Study of Learning Entropy for onset detection of epileptic seizures in EEG time series

Ivo Bukovsky; Matous Cejnek; Jan Vrba; Noriyasu Homma

doi:10.1109/IJCNN.2016.7727621

Study of Learning Entropy for onset detection of epileptic seizures in EEG time series

Ivo Bukovsky, Matous Cejnek, Jan Vrba, Noriyasu Homma

MED - Health Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

This paper presents a case study of non-Shannon entropy, i.e. Learning Entropy (LE), for instant detection of onset of epileptic seizures in individual EEG time series. Contrary to entropy methods of EEG evaluation that are based on probabilistic computations, we present the LE-based approach that evaluates the conformity of individual samples of data to the contemporary learned governing law of a learning system and thus LE can detect changes of dynamics on individual samples of data. For comparison, the principle and the results are compared to the Sample Entropy approach. The promising results indicate the LE potentials for feature extraction enhancement for early detection of epileptic seizures on individual-data-sample basis.

Original language	English
Title of host publication	2016 International Joint Conference on Neural Networks, IJCNN 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3302-3305
Number of pages	4
ISBN (Electronic)	9781509006199
DOIs	https://doi.org/10.1109/IJCNN.2016.7727621
Publication status	Published - 2016 Oct 31
Event	2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada Duration: 2016 Jul 24 → 2016 Jul 29

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2016-October

Other

Other	2016 International Joint Conference on Neural Networks, IJCNN 2016
Country/Territory	Canada
City	Vancouver
Period	16/7/24 → 16/7/29

Keywords

Adaptive novelty detection
EEG time series
Epileptic seizure
Higher order neural units
Incremental learning
Learning Entropy
Non-Shannon entropy
Onset detection
Sample Entropy

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2016.7727621

Cite this

Bukovsky, I., Cejnek, M., Vrba, J., & Homma, N. (2016). Study of Learning Entropy for onset detection of epileptic seizures in EEG time series. In 2016 International Joint Conference on Neural Networks, IJCNN 2016 (pp. 3302-3305). [7727621] (Proceedings of the International Joint Conference on Neural Networks; Vol. 2016-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2016.7727621

Study of Learning Entropy for onset detection of epileptic seizures in EEG time series. / Bukovsky, Ivo; Cejnek, Matous; Vrba, Jan et al.
2016 International Joint Conference on Neural Networks, IJCNN 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 3302-3305 7727621 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2016-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Bukovsky, I, Cejnek, M, Vrba, J & Homma, N 2016, Study of Learning Entropy for onset detection of epileptic seizures in EEG time series. in 2016 International Joint Conference on Neural Networks, IJCNN 2016., 7727621, Proceedings of the International Joint Conference on Neural Networks, vol. 2016-October, Institute of Electrical and Electronics Engineers Inc., pp. 3302-3305, 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, Canada, 16/7/24. https://doi.org/10.1109/IJCNN.2016.7727621

Bukovsky I, Cejnek M, Vrba J, Homma N. Study of Learning Entropy for onset detection of epileptic seizures in EEG time series. In 2016 International Joint Conference on Neural Networks, IJCNN 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 3302-3305. 7727621. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2016.7727621

@inproceedings{e78313d49360490ca18cd900cfbb1352,

title = "Study of Learning Entropy for onset detection of epileptic seizures in EEG time series",

abstract = "This paper presents a case study of non-Shannon entropy, i.e. Learning Entropy (LE), for instant detection of onset of epileptic seizures in individual EEG time series. Contrary to entropy methods of EEG evaluation that are based on probabilistic computations, we present the LE-based approach that evaluates the conformity of individual samples of data to the contemporary learned governing law of a learning system and thus LE can detect changes of dynamics on individual samples of data. For comparison, the principle and the results are compared to the Sample Entropy approach. The promising results indicate the LE potentials for feature extraction enhancement for early detection of epileptic seizures on individual-data-sample basis.",

keywords = "Adaptive novelty detection, EEG time series, Epileptic seizure, Higher order neural units, Incremental learning, Learning Entropy, Non-Shannon entropy, Onset detection, Sample Entropy",

author = "Ivo Bukovsky and Matous Cejnek and Jan Vrba and Noriyasu Homma",

note = "Funding Information: This work was supported by the Grant Agency of the Czech Technical University in Prague, grant No. SGS15118910HK2/3T/12, and also by JSPS KAKENHI Grants No. 25293258 and No. 26540112. Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 International Joint Conference on Neural Networks, IJCNN 2016 ; Conference date: 24-07-2016 Through 29-07-2016",

year = "2016",

month = oct,

day = "31",

doi = "10.1109/IJCNN.2016.7727621",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3302--3305",

booktitle = "2016 International Joint Conference on Neural Networks, IJCNN 2016",

}

TY - GEN

T1 - Study of Learning Entropy for onset detection of epileptic seizures in EEG time series

AU - Bukovsky, Ivo

AU - Cejnek, Matous

AU - Vrba, Jan

AU - Homma, Noriyasu

N1 - Funding Information: This work was supported by the Grant Agency of the Czech Technical University in Prague, grant No. SGS15118910HK2/3T/12, and also by JSPS KAKENHI Grants No. 25293258 and No. 26540112. Publisher Copyright: © 2016 IEEE.

PY - 2016/10/31

Y1 - 2016/10/31

N2 - This paper presents a case study of non-Shannon entropy, i.e. Learning Entropy (LE), for instant detection of onset of epileptic seizures in individual EEG time series. Contrary to entropy methods of EEG evaluation that are based on probabilistic computations, we present the LE-based approach that evaluates the conformity of individual samples of data to the contemporary learned governing law of a learning system and thus LE can detect changes of dynamics on individual samples of data. For comparison, the principle and the results are compared to the Sample Entropy approach. The promising results indicate the LE potentials for feature extraction enhancement for early detection of epileptic seizures on individual-data-sample basis.

AB - This paper presents a case study of non-Shannon entropy, i.e. Learning Entropy (LE), for instant detection of onset of epileptic seizures in individual EEG time series. Contrary to entropy methods of EEG evaluation that are based on probabilistic computations, we present the LE-based approach that evaluates the conformity of individual samples of data to the contemporary learned governing law of a learning system and thus LE can detect changes of dynamics on individual samples of data. For comparison, the principle and the results are compared to the Sample Entropy approach. The promising results indicate the LE potentials for feature extraction enhancement for early detection of epileptic seizures on individual-data-sample basis.

KW - Adaptive novelty detection

KW - EEG time series

KW - Epileptic seizure

KW - Higher order neural units

KW - Incremental learning

KW - Learning Entropy

KW - Non-Shannon entropy

KW - Onset detection

KW - Sample Entropy

UR - http://www.scopus.com/inward/record.url?scp=85007197218&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007197218&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2016.7727621

DO - 10.1109/IJCNN.2016.7727621

M3 - Conference contribution

AN - SCOPUS:85007197218

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 3302

EP - 3305

BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 International Joint Conference on Neural Networks, IJCNN 2016

Y2 - 24 July 2016 through 29 July 2016

ER -

Study of Learning Entropy for onset detection of epileptic seizures in EEG time series

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this