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

Convolution Properties II01:17

Convolution Properties II

586
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
586
Convolution Properties I01:20

Convolution Properties I

595
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
595
Protein-protein Interfaces02:04

Protein-protein Interfaces

14.7K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
14.7K
Protein-Protein Interfaces02:04

Protein-Protein Interfaces

4.5K
4.5K
Protein Networks02:26

Protein Networks

4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
Protein Networks02:26

Protein Networks

2.9K
2.9K

You might also read

Related Articles

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

Sort by
Same author

Early prediction and risk assessment of adverse drug combinations using ensemble learning.

Scientific reports·2026
Same author

Explainable CNN framework for accurate crop disease detection using plant leaf images.

Scientific reports·2026
Same author

Enhancing underwater sensor network security using QKD-enabled acoustic-optical hybrid communication.

Scientific reports·2026
Same author

Explainable multimodal feature fusion networks for Parkinson's disease prediction.

Frontiers in digital health·2026
Same author

AI driven automation for enhancing sustainability efforts in CDP report analysis.

Scientific reports·2025
Same author

A Cluster-Based Energy-Efficient Secure Optimal Path-Routing Protocol for Wireless Body-Area Sensor Networks.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Feb 1, 2026

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

18.4K

Adversarial robust EEG-based brain-computer interfaces using a hierarchical convolutional neural network.

Jebin Samuel1, Tamilarasi Kathirvel Murugan2, Logeswari Govindaraj1

  • 1School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, 600127, India.

Scientific Reports
|January 30, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a Hierarchical Convolutional Neural Network (HCNN) to enhance the security of Brain-Computer Interfaces (BCIs) against adversarial attacks. The HCNN improves classification accuracy and robustness for electroencephalography (EEG) based motor decoding.

Keywords:
Adversarial attackBrain–computer interfacesCommon spatial patternsConvolutional neural networksElectroencephalographyPerturbation methods

More Related Videos

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

955
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K

Related Experiment Videos

Last Updated: Feb 1, 2026

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

18.4K
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

955
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K

Area of Science:

  • Neuroscience and Artificial Intelligence
  • Brain-Computer Interface (BCI) technology
  • Machine Learning for neural signal processing

Background:

  • Electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) are crucial for motor rehabilitation and assistive technologies.
  • Deep learning, especially Convolutional Neural Networks (CNNs), has advanced motor imagery (MI) and motor execution (ME) classification.
  • EEG-BCIs are susceptible to adversarial attacks, compromising safety in critical applications.

Purpose of the Study:

  • To propose a novel three-level Hierarchical Convolutional Neural Network (HCNN) to enhance BCI classification performance and adversarial robustness.
  • To investigate a hierarchical approach for decoding motor intentions, improving reliability in EEG-based BCIs.

Main Methods:

  • Developed a three-level HCNN framework to hierarchically decode motor intentions: MI vs. ME, unilateral vs. bilateral, and fine-grained movement classification.
  • Evaluated the HCNN on the BCI Competition IV-2a dataset using multi-class MI EEG recordings from healthy subjects.
  • Assessed robustness against gradient-based adversarial attacks (FGSM, PGD, DeepFool) with adversarial training.

Main Results:

  • The proposed HCNN achieved a clean-data accuracy of 91.2% on the BCI Competition IV-2a dataset.
  • The HCNN demonstrated significantly reduced performance degradation under adversarial attacks compared to baseline CNNs.
  • Hierarchical architectures show promise for improving the reliability and security of EEG-based BCIs.

Conclusions:

  • The HCNN framework effectively improves both classification accuracy and adversarial robustness in EEG-based BCIs.
  • Hierarchical processing is a viable strategy for developing more secure and reliable BCI systems.
  • This research contributes to safer and more dependable applications of BCIs in rehabilitation and assistive control.