Fuzzy Hopfield neural network clustering for single-trial motor imagery EEG classification

Wei Yen Hsu

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

An electroencephalogram (EEG) analysis system for single-trial classification of motor imagery (MI) data is proposed in this study. Unsupervised fuzzy Hopfield neural network (FHNN) clustering, together with active segment selection and multiresolution fractal features, is used in the classification of left and right MI data. Active segment selection is used to obtain the active segment in the time-scale domain with the continuous wavelet transform (CWT) and Student's two-sample t-statistics. The multiresolution fractal features are then extracted from the discrete wavelet transform (DWT) data by using the modified fractal dimension. Finally, FHNN clustering is used as the discriminant of multiresolution fractal features. FHNN clustering is capable of making flexible partitions of a finite data set, and it is an unsupervised and robust approach suitable for the classification of non-stationary biomedical signals. Compared with several popular supervised classifiers, FHNN clustering achieves promising results in classification accuracy.

Original languageEnglish
Pages (from-to)1055-1061
Number of pages7
JournalExpert Systems with Applications
Volume39
Issue number1
DOIs
Publication statusPublished - Jan 2012
Externally publishedYes

Fingerprint

Hopfield neural networks
Fuzzy neural networks
Electroencephalography
Fractals
Discrete wavelet transforms
Fractal dimension
Wavelet transforms
Classifiers
Statistics
Students

Keywords

  • Brain-computer interface (BCI)
  • Electroencephalogram (EEG)
  • Fractal dimension (FD)
  • Fuzzy Hopfield neural network (FHNN)
  • Motor imagery (MI)
  • Wavelet transform

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

Fuzzy Hopfield neural network clustering for single-trial motor imagery EEG classification. / Hsu, Wei Yen.

In: Expert Systems with Applications, Vol. 39, No. 1, 01.2012, p. 1055-1061.

Research output: Contribution to journalArticle

@article{b83f0f04dae5471b9372a73d496a7d45,
title = "Fuzzy Hopfield neural network clustering for single-trial motor imagery EEG classification",
abstract = "An electroencephalogram (EEG) analysis system for single-trial classification of motor imagery (MI) data is proposed in this study. Unsupervised fuzzy Hopfield neural network (FHNN) clustering, together with active segment selection and multiresolution fractal features, is used in the classification of left and right MI data. Active segment selection is used to obtain the active segment in the time-scale domain with the continuous wavelet transform (CWT) and Student's two-sample t-statistics. The multiresolution fractal features are then extracted from the discrete wavelet transform (DWT) data by using the modified fractal dimension. Finally, FHNN clustering is used as the discriminant of multiresolution fractal features. FHNN clustering is capable of making flexible partitions of a finite data set, and it is an unsupervised and robust approach suitable for the classification of non-stationary biomedical signals. Compared with several popular supervised classifiers, FHNN clustering achieves promising results in classification accuracy.",
keywords = "Brain-computer interface (BCI), Electroencephalogram (EEG), Fractal dimension (FD), Fuzzy Hopfield neural network (FHNN), Motor imagery (MI), Wavelet transform",
author = "Hsu, {Wei Yen}",
year = "2012",
month = "1",
doi = "10.1016/j.eswa.2011.07.106",
language = "English",
volume = "39",
pages = "1055--1061",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "1",

}

TY - JOUR

T1 - Fuzzy Hopfield neural network clustering for single-trial motor imagery EEG classification

AU - Hsu, Wei Yen

PY - 2012/1

Y1 - 2012/1

N2 - An electroencephalogram (EEG) analysis system for single-trial classification of motor imagery (MI) data is proposed in this study. Unsupervised fuzzy Hopfield neural network (FHNN) clustering, together with active segment selection and multiresolution fractal features, is used in the classification of left and right MI data. Active segment selection is used to obtain the active segment in the time-scale domain with the continuous wavelet transform (CWT) and Student's two-sample t-statistics. The multiresolution fractal features are then extracted from the discrete wavelet transform (DWT) data by using the modified fractal dimension. Finally, FHNN clustering is used as the discriminant of multiresolution fractal features. FHNN clustering is capable of making flexible partitions of a finite data set, and it is an unsupervised and robust approach suitable for the classification of non-stationary biomedical signals. Compared with several popular supervised classifiers, FHNN clustering achieves promising results in classification accuracy.

AB - An electroencephalogram (EEG) analysis system for single-trial classification of motor imagery (MI) data is proposed in this study. Unsupervised fuzzy Hopfield neural network (FHNN) clustering, together with active segment selection and multiresolution fractal features, is used in the classification of left and right MI data. Active segment selection is used to obtain the active segment in the time-scale domain with the continuous wavelet transform (CWT) and Student's two-sample t-statistics. The multiresolution fractal features are then extracted from the discrete wavelet transform (DWT) data by using the modified fractal dimension. Finally, FHNN clustering is used as the discriminant of multiresolution fractal features. FHNN clustering is capable of making flexible partitions of a finite data set, and it is an unsupervised and robust approach suitable for the classification of non-stationary biomedical signals. Compared with several popular supervised classifiers, FHNN clustering achieves promising results in classification accuracy.

KW - Brain-computer interface (BCI)

KW - Electroencephalogram (EEG)

KW - Fractal dimension (FD)

KW - Fuzzy Hopfield neural network (FHNN)

KW - Motor imagery (MI)

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=81855218733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81855218733&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2011.07.106

DO - 10.1016/j.eswa.2011.07.106

M3 - Article

VL - 39

SP - 1055

EP - 1061

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 1

ER -