Epileptic Seizure Detection Using Convolutional Neural Network: A Multi-Biosignal study

Yu Liu; Shobi Sivathamboo; Peter Goodin; Paul Bonnington; Patrick Kwan; Levin Kuhlmann; Terence O'Brien; Piero Perucca; Zongyuan Ge

doi:10.1145/3373017.3373055

Epileptic Seizure Detection Using Convolutional Neural Network: A Multi-Biosignal study

Yu Liu, Shobi Sivathamboo, Peter Goodin, Paul Bonnington, Patrick Kwan, Levin Kuhlmann, Terence O'Brien, Piero Perucca, Zongyuan Ge

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

Abstract

Epilepsy affects over 70 million people worldwide, making it one of the most common serious neurological disorders in the world. The automated identification of seizures based on EEG signal is one of the most common methods but facing challenges such as the variability of seizures between individual patients and artifact generated during the measurement. In this work, we implement the multi-biosignals scheme for seizure detection by combing EEG, ECG and respiratory. We apply 1D and 2D convolutional neural network (CNN) on multi-biosignal epileptic seizure detection using the in-situ dataset with artifacts. The experimental results show that incorporating multi-biosignals outperforms than using EEG only. We also discovered that Conv2D model could achieve the best AUC of 65%, which is 7% better than the Conv1D model.

Original language	English
Title of host publication	Proceedings of the Australasian Computer Science Week Multiconference 2020, ACSW 2020
Editors	Abdur Forkan
Place of Publication	New York NY USA
Publisher	Association for Computing Machinery (ACM)
Number of pages	8
ISBN (Electronic)	9781450376976
DOIs	https://doi.org/10.1145/3373017.3373055
Publication status	Published - 4 Feb 2020
Event	Australasian Workshop on Health Informatics and Knowledge Management (HIKM) 2020 - Melbourne, Australia Duration: 3 Feb 2020 → 7 Feb 2020 Conference number: 13th

Workshop

Workshop	Australasian Workshop on Health Informatics and Knowledge Management (HIKM) 2020
Abbreviated title	HIKM 2020
Country/Territory	Australia
City	Melbourne
Period	3/02/20 → 7/02/20

Keywords

CNN
Epilepsy
Multi-Biosignal
Multimodal learning
Seizure detection

Access to Document

10.1145/3373017.3373055

Cite this

Liu, Y., Sivathamboo, S., Goodin, P., Bonnington, P., Kwan, P., Kuhlmann, L., O'Brien, T., Perucca, P., & Ge, Z. (2020). Epileptic Seizure Detection Using Convolutional Neural Network: A Multi-Biosignal study. In A. Forkan (Ed.), Proceedings of the Australasian Computer Science Week Multiconference 2020, ACSW 2020 [37] Association for Computing Machinery (ACM). https://doi.org/10.1145/3373017.3373055

Liu, Yu ; Sivathamboo, Shobi ; Goodin, Peter ; Bonnington, Paul ; Kwan, Patrick ; Kuhlmann, Levin ; O'Brien, Terence ; Perucca, Piero ; Ge, Zongyuan. / Epileptic Seizure Detection Using Convolutional Neural Network : A Multi-Biosignal study. Proceedings of the Australasian Computer Science Week Multiconference 2020, ACSW 2020. editor / Abdur Forkan. New York NY USA : Association for Computing Machinery (ACM), 2020.

@inproceedings{6600c87af174467bb855b5c94bd8f8d3,

title = "Epileptic Seizure Detection Using Convolutional Neural Network: A Multi-Biosignal study",

abstract = "Epilepsy affects over 70 million people worldwide, making it one of the most common serious neurological disorders in the world. The automated identification of seizures based on EEG signal is one of the most common methods but facing challenges such as the variability of seizures between individual patients and artifact generated during the measurement. In this work, we implement the multi-biosignals scheme for seizure detection by combing EEG, ECG and respiratory. We apply 1D and 2D convolutional neural network (CNN) on multi-biosignal epileptic seizure detection using the in-situ dataset with artifacts. The experimental results show that incorporating multi-biosignals outperforms than using EEG only. We also discovered that Conv2D model could achieve the best AUC of 65%, which is 7% better than the Conv1D model.",

keywords = "CNN, Epilepsy, Multi-Biosignal, Multimodal learning, Seizure detection",

author = "Yu Liu and Shobi Sivathamboo and Peter Goodin and Paul Bonnington and Patrick Kwan and Levin Kuhlmann and Terence O'Brien and Piero Perucca and Zongyuan Ge",

year = "2020",

month = feb,

day = "4",

doi = "10.1145/3373017.3373055",

language = "English",

editor = "Forkan, { Abdur }",

booktitle = "Proceedings of the Australasian Computer Science Week Multiconference 2020, ACSW 2020",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

note = "Australasian Workshop on Health Informatics and Knowledge Management (HIKM) 2020, HIKM 2020 ; Conference date: 03-02-2020 Through 07-02-2020",

}

Liu, Y, Sivathamboo, S, Goodin, P, Bonnington, P , Kwan, P , Kuhlmann, L , O'Brien, T , Perucca, P & Ge, Z 2020, Epileptic Seizure Detection Using Convolutional Neural Network: A Multi-Biosignal study. in A Forkan (ed.), Proceedings of the Australasian Computer Science Week Multiconference 2020, ACSW 2020., 37, Association for Computing Machinery (ACM), New York NY USA, Australasian Workshop on Health Informatics and Knowledge Management (HIKM) 2020, Melbourne, Victoria, Australia, 3/02/20. https://doi.org/10.1145/3373017.3373055

Epileptic Seizure Detection Using Convolutional Neural Network : A Multi-Biosignal study. / Liu, Yu; Sivathamboo, Shobi; Goodin, Peter; Bonnington, Paul ; Kwan, Patrick ; Kuhlmann, Levin ; O'Brien, Terence ; Perucca, Piero ; Ge, Zongyuan.

Proceedings of the Australasian Computer Science Week Multiconference 2020, ACSW 2020. ed. / Abdur Forkan. New York NY USA : Association for Computing Machinery (ACM), 2020. 37.

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

TY - GEN

T1 - Epileptic Seizure Detection Using Convolutional Neural Network

T2 - Australasian Workshop on Health Informatics and Knowledge Management (HIKM) 2020

AU - Liu, Yu

AU - Sivathamboo, Shobi

AU - Goodin, Peter

AU - Bonnington, Paul

AU - Kwan, Patrick

AU - Kuhlmann, Levin

AU - O'Brien, Terence

AU - Perucca, Piero

AU - Ge, Zongyuan

N1 - Conference code: 13th

PY - 2020/2/4

Y1 - 2020/2/4

N2 - Epilepsy affects over 70 million people worldwide, making it one of the most common serious neurological disorders in the world. The automated identification of seizures based on EEG signal is one of the most common methods but facing challenges such as the variability of seizures between individual patients and artifact generated during the measurement. In this work, we implement the multi-biosignals scheme for seizure detection by combing EEG, ECG and respiratory. We apply 1D and 2D convolutional neural network (CNN) on multi-biosignal epileptic seizure detection using the in-situ dataset with artifacts. The experimental results show that incorporating multi-biosignals outperforms than using EEG only. We also discovered that Conv2D model could achieve the best AUC of 65%, which is 7% better than the Conv1D model.

AB - Epilepsy affects over 70 million people worldwide, making it one of the most common serious neurological disorders in the world. The automated identification of seizures based on EEG signal is one of the most common methods but facing challenges such as the variability of seizures between individual patients and artifact generated during the measurement. In this work, we implement the multi-biosignals scheme for seizure detection by combing EEG, ECG and respiratory. We apply 1D and 2D convolutional neural network (CNN) on multi-biosignal epileptic seizure detection using the in-situ dataset with artifacts. The experimental results show that incorporating multi-biosignals outperforms than using EEG only. We also discovered that Conv2D model could achieve the best AUC of 65%, which is 7% better than the Conv1D model.

KW - CNN

KW - Epilepsy

KW - Multi-Biosignal

KW - Multimodal learning

KW - Seizure detection

UR - http://www.scopus.com/inward/record.url?scp=85079849120&partnerID=8YFLogxK

U2 - 10.1145/3373017.3373055

DO - 10.1145/3373017.3373055

M3 - Conference Paper

AN - SCOPUS:85079849120

BT - Proceedings of the Australasian Computer Science Week Multiconference 2020, ACSW 2020

A2 - Forkan, Abdur

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

Y2 - 3 February 2020 through 7 February 2020

ER -

Liu Y, Sivathamboo S, Goodin P, Bonnington P , Kwan P , Kuhlmann L et al. Epileptic Seizure Detection Using Convolutional Neural Network: A Multi-Biosignal study. In Forkan A, editor, Proceedings of the Australasian Computer Science Week Multiconference 2020, ACSW 2020. New York NY USA: Association for Computing Machinery (ACM). 2020. 37 https://doi.org/10.1145/3373017.3373055

Epileptic Seizure Detection Using Convolutional Neural Network: A Multi-Biosignal study

Abstract

Workshop

Keywords

Access to Document

Other files and links

Cite this