Model-based spike detection of epileptic EEG data

Yung Chun Liu, Chou Ching K Lin, Jing Jane Tsai, Yung Nien Sun

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this paper, a new two-stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is adopted to detect all possible spike candidates, then a newly proposed spike model with slow wave features is applied to these candidates for spike classification. Experimental results show that the proposed system, using the AdaBoost classifier, outperforms the conventional method in both two- and three-class EEG pattern classification problems. The proposed system not only achieves better accuracy for spike detection, but also provides new ability to differentiate between spikes and spikes with slow waves. Though spikes with slow waves occur frequently in epileptic EEGs, they are not used in conventional spike detection. Identifying spikes with slow waves allows the proposed system to have better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.

Original languageEnglish
Pages (from-to)12536-12547
Number of pages12
JournalSensors (Switzerland)
Volume13
Issue number9
DOIs
Publication statusPublished - 2013 Sep 17

Fingerprint

electroencephalography
Electroencephalography
spikes
Adaptive boosting
Pattern recognition
Classifiers
classifiers
examination

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Electrical and Electronic Engineering

Cite this

Liu, Yung Chun ; Lin, Chou Ching K ; Tsai, Jing Jane ; Sun, Yung Nien. / Model-based spike detection of epileptic EEG data. In: Sensors (Switzerland). 2013 ; Vol. 13, No. 9. pp. 12536-12547.
@article{502b348c1adc48ffba6a1f607dede31e,
title = "Model-based spike detection of epileptic EEG data",
abstract = "Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this paper, a new two-stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is adopted to detect all possible spike candidates, then a newly proposed spike model with slow wave features is applied to these candidates for spike classification. Experimental results show that the proposed system, using the AdaBoost classifier, outperforms the conventional method in both two- and three-class EEG pattern classification problems. The proposed system not only achieves better accuracy for spike detection, but also provides new ability to differentiate between spikes and spikes with slow waves. Though spikes with slow waves occur frequently in epileptic EEGs, they are not used in conventional spike detection. Identifying spikes with slow waves allows the proposed system to have better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.",
author = "Liu, {Yung Chun} and Lin, {Chou Ching K} and Tsai, {Jing Jane} and Sun, {Yung Nien}",
year = "2013",
month = "9",
day = "17",
doi = "10.3390/s130912536",
language = "English",
volume = "13",
pages = "12536--12547",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "9",

}

Model-based spike detection of epileptic EEG data. / Liu, Yung Chun; Lin, Chou Ching K; Tsai, Jing Jane; Sun, Yung Nien.

In: Sensors (Switzerland), Vol. 13, No. 9, 17.09.2013, p. 12536-12547.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Model-based spike detection of epileptic EEG data

AU - Liu, Yung Chun

AU - Lin, Chou Ching K

AU - Tsai, Jing Jane

AU - Sun, Yung Nien

PY - 2013/9/17

Y1 - 2013/9/17

N2 - Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this paper, a new two-stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is adopted to detect all possible spike candidates, then a newly proposed spike model with slow wave features is applied to these candidates for spike classification. Experimental results show that the proposed system, using the AdaBoost classifier, outperforms the conventional method in both two- and three-class EEG pattern classification problems. The proposed system not only achieves better accuracy for spike detection, but also provides new ability to differentiate between spikes and spikes with slow waves. Though spikes with slow waves occur frequently in epileptic EEGs, they are not used in conventional spike detection. Identifying spikes with slow waves allows the proposed system to have better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.

AB - Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this paper, a new two-stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is adopted to detect all possible spike candidates, then a newly proposed spike model with slow wave features is applied to these candidates for spike classification. Experimental results show that the proposed system, using the AdaBoost classifier, outperforms the conventional method in both two- and three-class EEG pattern classification problems. The proposed system not only achieves better accuracy for spike detection, but also provides new ability to differentiate between spikes and spikes with slow waves. Though spikes with slow waves occur frequently in epileptic EEGs, they are not used in conventional spike detection. Identifying spikes with slow waves allows the proposed system to have better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=84884369365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884369365&partnerID=8YFLogxK

U2 - 10.3390/s130912536

DO - 10.3390/s130912536

M3 - Article

C2 - 24048343

AN - SCOPUS:84884369365

VL - 13

SP - 12536

EP - 12547

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 9

ER -