Optimisation and data mining techniques for the screening of epileptic patients

Ya Ju Fan; Wanpracha A. Chaovalitwongse; Chang Chia Liu; Rajesh C. Sachdeo; Leonidas D. Iasemidis; Panos M. Pardalos

doi:10.1504/IJBRA.2009.024036

Optimisation and data mining techniques for the screening of epileptic patients

Ya Ju Fan, Wanpracha A. Chaovalitwongse, Chang Chia Liu, Rajesh C. Sachdeo, Leonidas D. Iasemidis, Panos M. Pardalos

School of Medicine

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

Identifying abnormalities or anomalies by visual inspection on neurophysiologic signals such as ElectroEncephaloGrams (EEGs), is extremely challenging. We propose a novel Multi-Dimensional Time Series (MDTS) classification technique, called Connectivity Support Vector Machines (C-SVMs) that integrates brain connectivity network with SVMs. To filter noise in EEG data, Independent Component Analysis based on the Unbiased Quasi Newton Method was applied. C-SVM achieved 94.8% accuracy classifying subjects compared to 69.4% accuracy with standard SVMs. It suggests that C-SVM can be a rapid, yet accurate, technique for online differentiation between epileptic and normal subjects. It may solve other classification MDTS problems too.

Original language	English (US)
Pages (from-to)	187-196
Number of pages	10
Journal	International Journal of Bioinformatics Research and Applications
Volume	5
Issue number	2
DOIs	https://doi.org/10.1504/IJBRA.2009.024036
State	Published - Mar 2009

Keywords

Bioinformatics
Cross validation
Data mining
Epilepsy
Euclidean distance
Gaussian kernel

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Clinical Biochemistry
Health Information Management

Access to Document

10.1504/IJBRA.2009.024036

Cite this

@article{add04326ac77417692def6c04c187bbb,

title = "Optimisation and data mining techniques for the screening of epileptic patients",

abstract = "Identifying abnormalities or anomalies by visual inspection on neurophysiologic signals such as ElectroEncephaloGrams (EEGs), is extremely challenging. We propose a novel Multi-Dimensional Time Series (MDTS) classification technique, called Connectivity Support Vector Machines (C-SVMs) that integrates brain connectivity network with SVMs. To filter noise in EEG data, Independent Component Analysis based on the Unbiased Quasi Newton Method was applied. C-SVM achieved 94.8% accuracy classifying subjects compared to 69.4% accuracy with standard SVMs. It suggests that C-SVM can be a rapid, yet accurate, technique for online differentiation between epileptic and normal subjects. It may solve other classification MDTS problems too.",

keywords = "Bioinformatics, Cross validation, Data mining, Epilepsy, Euclidean distance, Gaussian kernel",

author = "Fan, {Ya Ju} and Chaovalitwongse, {Wanpracha A.} and Liu, {Chang Chia} and Sachdeo, {Rajesh C.} and Iasemidis, {Leonidas D.} and Pardalos, {Panos M.}",

year = "2009",

month = mar,

doi = "10.1504/IJBRA.2009.024036",

language = "English (US)",

volume = "5",

pages = "187--196",

journal = "International Journal of Bioinformatics Research and Applications",

issn = "1744-5485",

publisher = "Inderscience Enterprises Ltd",

number = "2",

}

TY - JOUR

T1 - Optimisation and data mining techniques for the screening of epileptic patients

AU - Fan, Ya Ju

AU - Chaovalitwongse, Wanpracha A.

AU - Liu, Chang Chia

AU - Sachdeo, Rajesh C.

AU - Iasemidis, Leonidas D.

AU - Pardalos, Panos M.

PY - 2009/3

Y1 - 2009/3

N2 - Identifying abnormalities or anomalies by visual inspection on neurophysiologic signals such as ElectroEncephaloGrams (EEGs), is extremely challenging. We propose a novel Multi-Dimensional Time Series (MDTS) classification technique, called Connectivity Support Vector Machines (C-SVMs) that integrates brain connectivity network with SVMs. To filter noise in EEG data, Independent Component Analysis based on the Unbiased Quasi Newton Method was applied. C-SVM achieved 94.8% accuracy classifying subjects compared to 69.4% accuracy with standard SVMs. It suggests that C-SVM can be a rapid, yet accurate, technique for online differentiation between epileptic and normal subjects. It may solve other classification MDTS problems too.

AB - Identifying abnormalities or anomalies by visual inspection on neurophysiologic signals such as ElectroEncephaloGrams (EEGs), is extremely challenging. We propose a novel Multi-Dimensional Time Series (MDTS) classification technique, called Connectivity Support Vector Machines (C-SVMs) that integrates brain connectivity network with SVMs. To filter noise in EEG data, Independent Component Analysis based on the Unbiased Quasi Newton Method was applied. C-SVM achieved 94.8% accuracy classifying subjects compared to 69.4% accuracy with standard SVMs. It suggests that C-SVM can be a rapid, yet accurate, technique for online differentiation between epileptic and normal subjects. It may solve other classification MDTS problems too.

KW - Bioinformatics

KW - Cross validation

KW - Data mining

KW - Epilepsy

KW - Euclidean distance

KW - Gaussian kernel

UR - http://www.scopus.com/inward/record.url?scp=63149127429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63149127429&partnerID=8YFLogxK

U2 - 10.1504/IJBRA.2009.024036

DO - 10.1504/IJBRA.2009.024036

M3 - Article

C2 - 19324604

AN - SCOPUS:63149127429

SN - 1744-5485

VL - 5

SP - 187

EP - 196

JO - International Journal of Bioinformatics Research and Applications

JF - International Journal of Bioinformatics Research and Applications

IS - 2

ER -

Optimisation and data mining techniques for the screening of epileptic patients

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this