Automatic detection of absence seizures with compressive sensing EEG

Research output: Contribution to journalArticlepeer-review

Standard

Automatic detection of absence seizures with compressive sensing EEG. / Zeng, Ke; Yan, Jiaqing; Wang, Yinghua; Sik, Attila; Ouyang, Gaoxiang; Li, Xiaoli.

In: Neurocomputing, Vol. 171, 01.2016, p. 497-502.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Zeng, Ke ; Yan, Jiaqing ; Wang, Yinghua ; Sik, Attila ; Ouyang, Gaoxiang ; Li, Xiaoli. / Automatic detection of absence seizures with compressive sensing EEG. In: Neurocomputing. 2016 ; Vol. 171. pp. 497-502.

Bibtex

@article{9d20af6c776641b0b2aa23b06f139f79,
title = "Automatic detection of absence seizures with compressive sensing EEG",
abstract = "Absence epilepsy, a neurological disorder, is characterized by the recurrence of seizures, which have serious impact on the sufferers' daily life. The seizure detection has a great importance in the diagnosis and therapy of epileptic patients. Visual inspection of the electroencephalogram (EEG) signals for detection of interictal, pre-ictal and ictal activities is a strenuous and time-consuming task due to the huge volumes of EEG segments that have to be studied. In this study, we proposed a novel automatic detection method based on the altered compressibility of EEG during the three states with compressive sensing. To evaluate the proposed method, segments of interictal, pre-ictal and ictal EEG segments (100 segments in each state) were used. Two entropies, namely the Sample Entropy (SE) and the permutation Entropy (PE), and Hurst Index (HI) were extracted respectively from the segments to compare with the proposed method. Significant features were selected using the ANOVA test. After evaluating the performance of the selected features by four classifiers (Decision Tree, K-Nearest Neighbor, Discriminant Analysis, Support Vector Machine) respectively, the results show that the proposed method can achieve the highest accuracy of 76.7%, which is higher than HI (55.3%), sample entropy (71%), and permutation entropy (73%). Hence, the altered compressibility of EEG with CS can act as a good biomarker for distinguish seizure-free, per-seizure and seizure state. In addition, compressive sensing requires less energy but has competitive compression ratio compared to traditional compression techniques, which enables our method to tele-monitoring of epilepsy patients using wireless body-area networks in personalized medicine.",
keywords = "Absence seizure, Classification, Compressive sensing, EEG, Permutation entropy",
author = "Ke Zeng and Jiaqing Yan and Yinghua Wang and Attila Sik and Gaoxiang Ouyang and Xiaoli Li",
year = "2016",
month = jan,
doi = "10.1016/j.neucom.2015.06.076",
language = "English",
volume = "171",
pages = "497--502",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Automatic detection of absence seizures with compressive sensing EEG

AU - Zeng, Ke

AU - Yan, Jiaqing

AU - Wang, Yinghua

AU - Sik, Attila

AU - Ouyang, Gaoxiang

AU - Li, Xiaoli

PY - 2016/1

Y1 - 2016/1

N2 - Absence epilepsy, a neurological disorder, is characterized by the recurrence of seizures, which have serious impact on the sufferers' daily life. The seizure detection has a great importance in the diagnosis and therapy of epileptic patients. Visual inspection of the electroencephalogram (EEG) signals for detection of interictal, pre-ictal and ictal activities is a strenuous and time-consuming task due to the huge volumes of EEG segments that have to be studied. In this study, we proposed a novel automatic detection method based on the altered compressibility of EEG during the three states with compressive sensing. To evaluate the proposed method, segments of interictal, pre-ictal and ictal EEG segments (100 segments in each state) were used. Two entropies, namely the Sample Entropy (SE) and the permutation Entropy (PE), and Hurst Index (HI) were extracted respectively from the segments to compare with the proposed method. Significant features were selected using the ANOVA test. After evaluating the performance of the selected features by four classifiers (Decision Tree, K-Nearest Neighbor, Discriminant Analysis, Support Vector Machine) respectively, the results show that the proposed method can achieve the highest accuracy of 76.7%, which is higher than HI (55.3%), sample entropy (71%), and permutation entropy (73%). Hence, the altered compressibility of EEG with CS can act as a good biomarker for distinguish seizure-free, per-seizure and seizure state. In addition, compressive sensing requires less energy but has competitive compression ratio compared to traditional compression techniques, which enables our method to tele-monitoring of epilepsy patients using wireless body-area networks in personalized medicine.

AB - Absence epilepsy, a neurological disorder, is characterized by the recurrence of seizures, which have serious impact on the sufferers' daily life. The seizure detection has a great importance in the diagnosis and therapy of epileptic patients. Visual inspection of the electroencephalogram (EEG) signals for detection of interictal, pre-ictal and ictal activities is a strenuous and time-consuming task due to the huge volumes of EEG segments that have to be studied. In this study, we proposed a novel automatic detection method based on the altered compressibility of EEG during the three states with compressive sensing. To evaluate the proposed method, segments of interictal, pre-ictal and ictal EEG segments (100 segments in each state) were used. Two entropies, namely the Sample Entropy (SE) and the permutation Entropy (PE), and Hurst Index (HI) were extracted respectively from the segments to compare with the proposed method. Significant features were selected using the ANOVA test. After evaluating the performance of the selected features by four classifiers (Decision Tree, K-Nearest Neighbor, Discriminant Analysis, Support Vector Machine) respectively, the results show that the proposed method can achieve the highest accuracy of 76.7%, which is higher than HI (55.3%), sample entropy (71%), and permutation entropy (73%). Hence, the altered compressibility of EEG with CS can act as a good biomarker for distinguish seizure-free, per-seizure and seizure state. In addition, compressive sensing requires less energy but has competitive compression ratio compared to traditional compression techniques, which enables our method to tele-monitoring of epilepsy patients using wireless body-area networks in personalized medicine.

KW - Absence seizure

KW - Classification

KW - Compressive sensing

KW - EEG

KW - Permutation entropy

UR - http://www.scopus.com/inward/record.url?scp=84938125253&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2015.06.076

DO - 10.1016/j.neucom.2015.06.076

M3 - Article

VL - 171

SP - 497

EP - 502

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -