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

You might also read

Related Articles

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

Sort by

Same author

Differential Neural Networks Prediction Using Slow and Fast Hybrid Learning: Application to Prognosis of Infectionsand Deaths of COVID-19 Dynamics.

Neural processing letters·2023

Same author

Intensification of Hydrogen Production by a Co-culture of Syntrophomonas wolfei and Rhodopseudomonas palustris Employing High Concentrations of Butyrate as a Substrate.

Applied biochemistry and biotechnology·2022

Same author

Study of the fatigue delamination behaviour of adhesive joints in carbon fibre reinforced epoxy composites, influence of the period of exposure to saline environment.

Scientific reports·2022

Same author

Deep Learning Adapted to Differential Neural Networks Used as Pattern Classification of Electrophysiological Signals.

IEEE transactions on pattern analysis and machine intelligence·2021

Same author

Multi-link endoscopic manipulator robot actuated by shape memory alloys spring actuators controlled by a sliding mode.

ISA transactions·2020

Same author

Effect of the type of soil on dimethyl phthalate degradation by ozone.

Journal of environmental management·2020

Search research articles

Related Experiment Video

Updated: Mar 21, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Pattern recognition for electroencephalographic signals based on continuous neural networks.

M Alfaro-Ponce¹, A Argüelles², I Chairez³

¹Escuela Superior de Tizayuca, Universidad Autonoma del Estado de Hidalgo, Tizayuca, Hidalgo, Mexico.

Neural Networks : the Official Journal of the International Neural Network Society

|May 2, 2016

Summary

This summary is machine-generated.

This study introduces a novel artificial neural network (ANN) algorithm for classifying electroencephalographic (EEG) signals. The continuous neural network (CNN) achieved 97.2% accuracy, outperforming existing methods on complex epilepsy and visual evoked potential datasets.

Keywords:

Continuous neural networks Electroencephalographic signals Pattern recognition Signal classifier

More Related Videos

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

Related Experiment Videos

Last Updated: Mar 21, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

Area of Science:

Biomedical Engineering
Computational Neuroscience
Machine Learning

Background:

Accurate classification of electroencephalographic (EEG) signals is crucial for diagnosing neurological disorders and understanding brain activity.
Existing pattern recognition algorithms face challenges in handling the complexity and variability of EEG data.

Purpose of the Study:

To design and implement a novel pattern recognition algorithm for EEG signal classification.
To develop a robust training method for continuous neural networks (CNNs) based on Lyapunov stability theory.
To evaluate the performance of the proposed algorithm on epilepsy and visual evoked potential (VEP) datasets.

Main Methods:

Utilized artificial neural networks (NNs) described by ordinary differential equations (ODEs) to create a continuous neural network (CNN).
Developed a training method grounded in Lyapunov theory for enhanced stability.
Implemented a parallel structure with fixed weights for efficient classification.
Validated the algorithm using generalization-regularization and k-fold cross-validation (k=5).

Main Results:

Achieved a maximum correct classification rate of 97.2% across a comprehensive dataset including epilepsy and VEP signals.
Demonstrated superior or comparable performance to existing methods, even when classifying more signal classes.
Successfully applied the CNN to two distinct databases, one with five epilepsy classes and another with three VEP classes.

Conclusions:

The proposed continuous neural network (CNN) offers a highly effective approach for EEG signal pattern recognition.
The Lyapunov-based training method ensures stable and reliable classification performance.
This algorithm holds significant potential for improving diagnostic accuracy and advancing brain-computer interfaces.