Seizure recognition on epilepsy feature tensor

Evrim Acar; Canan Aykut Bingos; Haluk Bingol; Rasmus Bro; Bülent Yener

doi:10.1109/IEMBS.2007.4353280

Seizure recognition on epilepsy feature tensor

Evrim Acar^*, Canan Aykut Bingos, Haluk Bingol, Rasmus Bro, Bülent Yener

^*Corresponding author for this work

Food Analytics and Biotechnology

20 Citations (Scopus)

Abstract

With a goal of automating visual analysis of electroencephalogram (EEG) data and assessing the performance of various features in seizure recognition, we introduce a mathematical model capable of recognizing patient-specific epileptic seizures with high accuracy. We represent multi-channel scalp EEG using a set of features. These features expected to have distinct trends during seizure and non-seizure periods include features from both time and frequency domains. The contributions of this paper are threefold. First, we rearrange multi-channel EEG signals as a third-order tensor called an Epilepsy Feature Tensor with modes: time epochs, features and electrodes. Second, we model the Epilepsy Feature Tensor using a multilinear regression model, i.e., Multilinear Partial Least Squares regression, which is the generalization of Partial Least Squares (PLS) regression to higher-order datasets. This two-step approach facilitates EEG data analysis from multiple electrodes represented by several features from different domains. Third, we identify which features are more significant for seizure recognition. Our results based on the analysis of 19 seizures from 5 epileptic patients demonstrate that multiway analysis of an Epilepsy Feature Tensor can detect (patient-specific) seizures with classification accuracy ranging between 77-96%.

Original language	English
Title of host publication	29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
Number of pages	4
Publication date	1 Dec 2007
Pages	4273-4276
Article number	4353280
ISBN (Print)	1424407885, 9781424407880
DOIs	https://doi.org/10.1109/IEMBS.2007.4353280
Publication status	Published - 1 Dec 2007
Event	29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 - Lyon, France Duration: 23 Aug 2007 → 26 Aug 2007

Conference

Conference	29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
Country/Territory	France
City	Lyon
Period	23/08/2007 → 26/08/2007
Sponsor	ACIES, Research Promotion and Management Consulting, EOARD, European Office of Aerospace R and D, Grand Lyon, NSF, National Science Foundation, Philips Research Europe, Philips Research North America

Series	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
ISSN	0589-1019

Access to Document

10.1109/IEMBS.2007.4353280

Cite this

Acar, E., Bingos, C. A., Bingol, H., Bro, R., & Yener, B. (2007). Seizure recognition on epilepsy feature tensor. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 (pp. 4273-4276). [4353280] Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings https://doi.org/10.1109/IEMBS.2007.4353280

Seizure recognition on epilepsy feature tensor. / Acar, Evrim; Bingos, Canan Aykut; Bingol, Haluk et al.

29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. 2007. p. 4273-4276 4353280 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Acar, E, Bingos, CA, Bingol, H, Bro, R & Yener, B 2007, Seizure recognition on epilepsy feature tensor. in 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07., 4353280, Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 4273-4276, 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07, Lyon, France, 23/08/2007. https://doi.org/10.1109/IEMBS.2007.4353280

@inproceedings{10a4e4bdc76a4f08a5af8e00d9a67c5d,

title = "Seizure recognition on epilepsy feature tensor",

abstract = "With a goal of automating visual analysis of electroencephalogram (EEG) data and assessing the performance of various features in seizure recognition, we introduce a mathematical model capable of recognizing patient-specific epileptic seizures with high accuracy. We represent multi-channel scalp EEG using a set of features. These features expected to have distinct trends during seizure and non-seizure periods include features from both time and frequency domains. The contributions of this paper are threefold. First, we rearrange multi-channel EEG signals as a third-order tensor called an Epilepsy Feature Tensor with modes: time epochs, features and electrodes. Second, we model the Epilepsy Feature Tensor using a multilinear regression model, i.e., Multilinear Partial Least Squares regression, which is the generalization of Partial Least Squares (PLS) regression to higher-order datasets. This two-step approach facilitates EEG data analysis from multiple electrodes represented by several features from different domains. Third, we identify which features are more significant for seizure recognition. Our results based on the analysis of 19 seizures from 5 epileptic patients demonstrate that multiway analysis of an Epilepsy Feature Tensor can detect (patient-specific) seizures with classification accuracy ranging between 77-96%.",

author = "Evrim Acar and Bingos, {Canan Aykut} and Haluk Bingol and Rasmus Bro and B{\"u}lent Yener",

year = "2007",

month = dec,

day = "1",

doi = "10.1109/IEMBS.2007.4353280",

language = "English",

isbn = "1424407885",

series = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

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

pages = "4273--4276",

booktitle = "29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07",

note = "29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 ; Conference date: 23-08-2007 Through 26-08-2007",

}

TY - GEN

T1 - Seizure recognition on epilepsy feature tensor

AU - Acar, Evrim

AU - Bingos, Canan Aykut

AU - Bingol, Haluk

AU - Bro, Rasmus

AU - Yener, Bülent

PY - 2007/12/1

Y1 - 2007/12/1

N2 - With a goal of automating visual analysis of electroencephalogram (EEG) data and assessing the performance of various features in seizure recognition, we introduce a mathematical model capable of recognizing patient-specific epileptic seizures with high accuracy. We represent multi-channel scalp EEG using a set of features. These features expected to have distinct trends during seizure and non-seizure periods include features from both time and frequency domains. The contributions of this paper are threefold. First, we rearrange multi-channel EEG signals as a third-order tensor called an Epilepsy Feature Tensor with modes: time epochs, features and electrodes. Second, we model the Epilepsy Feature Tensor using a multilinear regression model, i.e., Multilinear Partial Least Squares regression, which is the generalization of Partial Least Squares (PLS) regression to higher-order datasets. This two-step approach facilitates EEG data analysis from multiple electrodes represented by several features from different domains. Third, we identify which features are more significant for seizure recognition. Our results based on the analysis of 19 seizures from 5 epileptic patients demonstrate that multiway analysis of an Epilepsy Feature Tensor can detect (patient-specific) seizures with classification accuracy ranging between 77-96%.

AB - With a goal of automating visual analysis of electroencephalogram (EEG) data and assessing the performance of various features in seizure recognition, we introduce a mathematical model capable of recognizing patient-specific epileptic seizures with high accuracy. We represent multi-channel scalp EEG using a set of features. These features expected to have distinct trends during seizure and non-seizure periods include features from both time and frequency domains. The contributions of this paper are threefold. First, we rearrange multi-channel EEG signals as a third-order tensor called an Epilepsy Feature Tensor with modes: time epochs, features and electrodes. Second, we model the Epilepsy Feature Tensor using a multilinear regression model, i.e., Multilinear Partial Least Squares regression, which is the generalization of Partial Least Squares (PLS) regression to higher-order datasets. This two-step approach facilitates EEG data analysis from multiple electrodes represented by several features from different domains. Third, we identify which features are more significant for seizure recognition. Our results based on the analysis of 19 seizures from 5 epileptic patients demonstrate that multiway analysis of an Epilepsy Feature Tensor can detect (patient-specific) seizures with classification accuracy ranging between 77-96%.

UR - http://www.scopus.com/inward/record.url?scp=57649216253&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2007.4353280

DO - 10.1109/IEMBS.2007.4353280

M3 - Article in proceedings

C2 - 18002946

AN - SCOPUS:57649216253

SN - 1424407885

SN - 9781424407880

T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

SP - 4273

EP - 4276

BT - 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07

T2 - 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07

Y2 - 23 August 2007 through 26 August 2007

ER -

Seizure recognition on epilepsy feature tensor

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this