Search research articles

Search research articles

Related Experiment Videos

Multiclass support vector machines for EEG-signals classification.

Inan Güler¹, Elif Derya Ubeyli

¹Department of Electronics and Computer Education, Faculty of Technical Education, Gazi University, 06500 Teknikokullar, Ankara, Turkey.

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society

|March 30, 2007

Summary

This summary is machine-generated.

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

Designing and application of a new medical instrument sterilization system using reactive oxygen species.

The Review of scientific instruments·2021

Same author

P300-Based Asynchronous Brain Computer Interface for Environmental Control System.

IEEE journal of biomedical and health informatics·2017

Same author

The Use of Stepper Motor-Controlled Proportional Valve for Fio<sub>2</sub> Calculation in the Ventilator and its Control with Fuzzy Logic.

Journal of medical systems·2016

Same author

Design and Construction of a Microcontroller-Based Ventilator Synchronized with Pulse Oximeter.

Journal of medical systems·2016

Same author

Region based Brain Computer Interface for a home control application.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2016

Same author

Implementation of an Embedded Web Server Application for Wireless Control of Brain Computer Interface Based Home Environments.

Journal of medical systems·2015

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

This study introduces multiclass support vector machine (SVM) and probabilistic neural network (PNN) for electroencephalogram (EEG) signal classification. Wavelet coefficients and Lyapunov exponents proved effective features, achieving high classification accuracies.

Area of Science:

Biomedical Engineering
Computational Neuroscience
Machine Learning

Background:

Electroencephalogram (EEG) signal classification is crucial for diagnosing neurological disorders.
Existing methods face challenges in accurately classifying complex, multiclass EEG data.
Identifying robust features and optimal classifiers is essential for improving EEG analysis.

Purpose of the Study:

To evaluate the effectiveness of multiclass Support Vector Machine (SVM) with error-correcting output codes for EEG classification.
To compare the performance of SVM against Probabilistic Neural Network (PNN) and Multilayer Perceptron (MLP) for EEG signal classification.
To determine the optimal classification scheme and assess the significance of extracted features for EEG data.

Main Methods:

Related Experiment Videos

Feature extraction using wavelet coefficients and Lyapunov exponents.

Classification using multiclass SVM with error-correcting output codes, PNN, and MLP.

Two-stage decision making process involving feature extraction followed by classification.

Main Results:

Wavelet coefficients and Lyapunov exponents were identified as highly representative features for EEG signals.
Multiclass SVM and PNN demonstrated high classification accuracies when trained on these extracted features.
Comparative analysis confirmed the efficacy of the proposed feature extraction and classification approach.

Conclusions:

The combination of wavelet coefficients and Lyapunov exponents provides a robust feature set for EEG signal classification.
Multiclass SVM and PNN are effective classifiers for multiclass EEG problems, offering high accuracy.
The proposed methodology offers a promising approach for advancing EEG signal analysis and interpretation.