Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal

Sadr Nadi; Philip de Chazal; André van Schaik; Paul Breen

doi:10.1109/EMBC.2015.7320170

Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal

Sadr Nadi, Philip de Chazal, André van Schaik, Paul Breen

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

4 Citations (Scopus)

Abstract

This paper describes a system for the recognition of sleep apnoea episodes from ECG signals using a committee of extreme learning machine (ELM) classifiers. RR-interval parameters (heart rate variability) have been used as the identifying features as they are directly affected by sleep apnoea. The MIT PhysioNet Apnea-ECG database was used. A committee of five ELM classifiers has been employed to classify one-minute epochs of ECG into normal or apnoeic epochs. Our results show that the classification performance from the committee of networks was superior to the results of a single ELM classifier for fan-outs from 1 to 100. Classification performance reached a plateau at a fan-out of 10. The maximum accuracy was 82.5% with a sensitivity of 81.9% and a specificity of 82.8%. The results were comparable to other published research with the same input data.

Original language	English
Title of host publication	Biomedical Engineering: A Bridge to Improve the Quality of Health Care and the Quality of Life: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milano, Italy, 25-29 August 2015
Publisher	IEEE
Pages	7675-7678
Number of pages	4
ISBN (Print)	9781424492701
DOIs	https://doi.org/10.1109/EMBC.2015.7320170
Publication status	Published - 2015
Event	IEEE Engineering in Medicine and Biology Society. Annual Conference - Duration: 25 Aug 2015 → …

Publication series

Name
ISSN (Print)	1557-170X

Conference

Conference	IEEE Engineering in Medicine and Biology Society. Annual Conference
Period	25/08/15 → …

Keywords

electrocardiography
heart beat
sleep apnea syndromes

Access to Document

10.1109/EMBC.2015.7320170

Cite this

Nadi, S., de Chazal, P., Schaik, A. V., & Breen, P. (2015). Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal. In Biomedical Engineering: A Bridge to Improve the Quality of Health Care and the Quality of Life: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milano, Italy, 25-29 August 2015 (pp. 7675-7678). IEEE. https://doi.org/10.1109/EMBC.2015.7320170

Nadi, Sadr ; de Chazal, Philip ; Schaik, André van et al. / Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal. Biomedical Engineering: A Bridge to Improve the Quality of Health Care and the Quality of Life: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milano, Italy, 25-29 August 2015. IEEE, 2015. pp. 7675-7678

@inproceedings{f3753c62faaa443ca0fe8a6beae7e4f4,

title = "Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal",

abstract = "This paper describes a system for the recognition of sleep apnoea episodes from ECG signals using a committee of extreme learning machine (ELM) classifiers. RR-interval parameters (heart rate variability) have been used as the identifying features as they are directly affected by sleep apnoea. The MIT PhysioNet Apnea-ECG database was used. A committee of five ELM classifiers has been employed to classify one-minute epochs of ECG into normal or apnoeic epochs. Our results show that the classification performance from the committee of networks was superior to the results of a single ELM classifier for fan-outs from 1 to 100. Classification performance reached a plateau at a fan-out of 10. The maximum accuracy was 82.5% with a sensitivity of 81.9% and a specificity of 82.8%. The results were comparable to other published research with the same input data.",

keywords = "electrocardiography, heart beat, sleep apnea syndromes",

author = "Sadr Nadi and {de Chazal}, Philip and Schaik, {Andr{\'e} van} and Paul Breen",

year = "2015",

doi = "10.1109/EMBC.2015.7320170",

language = "English",

isbn = "9781424492701",

publisher = "IEEE",

pages = "7675--7678",

booktitle = "Biomedical Engineering: A Bridge to Improve the Quality of Health Care and the Quality of Life: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milano, Italy, 25-29 August 2015",

note = "IEEE Engineering in Medicine and Biology Society. Annual Conference ; Conference date: 25-08-2015",

}

Nadi, S, de Chazal, P, Schaik, AV & Breen, P 2015, Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal. in Biomedical Engineering: A Bridge to Improve the Quality of Health Care and the Quality of Life: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milano, Italy, 25-29 August 2015. IEEE, pp. 7675-7678, IEEE Engineering in Medicine and Biology Society. Annual Conference, 25/08/15. https://doi.org/10.1109/EMBC.2015.7320170

Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal. / Nadi, Sadr; de Chazal, Philip; Schaik, André van et al.
Biomedical Engineering: A Bridge to Improve the Quality of Health Care and the Quality of Life: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milano, Italy, 25-29 August 2015. IEEE, 2015. p. 7675-7678.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal

AU - Nadi, Sadr

AU - de Chazal, Philip

AU - Schaik, André van

AU - Breen, Paul

PY - 2015

Y1 - 2015

N2 - This paper describes a system for the recognition of sleep apnoea episodes from ECG signals using a committee of extreme learning machine (ELM) classifiers. RR-interval parameters (heart rate variability) have been used as the identifying features as they are directly affected by sleep apnoea. The MIT PhysioNet Apnea-ECG database was used. A committee of five ELM classifiers has been employed to classify one-minute epochs of ECG into normal or apnoeic epochs. Our results show that the classification performance from the committee of networks was superior to the results of a single ELM classifier for fan-outs from 1 to 100. Classification performance reached a plateau at a fan-out of 10. The maximum accuracy was 82.5% with a sensitivity of 81.9% and a specificity of 82.8%. The results were comparable to other published research with the same input data.

AB - This paper describes a system for the recognition of sleep apnoea episodes from ECG signals using a committee of extreme learning machine (ELM) classifiers. RR-interval parameters (heart rate variability) have been used as the identifying features as they are directly affected by sleep apnoea. The MIT PhysioNet Apnea-ECG database was used. A committee of five ELM classifiers has been employed to classify one-minute epochs of ECG into normal or apnoeic epochs. Our results show that the classification performance from the committee of networks was superior to the results of a single ELM classifier for fan-outs from 1 to 100. Classification performance reached a plateau at a fan-out of 10. The maximum accuracy was 82.5% with a sensitivity of 81.9% and a specificity of 82.8%. The results were comparable to other published research with the same input data.

KW - electrocardiography

KW - heart beat

KW - sleep apnea syndromes

UR - http://handle.uws.edu.au:8081/1959.7/uws:33580

UR - http://embc.embs.org/2015/

U2 - 10.1109/EMBC.2015.7320170

DO - 10.1109/EMBC.2015.7320170

M3 - Conference Paper

SN - 9781424492701

SP - 7675

EP - 7678

BT - Biomedical Engineering: A Bridge to Improve the Quality of Health Care and the Quality of Life: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milano, Italy, 25-29 August 2015

PB - IEEE

T2 - IEEE Engineering in Medicine and Biology Society. Annual Conference

Y2 - 25 August 2015

ER -

Nadi S, de Chazal P, Schaik AV , Breen P. Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal. In Biomedical Engineering: A Bridge to Improve the Quality of Health Care and the Quality of Life: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), Milano, Italy, 25-29 August 2015. IEEE. 2015. p. 7675-7678 doi: 10.1109/EMBC.2015.7320170

Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this