A Study of Combined Lossy Compression and Seizure Detection on Epileptic EEG Signals

The Binh NGUYEN, Wanli MA, Dat TRAN

Research output: A Conference proceeding or a Chapter in BookConference contribution

1 Downloads (Pure)

Abstract

Electroencephalogram (EEG) has been widely used in diagnosing and detecting epileptic seizure. Large epileptic EEG databases have been built, the use of EEG compression is therefore becoming necessary. Epilepsy causes a change on EEG characteristics, especially on frequency, hence exploiting these features may improve the performance of EEG lossy compression techniques that are mostly working on frequency domain. In this paper, we propose a lossy compression method for epileptic EEG data, by exploiting the characteristics of EEG under epilepsy. Moreover, the recovered EEG signals processed by the proposed method are used by an EEG-based seizure detection system to evaluate the possibility of applying in real world as well as the impact of lossy compression on seizure detection. The results show that the proposed method gives a higher result, and applying the proposed method to EEG-based seizure detection system is feasible and has the advantage compared to using lossless ones.
Original languageEnglish
Title of host publicationKnowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES-2018)
EditorsRobert J. Howlett, Carlos Toro, Yulia Hicks, Lakhmi C. Jain
Place of PublicationBelgrade, Serbia
PublisherElsevier
Pages156-165
Number of pages10
Volume126
DOIs
Publication statusPublished - 3 Sep 2018
Event22nd International Conference on Knowledge-Based and Intelligent Information and Engineering Systems - Metropol Palace Hotel , Belgrade, Serbia
Duration: 3 Sep 20185 Sep 2018
http://kes2018.kesinternational.org/

Publication series

NameProcedia Computer Science
PublisherElsevier BV
ISSN (Print)1877-0509

Conference

Conference22nd International Conference on Knowledge-Based and Intelligent Information and Engineering Systems
Abbreviated titleKES 2018
CountrySerbia
CityBelgrade
Period3/09/185/09/18
Internet address

Fingerprint

Electroencephalography

Cite this

NGUYEN, T. B., MA, W., & TRAN, D. (2018). A Study of Combined Lossy Compression and Seizure Detection on Epileptic EEG Signals. In R. J. Howlett, C. Toro, Y. Hicks, & L. C. Jain (Eds.), Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES-2018) (Vol. 126, pp. 156-165). (Procedia Computer Science). Belgrade, Serbia: Elsevier. https://doi.org/10.1016/j.procs.2018.07.219
NGUYEN, The Binh ; MA, Wanli ; TRAN, Dat. / A Study of Combined Lossy Compression and Seizure Detection on Epileptic EEG Signals. Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES-2018). editor / Robert J. Howlett ; Carlos Toro ; Yulia Hicks ; Lakhmi C. Jain. Vol. 126 Belgrade, Serbia : Elsevier, 2018. pp. 156-165 (Procedia Computer Science).
@inproceedings{52d1676e27984d67ad1f711c49b89f14,
title = "A Study of Combined Lossy Compression and Seizure Detection on Epileptic EEG Signals",
abstract = "Electroencephalogram (EEG) has been widely used in diagnosing and detecting epileptic seizure. Large epileptic EEG databases have been built, the use of EEG compression is therefore becoming necessary. Epilepsy causes a change on EEG characteristics, especially on frequency, hence exploiting these features may improve the performance of EEG lossy compression techniques that are mostly working on frequency domain. In this paper, we propose a lossy compression method for epileptic EEG data, by exploiting the characteristics of EEG under epilepsy. Moreover, the recovered EEG signals processed by the proposed method are used by an EEG-based seizure detection system to evaluate the possibility of applying in real world as well as the impact of lossy compression on seizure detection. The results show that the proposed method gives a higher result, and applying the proposed method to EEG-based seizure detection system is feasible and has the advantage compared to using lossless ones.",
keywords = "EEG, Epileptic EEG signal, lossy compression, DWT-AAC, EEG-based seizure detection",
author = "NGUYEN, {The Binh} and Wanli MA and Dat TRAN",
year = "2018",
month = "9",
day = "3",
doi = "10.1016/j.procs.2018.07.219",
language = "English",
volume = "126",
series = "Procedia Computer Science",
publisher = "Elsevier",
pages = "156--165",
editor = "Howlett, {Robert J.} and Carlos Toro and Yulia Hicks and Jain, {Lakhmi C. }",
booktitle = "Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES-2018)",
address = "Netherlands",

}

NGUYEN, TB, MA, W & TRAN, D 2018, A Study of Combined Lossy Compression and Seizure Detection on Epileptic EEG Signals. in RJ Howlett, C Toro, Y Hicks & LC Jain (eds), Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES-2018). vol. 126, Procedia Computer Science, Elsevier, Belgrade, Serbia, pp. 156-165, 22nd International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, Belgrade, Serbia, 3/09/18. https://doi.org/10.1016/j.procs.2018.07.219

A Study of Combined Lossy Compression and Seizure Detection on Epileptic EEG Signals. / NGUYEN, The Binh; MA, Wanli; TRAN, Dat.

Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES-2018). ed. / Robert J. Howlett; Carlos Toro; Yulia Hicks; Lakhmi C. Jain. Vol. 126 Belgrade, Serbia : Elsevier, 2018. p. 156-165 (Procedia Computer Science).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A Study of Combined Lossy Compression and Seizure Detection on Epileptic EEG Signals

AU - NGUYEN, The Binh

AU - MA, Wanli

AU - TRAN, Dat

PY - 2018/9/3

Y1 - 2018/9/3

N2 - Electroencephalogram (EEG) has been widely used in diagnosing and detecting epileptic seizure. Large epileptic EEG databases have been built, the use of EEG compression is therefore becoming necessary. Epilepsy causes a change on EEG characteristics, especially on frequency, hence exploiting these features may improve the performance of EEG lossy compression techniques that are mostly working on frequency domain. In this paper, we propose a lossy compression method for epileptic EEG data, by exploiting the characteristics of EEG under epilepsy. Moreover, the recovered EEG signals processed by the proposed method are used by an EEG-based seizure detection system to evaluate the possibility of applying in real world as well as the impact of lossy compression on seizure detection. The results show that the proposed method gives a higher result, and applying the proposed method to EEG-based seizure detection system is feasible and has the advantage compared to using lossless ones.

AB - Electroencephalogram (EEG) has been widely used in diagnosing and detecting epileptic seizure. Large epileptic EEG databases have been built, the use of EEG compression is therefore becoming necessary. Epilepsy causes a change on EEG characteristics, especially on frequency, hence exploiting these features may improve the performance of EEG lossy compression techniques that are mostly working on frequency domain. In this paper, we propose a lossy compression method for epileptic EEG data, by exploiting the characteristics of EEG under epilepsy. Moreover, the recovered EEG signals processed by the proposed method are used by an EEG-based seizure detection system to evaluate the possibility of applying in real world as well as the impact of lossy compression on seizure detection. The results show that the proposed method gives a higher result, and applying the proposed method to EEG-based seizure detection system is feasible and has the advantage compared to using lossless ones.

KW - EEG

KW - Epileptic EEG signal

KW - lossy compression

KW - DWT-AAC

KW - EEG-based seizure detection

UR - http://www.scopus.com/inward/record.url?scp=85056614019&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2018.07.219

DO - 10.1016/j.procs.2018.07.219

M3 - Conference contribution

VL - 126

T3 - Procedia Computer Science

SP - 156

EP - 165

BT - Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES-2018)

A2 - Howlett, Robert J.

A2 - Toro, Carlos

A2 - Hicks, Yulia

A2 - Jain, Lakhmi C.

PB - Elsevier

CY - Belgrade, Serbia

ER -

NGUYEN TB, MA W, TRAN D. A Study of Combined Lossy Compression and Seizure Detection on Epileptic EEG Signals. In Howlett RJ, Toro C, Hicks Y, Jain LC, editors, Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 22nd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES-2018). Vol. 126. Belgrade, Serbia: Elsevier. 2018. p. 156-165. (Procedia Computer Science). https://doi.org/10.1016/j.procs.2018.07.219