Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer Interface

A brain computer interface BCI enables direct communication between a brain and a computer translating brain activity into computer commands using preprocessing, feature extraction, and classification operations. Feature extraction is crucial, as it has a substantial effect on the classification acc...

Full description

Saved in:
Bibliographic Details
Main Authors: Chu Kiong Loo, Andrews Samraj, Gin Chong Lee
Format: Article
Language:English
Published: Wiley 2011-01-01
Series:Discrete Dynamics in Nature and Society
Online Access:http://dx.doi.org/10.1155/2011/724697
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850159122483249152
author Chu Kiong Loo
Andrews Samraj
Gin Chong Lee
author_facet Chu Kiong Loo
Andrews Samraj
Gin Chong Lee
author_sort Chu Kiong Loo
collection DOAJ
description A brain computer interface BCI enables direct communication between a brain and a computer translating brain activity into computer commands using preprocessing, feature extraction, and classification operations. Feature extraction is crucial, as it has a substantial effect on the classification accuracy and speed. While fractal dimension has been successfully used in various domains to characterize data exhibiting fractal properties, its usage in motor imagery-based BCI has been more recent. In this study, commonly used fractal dimension estimation methods to characterize time series Katz's method, Higuchi's method, rescaled range method, and Renyi's entropy were evaluated for feature extraction in motor imagery-based BCI by conducting offline analyses of a two class motor imagery dataset. Different classifiers fuzzy k-nearest neighbours FKNN, support vector machine, and linear discriminant analysis were tested in combination with these methods to determine the methodology with the best performance. This methodology was then modified by implementing the time-dependent fractal dimension TDFD, differential fractal dimension, and differential signals methods to determine if the results could be further improved. Katz's method with FKNN resulted in the highest classification accuracy of 85%, and further improvements by 3% were achieved by implementing the TDFD method.
format Article
id doaj-art-5f9555432a5f4292a5f14609cce0b05b
institution OA Journals
issn 1026-0226
1607-887X
language English
publishDate 2011-01-01
publisher Wiley
record_format Article
series Discrete Dynamics in Nature and Society
spelling doaj-art-5f9555432a5f4292a5f14609cce0b05b2025-08-20T02:23:40ZengWileyDiscrete Dynamics in Nature and Society1026-02261607-887X2011-01-01201110.1155/2011/724697724697Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer InterfaceChu Kiong Loo0Andrews Samraj1Gin Chong Lee2Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, MalaysiaSchool of Computing Science and Engineering, VIT University, Chennai Campus, Vandalor-Kellambakkam Road, Chennai 48, IndiaFaculty of Engineering and Technology, Multimedia University, Jalan Ayer Keroh Lama, 75450 Malacca, MalaysiaA brain computer interface BCI enables direct communication between a brain and a computer translating brain activity into computer commands using preprocessing, feature extraction, and classification operations. Feature extraction is crucial, as it has a substantial effect on the classification accuracy and speed. While fractal dimension has been successfully used in various domains to characterize data exhibiting fractal properties, its usage in motor imagery-based BCI has been more recent. In this study, commonly used fractal dimension estimation methods to characterize time series Katz's method, Higuchi's method, rescaled range method, and Renyi's entropy were evaluated for feature extraction in motor imagery-based BCI by conducting offline analyses of a two class motor imagery dataset. Different classifiers fuzzy k-nearest neighbours FKNN, support vector machine, and linear discriminant analysis were tested in combination with these methods to determine the methodology with the best performance. This methodology was then modified by implementing the time-dependent fractal dimension TDFD, differential fractal dimension, and differential signals methods to determine if the results could be further improved. Katz's method with FKNN resulted in the highest classification accuracy of 85%, and further improvements by 3% were achieved by implementing the TDFD method.http://dx.doi.org/10.1155/2011/724697
spellingShingle Chu Kiong Loo
Andrews Samraj
Gin Chong Lee
Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer Interface
Discrete Dynamics in Nature and Society
title Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer Interface
title_full Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer Interface
title_fullStr Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer Interface
title_full_unstemmed Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer Interface
title_short Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer Interface
title_sort evaluation of methods for estimating fractal dimension in motor imagery based brain computer interface
url http://dx.doi.org/10.1155/2011/724697
work_keys_str_mv AT chukiongloo evaluationofmethodsforestimatingfractaldimensioninmotorimagerybasedbraincomputerinterface
AT andrewssamraj evaluationofmethodsforestimatingfractaldimensioninmotorimagerybasedbraincomputerinterface
AT ginchonglee evaluationofmethodsforestimatingfractaldimensioninmotorimagerybasedbraincomputerinterface