li Li1, Lei Zhang1

  • 1Department of Automation Science and Electrical Engineering, Beihang University, Beijing, China.

Frontiers in Computational Neuroscience
|April 11, 2022
PubMed
Summary

This study introduces a novel electroencephalography (EEG) decoding framework using a spectral-temporal long short-term memory (stLSTM) network for precise two-dimensional (2D) cursor control in brain-computer interfaces (BCIs). The method significantly improves cursor control accuracy by reducing trajectory errors.

Keywords:
brain-computer interfaceelectroencephalographyspectral-temporal LSTM networktwo-dimensional cursor controlvelocity-constrained loss

More Related Videos

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
07:43

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

7.9K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.5K

Related Experiment Videos

Last Updated: Sep 27, 2025

Using an EEG-Based Brain-Computer Interface for Virtual Cursor Movement with BCI2000
12:07

Using an EEG-Based Brain-Computer Interface for Virtual Cursor Movement with BCI2000

Published on: July 29, 2009

17.9K
Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
07:43

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

7.9K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.5K

Area of Science:

  • Neuroscience
  • Computer Science
  • Biomedical Engineering

Background:

  • Two-dimensional (2D) cursor control using electroencephalography (EEG)-based brain-computer interfaces (BCIs) presents significant challenges.
  • Existing BCIs often struggle with generating accurate and smooth control trajectories due to categorical output limitations.

Purpose of the Study:

  • To propose a novel EEG decoding framework for accurate and smooth 2D cursor control.
  • To enhance BCI performance by integrating spectral and temporal features for improved trajectory generation.

Main Methods:

  • A spectral-temporal long short-term memory (stLSTM) network was developed for EEG decoding.
  • Spectral information decoded motor imagery intention, while error-related P300 detected trajectory deviations.
  • A velocity-constrained (VC) strategy mapped features to cursor velocities, fitting intended movement and suppressing unintended movement.

Main Results:

  • The proposed stLSTM framework demonstrated superior performance on a public BCI dataset.
  • Root Mean Square Error (RMSE) in non-imaginary directions was reduced by an average of 63.45% compared to state-of-the-art methods.
  • Visualization confirmed accurate cursor control in complex tasks, highlighting the effectiveness of velocity decoupling.

Conclusions:

  • The novel stLSTM-based EEG decoding framework significantly enhances 2D cursor control accuracy and trajectory smoothness in BCIs.
  • The velocity-constrained strategy effectively decouples intended cursor movement, leading to improved performance in complex control tasks.