Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...

You might also read

Related Articles

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

Sort by

Same author

Corticospinal tract reconstruction with tumor by using a novel direction filter based tractography method.

Medical & biological engineering & computing·2025

Same author

SMANet: A Model Combining SincNet, Multi-Branch Spatial-Temporal CNN, and Attention Mechanism for Motor Imagery BCI.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2025

Same author

Enhancing the performance of SSVEP-based BCIs by combining task-related component analysis and deep neural network.

Scientific reports·2025

Same author

Prognostic factors and surgical approaches in the analysis of primary central nervous system diffuse large B-cell lymphoma: a large population-based cohort study and external validation.

Frontiers in neurology·2024

Same author

Tensor decomposition-based channel selection for motor imagery-based brain-computer interfaces.

Cognitive neurodynamics·2024

Same author

<i>De novo</i> assembly and characterization of the transcriptome of <i>Morchella esculenta</i> growth with selenium supplementation.

PeerJ·2024

Search research articles

Related Experiment Video

Updated: Sep 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A deep learning model combining convolutional neural networks and a selective kernel mechanism for SSVEP-Based BCIs.

Shengwei Huang¹, Qingguo Wei¹

¹Department of Information and Communication Engineering, School of Information Engineering, Nanchang University, Nanchang, 330031, China.

Computers in Biology and Medicine

|July 2, 2025

Summary

A new deep learning model, FBCNN-TKS, improves brain-computer interfaces (BCIs) using steady-state visually evoked potentials (SSVEPs). It enhances feature extraction and reduces overfitting, leading to higher accuracy and information transfer rates for BCIs.

Keywords:

Brain-computer interface (BCI)Deep learning Frequency recognition Selective kernel mechanism Steady-state visual evoked potentials (SSVEP)

More Related Videos

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

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

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

Published on: July 7, 2023

Related Experiment Videos

Last Updated: Sep 17, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

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

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

Published on: July 7, 2023

Area of Science:

Neuroscience and Artificial Intelligence
Brain-Computer Interface (BCI) Technology

Background:

Existing deep learning models for steady-state visually evoked potential (SSVEP) brain-computer interfaces (BCIs) struggle with insufficient training data, leading to overfitting.
Limited receptive fields in current models hinder the effective capture of global temporal features in SSVEP signals.

Purpose of the Study:

To introduce a novel deep learning model, FBCNN-TKS, designed to overcome the limitations of existing SSVEP-BCI methods.
To enhance feature extraction capabilities and improve classification accuracy and information transfer rates (ITR) in SSVEP-BCIs.

Main Methods:

The FBCNN-TKS model utilizes a filter bank to extract harmonic components from SSVEP signals.
Feature extraction is performed using convolutional neural networks (CNNs) integrated with a temporal kernel selection (TKS) module.
A combined objective function of cross-entropy loss and center loss optimizes the model, employing dilated and grouped convolutions within the TKS module to reduce parameters and prevent overfitting.

Main Results:

The FBCNN-TKS model demonstrated superior performance compared to state-of-the-art methods on public datasets Benchmark and BETA.
Achieved highest accuracies of 83.10% and 72.98% with information transfer rates (ITR) of 251.54 bpm and 203.47 bpm, respectively, at a 0.4s data length.
The TKS module significantly improved feature extraction by providing a broader receptive field.

Conclusions:

The FBCNN-TKS model effectively addresses overfitting and enhances temporal feature extraction in SSVEP-BCIs.
The proposed model shows significant potential for developing high-performance SSVEP-BCI systems, particularly for character spelling applications.
The integration of TKS module, dilated, and grouped convolutions offers a promising direction for future BCI research.