Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography

Nadia Mammone; Jonas Duun-Henriksen; Troels Wesenberg Kjr; Maurizio Campolo; Fabio La Foresta; Francesco C. Morabito

doi:10.1109/IJCNN.2015.7280615

Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography

Nadia Mammone, Jonas Duun-Henriksen, Troels Wesenberg Kjr, Maurizio Campolo, Fabio La Foresta, Francesco C. Morabito

IRCCS Centro Neurolesi "Bonino Pulejo"

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

Abstract

In this paper, we address the issue of dealing with huge amounts of data from recordings of an Electroencephalogram (EEG) in epileptic patients. In particular, the attention is focused on the development of tools to support the neurophysiologists in the time consuming and challenging task of reviewing the EEG to identify critical events that are worth of inspection for diagnostic purposes. A novel methodology is proposed for the automatic estimation of descriptors of EEG complexity and the subsequent classification of critical events. Based on the estimation of Permutation Entropy (PE) profiles from the EEG traces, the methodology relies on Learning Vector Quantization (LVQ) to cluster the electrodes in a competitive way according to their PE levels and to classify the cerebral state accordingly. An absence seizure EEG of 15.5 minutes was processed and a 93.94% sensitivity together with a 100% specificity were obtained.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Publisher	Institute of Electrical and Electronics Engineers Inc.
Volume	2015-September
ISBN (Print)	9781479919604, 9781479919604, 9781479919604, 9781479919604
DOIs	https://doi.org/10.1109/IJCNN.2015.7280615
Publication status	Published - Sep 28 2015
Event	International Joint Conference on Neural Networks, IJCNN 2015 - Killarney, Ireland Duration: Jul 12 2015 → Jul 17 2015

Other

Other	International Joint Conference on Neural Networks, IJCNN 2015
Country	Ireland
City	Killarney
Period	7/12/15 → 7/17/15

Keywords

Electroencephalography
Logic gates
Neurons

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2015.7280615

Fingerprint Dive into the research topics of 'Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography'. Together they form a unique fingerprint.

Cite this

Mammone, N., Duun-Henriksen, J., Kjr, T. W., Campolo, M., La Foresta, F., & Morabito, F. C. (2015). Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2015-September). [7280615] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2015.7280615

Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography. / Mammone, Nadia; Duun-Henriksen, Jonas; Kjr, Troels Wesenberg; Campolo, Maurizio; La Foresta, Fabio; Morabito, Francesco C.

Proceedings of the International Joint Conference on Neural Networks. Vol. 2015-September Institute of Electrical and Electronics Engineers Inc., 2015. 7280615.

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

Mammone, N, Duun-Henriksen, J, Kjr, TW, Campolo, M, La Foresta, F & Morabito, FC 2015, Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography. in Proceedings of the International Joint Conference on Neural Networks. vol. 2015-September, 7280615, Institute of Electrical and Electronics Engineers Inc., International Joint Conference on Neural Networks, IJCNN 2015, Killarney, Ireland, 7/12/15. https://doi.org/10.1109/IJCNN.2015.7280615

Mammone N, Duun-Henriksen J, Kjr TW, Campolo M, La Foresta F, Morabito FC. Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography. In Proceedings of the International Joint Conference on Neural Networks. Vol. 2015-September. Institute of Electrical and Electronics Engineers Inc. 2015. 7280615 https://doi.org/10.1109/IJCNN.2015.7280615

Mammone, Nadia ; Duun-Henriksen, Jonas ; Kjr, Troels Wesenberg ; Campolo, Maurizio ; La Foresta, Fabio ; Morabito, Francesco C. / Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography. Proceedings of the International Joint Conference on Neural Networks. Vol. 2015-September Institute of Electrical and Electronics Engineers Inc., 2015.

@inproceedings{70f530ccc5ef4b578964c6d827e4cba2,

title = "Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography",

abstract = "In this paper, we address the issue of dealing with huge amounts of data from recordings of an Electroencephalogram (EEG) in epileptic patients. In particular, the attention is focused on the development of tools to support the neurophysiologists in the time consuming and challenging task of reviewing the EEG to identify critical events that are worth of inspection for diagnostic purposes. A novel methodology is proposed for the automatic estimation of descriptors of EEG complexity and the subsequent classification of critical events. Based on the estimation of Permutation Entropy (PE) profiles from the EEG traces, the methodology relies on Learning Vector Quantization (LVQ) to cluster the electrodes in a competitive way according to their PE levels and to classify the cerebral state accordingly. An absence seizure EEG of 15.5 minutes was processed and a 93.94% sensitivity together with a 100% specificity were obtained.",

keywords = "Electroencephalography, Logic gates, Neurons",

author = "Nadia Mammone and Jonas Duun-Henriksen and Kjr, {Troels Wesenberg} and Maurizio Campolo and {La Foresta}, Fabio and Morabito, {Francesco C.}",

year = "2015",

month = sep,

day = "28",

doi = "10.1109/IJCNN.2015.7280615",

language = "English",

isbn = "9781479919604",

volume = "2015-September",

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

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

note = "International Joint Conference on Neural Networks, IJCNN 2015 ; Conference date: 12-07-2015 Through 17-07-2015",

}

TY - GEN

T1 - Learning Vector Quantization and Permutation Entropy to analyse epileptic electroencephalography

AU - Mammone, Nadia

AU - Duun-Henriksen, Jonas

AU - Kjr, Troels Wesenberg

AU - Campolo, Maurizio

AU - La Foresta, Fabio

AU - Morabito, Francesco C.

PY - 2015/9/28

Y1 - 2015/9/28

N2 - In this paper, we address the issue of dealing with huge amounts of data from recordings of an Electroencephalogram (EEG) in epileptic patients. In particular, the attention is focused on the development of tools to support the neurophysiologists in the time consuming and challenging task of reviewing the EEG to identify critical events that are worth of inspection for diagnostic purposes. A novel methodology is proposed for the automatic estimation of descriptors of EEG complexity and the subsequent classification of critical events. Based on the estimation of Permutation Entropy (PE) profiles from the EEG traces, the methodology relies on Learning Vector Quantization (LVQ) to cluster the electrodes in a competitive way according to their PE levels and to classify the cerebral state accordingly. An absence seizure EEG of 15.5 minutes was processed and a 93.94% sensitivity together with a 100% specificity were obtained.

AB - In this paper, we address the issue of dealing with huge amounts of data from recordings of an Electroencephalogram (EEG) in epileptic patients. In particular, the attention is focused on the development of tools to support the neurophysiologists in the time consuming and challenging task of reviewing the EEG to identify critical events that are worth of inspection for diagnostic purposes. A novel methodology is proposed for the automatic estimation of descriptors of EEG complexity and the subsequent classification of critical events. Based on the estimation of Permutation Entropy (PE) profiles from the EEG traces, the methodology relies on Learning Vector Quantization (LVQ) to cluster the electrodes in a competitive way according to their PE levels and to classify the cerebral state accordingly. An absence seizure EEG of 15.5 minutes was processed and a 93.94% sensitivity together with a 100% specificity were obtained.

KW - Electroencephalography

KW - Logic gates

KW - Neurons

UR - http://www.scopus.com/inward/record.url?scp=84951180851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951180851&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2015.7280615

DO - 10.1109/IJCNN.2015.7280615

M3 - Conference contribution

AN - SCOPUS:84951180851

SN - 9781479919604

VL - 2015-September

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - International Joint Conference on Neural Networks, IJCNN 2015

Y2 - 12 July 2015 through 17 July 2015

ER -