Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System

Isa Conradsen; Sándor Beniczky; Peter Wolf; Jonas Duun-Henriksen; Thomas Sams; Helge Bjarup Dissing Sørensen

doi:10.1109/IEMBS.2010.5627218

Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System

Isa Conradsen, Sándor Beniczky, Peter Wolf, Jonas Duun-Henriksen, Thomas Sams, Helge Bjarup Dissing Sørensen

Danish Epilepsy Center

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

576 Downloads (Orbit)

Abstract

An automatic Uni- or Multi-modal Inteligent Seizure Acquisition (UISA/MISA) system is highly applicable for onset detection of epileptic seizures based on motion data. The modalities used are surface electromyography (sEMG), acceleration (ACC) and angular velocity (ANG). The new proposed automatic algorithm on motion data is extracting features as “log-sum” measures of discrete wavelet components. Classification into the two groups “seizure” versus “nonseizure” is made based on the support vector machine (SVM) algorithm. The algorithm performs with a sensitivity of 91-100%, a median latency of 1 second and a specificity of 100% on multi-modal data from five healthy subjects simulating seizures. The uni-modal algorithm based on sEMG data from the subjects and patients performs satisfactorily in some cases. As expected, our results clearly show superiority of the multimodal approach, as compared with the uni-modal one.

Original language	English
Title of host publication	2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Publisher	IEEE
Publication date	2010
Pages	3269-3272
ISBN (Print)	978-1-4244-4123-5
DOIs	https://doi.org/10.1109/IEMBS.2010.5627218
Publication status	Published - 2010
Event	32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Buenos Aires, Argentina Duration: 31 Aug 2010 → 4 Sept 2010 Conference number: 32 http://embc2010.embs.org/

Conference

Conference	32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Number	32
Country/Territory	Argentina
City	Buenos Aires
Period	31/08/2010 → 04/09/2010
Internet address	http://embc2010.embs.org/

Series	I E E E Engineering in Medicine and Biology Society. Conference Proceedings
ISSN	2375-7477

Bibliographical note

Copyright 2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

Access to Document

10.1109/IEMBS.2010.5627218

6120Bd01Final published version, 359 KB

http://embc2010.embs.org/

OpenUrl availability

Full text

Cite this

Conradsen, I., Beniczky, S., Wolf, P., Duun-Henriksen, J., Sams, T., & Sørensen, H. B. D. (2010). Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 3269-3272). IEEE. https://doi.org/10.1109/IEMBS.2010.5627218

Conradsen, Isa ; Beniczky, Sándor ; Wolf, Peter et al. / Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System. 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2010. pp. 3269-3272 (I E E E Engineering in Medicine and Biology Society. Conference Proceedings).

@inproceedings{1645acb236af4d2e8d41c2c97f318b6d,

title = "Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System",

abstract = "An automatic Uni- or Multi-modal Inteligent Seizure Acquisition (UISA/MISA) system is highly applicable for onset detection of epileptic seizures based on motion data. The modalities used are surface electromyography (sEMG), acceleration (ACC) and angular velocity (ANG). The new proposed automatic algorithm on motion data is extracting features as “log-sum” measures of discrete wavelet components. Classification into the two groups “seizure” versus “nonseizure” is made based on the support vector machine (SVM) algorithm. The algorithm performs with a sensitivity of 91-100%, a median latency of 1 second and a specificity of 100% on multi-modal data from five healthy subjects simulating seizures. The uni-modal algorithm based on sEMG data from the subjects and patients performs satisfactorily in some cases. As expected, our results clearly show superiority of the multimodal approach, as compared with the uni-modal one.",

author = "Isa Conradsen and S{\'a}ndor Beniczky and Peter Wolf and Jonas Duun-Henriksen and Thomas Sams and S{\o}rensen, {Helge Bjarup Dissing}",

note = "Copyright 2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.; 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 ; Conference date: 31-08-2010 Through 04-09-2010",

year = "2010",

doi = "10.1109/IEMBS.2010.5627218",

language = "English",

isbn = "978-1-4244-4123-5",

series = "I E E E Engineering in Medicine and Biology Society. Conference Proceedings",

publisher = "IEEE",

pages = "3269--3272",

booktitle = "2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",

address = "United States",

url = "http://embc2010.embs.org/",

}

Conradsen, I, Beniczky, S, Wolf, P, Duun-Henriksen, J, Sams, T & Sørensen, HBD 2010, Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System. in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, I E E E Engineering in Medicine and Biology Society. Conference Proceedings, pp. 3269-3272, 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Buenos Aires, Argentina, 31/08/2010. https://doi.org/10.1109/IEMBS.2010.5627218

Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System. / Conradsen, Isa; Beniczky, Sándor; Wolf, Peter et al.
2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2010. p. 3269-3272 (I E E E Engineering in Medicine and Biology Society. Conference Proceedings).

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

TY - GEN

T1 - Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System

AU - Conradsen, Isa

AU - Beniczky, Sándor

AU - Wolf, Peter

AU - Duun-Henriksen, Jonas

AU - Sams, Thomas

AU - Sørensen, Helge Bjarup Dissing

N1 - Conference code: 32

PY - 2010

Y1 - 2010

N2 - An automatic Uni- or Multi-modal Inteligent Seizure Acquisition (UISA/MISA) system is highly applicable for onset detection of epileptic seizures based on motion data. The modalities used are surface electromyography (sEMG), acceleration (ACC) and angular velocity (ANG). The new proposed automatic algorithm on motion data is extracting features as “log-sum” measures of discrete wavelet components. Classification into the two groups “seizure” versus “nonseizure” is made based on the support vector machine (SVM) algorithm. The algorithm performs with a sensitivity of 91-100%, a median latency of 1 second and a specificity of 100% on multi-modal data from five healthy subjects simulating seizures. The uni-modal algorithm based on sEMG data from the subjects and patients performs satisfactorily in some cases. As expected, our results clearly show superiority of the multimodal approach, as compared with the uni-modal one.

AB - An automatic Uni- or Multi-modal Inteligent Seizure Acquisition (UISA/MISA) system is highly applicable for onset detection of epileptic seizures based on motion data. The modalities used are surface electromyography (sEMG), acceleration (ACC) and angular velocity (ANG). The new proposed automatic algorithm on motion data is extracting features as “log-sum” measures of discrete wavelet components. Classification into the two groups “seizure” versus “nonseizure” is made based on the support vector machine (SVM) algorithm. The algorithm performs with a sensitivity of 91-100%, a median latency of 1 second and a specificity of 100% on multi-modal data from five healthy subjects simulating seizures. The uni-modal algorithm based on sEMG data from the subjects and patients performs satisfactorily in some cases. As expected, our results clearly show superiority of the multimodal approach, as compared with the uni-modal one.

U2 - 10.1109/IEMBS.2010.5627218

DO - 10.1109/IEMBS.2010.5627218

M3 - Article in proceedings

C2 - 21096611

SN - 978-1-4244-4123-5

T3 - I E E E Engineering in Medicine and Biology Society. Conference Proceedings

SP - 3269

EP - 3272

BT - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

PB - IEEE

T2 - 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 31 August 2010 through 4 September 2010

ER -

Conradsen I, Beniczky S, Wolf P, Duun-Henriksen J, Sams T, Sørensen HBD. Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE. 2010. p. 3269-3272. (I E E E Engineering in Medicine and Biology Society. Conference Proceedings). doi: 10.1109/IEMBS.2010.5627218

Seizure Onset Detection based on a Uni- or Multi-modal Intelligent Seizure Acquisition (UISA/MISA) System

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this