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

Advancing WBC Classification: A Hybrid ConvNextV2-Swin Transformer Framework with R3GAN Data Balancing and CLAHE Preprocessing.

Journal of imaging informatics in medicine·2025
Same author

Generative adversarial network: a statistical-based deep learning paradigm to improve detecting breast cancer in thermograms.

Medical & biological engineering & computing·2023
Same author

A Novel Pulse-Taking Device for Persian Medicine Based on Convolutional Neural Networks.

Journal of medical signals and sensors·2023
Same author

A New method for promote the performance of deep learning paradigm in diagnosing breast cancer: improving role of fusing multiple views of thermography images.

Health and technology·2022
Same author

Residual Learning: A New Paradigm to Improve Deep Learning-Based Segmentation of the Left Ventricle in Magnetic Resonance Imaging Cardiac Images.

Journal of medical signals and sensors·2021
Same author

Mobile sensor based human activity recognition: distinguishing of challenging activities by applying long short-term memory deep learning modified by residual network concept.

Biomedical engineering letters·2020

Related Experiment Video

Updated: Oct 31, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

729

A New Method to Improve the Performance of Deep Neural Networks in Detecting P300 Signals: Optimizing Curvature of

Seyed Vahab Shojaedini1, Sajedeh Morabbi2, Mohamad Reza Keyvanpour3

  • 1PhD, Associate professor in Biomedical Engineering, Department of Biomedical Engineering, Iranian Research Organization for Science and Technology, Tehran, Iran.

Journal of Biomedical Physics & Engineering
|June 30, 2021
PubMed
Summary

This study introduces a method to minimize error surface curvature in Convolutional Neural Networks (CNNs) for improved Brain Machine Interface (BMI) performance. The approach enhances P300 signal detection accuracy and reliability.

Keywords:
Brain-Computer InterfacesCurvature VariationDeep learningElectroencephalogramNeurosciencesP300 Signal Detection

More Related Videos

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K
Experimental and Data Analysis Workflow for Soft Matter Nanoindentation
13:04

Experimental and Data Analysis Workflow for Soft Matter Nanoindentation

Published on: January 18, 2022

4.3K

Related Experiment Videos

Last Updated: Oct 31, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

729
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K
Experimental and Data Analysis Workflow for Soft Matter Nanoindentation
13:04

Experimental and Data Analysis Workflow for Soft Matter Nanoindentation

Published on: January 18, 2022

4.3K

Area of Science:

  • Neuroscience
  • Computer Science
  • Machine Learning

Background:

  • Deep neural networks are crucial for P300 signal detection in Brain Machine Interface (BMI) systems.
  • High error surface curvature in these networks hinders optimal performance.
  • Minimizing curvature variations is essential for improving P300 detection.

Purpose of the Study:

  • To introduce a method for minimizing error surface curvature during Convolutional Neural Network (CNN) training.
  • To optimize deep neural network parameters to reduce curvature variations.
  • To enhance the performance of CNNs in P300 signal detection.

Main Methods:

  • Experimental tuning of CNN parameters influencing error surface curvature.
  • Utilizing Genetic Algorithm to optimize parameters and minimize curvature variations.
  • Evaluating the proposed method on the EPFL dataset.

Main Results:

  • The proposed method achieved a maximum classification accuracy of 98.91% for P300 signal detection.
  • A True Positive Ratio (TPR) of 98.54% was recorded.
  • Demonstrated significant improvements in P300 detection performance.

Conclusions:

  • Genetic algorithm-based curvature minimization enhances CNN accuracy for P300 detection.
  • The method reduces result variance, indicating increased reliability.
  • The proposed approach shows potential as a P300 detection module in BMI applications.