An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification

Mohamed Deriche; Saeed Aljabri; Mohammed Al-Akhras; Mohammed Siddiqui; Naziha Deriche

doi:10.1109/SSD.2019.8893151

An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification

Mohamed Deriche
, Saeed Aljabri
, Mohammed Al-Akhras
, Mohammed Siddiqui
, Naziha Deriche

King Fahd University of Petroleum and Minerals
Johnson Johnson

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

1 Scopus citations

Abstract

The analysis of the ECG signal provides important information useful for heart disease diagnosis. Moreover, it can also help in identifying other problems such as neonatal seizures. Considering the nature of ECG patterns, several features can be extracted and used for the purpose of heartbeat and rhythm classification. In this paper, we discuss a set of 13 ECG geometric features for the purpose of identifying five abnormal types of heart beats. The proposed algorithm for feature extraction is based on the Pan-Tompkins QRS model. The MIT-BIH arrhythmia database is used in this study to test the performance of the proposed algorithm. The results show that different types of ECG based features are optimal for different types of heartbeat abnormalities. More importantly, we show that using the developed 13 features, we can identify at least 5 types of abnormalities with an accuracy of more than 92%.

Original language	English
Title of host publication	16th International Multi-Conference on Systems, Signals and Devices, SSD 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	418-422
Number of pages	5
ISBN (Electronic)	9781728118208
DOIs	https://doi.org/10.1109/SSD.2019.8893151
State	Published - Mar 2019
Externally published	Yes
Event	16th International Multi-Conference on Systems, Signals and Devices, SSD 2019 - Istanbul, Turkey Duration: 21 Mar 2019 → 24 Mar 2019

Publication series

Name	16th International Multi-Conference on Systems, Signals and Devices, SSD 2019

Conference

Conference	16th International Multi-Conference on Systems, Signals and Devices, SSD 2019
Country/Territory	Turkey
City	Istanbul
Period	21/03/19 → 24/03/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Bayes classifier
Cardiac Signal
ECG feature Extraction
Heart Arrhythmia

Access to Document

10.1109/SSD.2019.8893151

Cite this

Deriche, M., Aljabri, S., Al-Akhras, M., Siddiqui, M., & Deriche, N. (2019). An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification. In 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019 (pp. 418-422). Article 8893151 (16th International Multi-Conference on Systems, Signals and Devices, SSD 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSD.2019.8893151

Deriche, Mohamed ; Aljabri, Saeed ; Al-Akhras, Mohammed et al. / An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification. 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 418-422 (16th International Multi-Conference on Systems, Signals and Devices, SSD 2019).

@inproceedings{7e4348e67f97414ea87d3a31871871d6,

title = "An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification",

abstract = "The analysis of the ECG signal provides important information useful for heart disease diagnosis. Moreover, it can also help in identifying other problems such as neonatal seizures. Considering the nature of ECG patterns, several features can be extracted and used for the purpose of heartbeat and rhythm classification. In this paper, we discuss a set of 13 ECG geometric features for the purpose of identifying five abnormal types of heart beats. The proposed algorithm for feature extraction is based on the Pan-Tompkins QRS model. The MIT-BIH arrhythmia database is used in this study to test the performance of the proposed algorithm. The results show that different types of ECG based features are optimal for different types of heartbeat abnormalities. More importantly, we show that using the developed 13 features, we can identify at least 5 types of abnormalities with an accuracy of more than 92\%.",

keywords = "Bayes classifier, Cardiac Signal, ECG feature Extraction, Heart Arrhythmia",

author = "Mohamed Deriche and Saeed Aljabri and Mohammed Al-Akhras and Mohammed Siddiqui and Naziha Deriche",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019 ; Conference date: 21-03-2019 Through 24-03-2019",

year = "2019",

month = mar,

doi = "10.1109/SSD.2019.8893151",

language = "English",

series = "16th International Multi-Conference on Systems, Signals and Devices, SSD 2019",

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

pages = "418--422",

booktitle = "16th International Multi-Conference on Systems, Signals and Devices, SSD 2019",

address = "United States",

}

Deriche, M, Aljabri, S, Al-Akhras, M, Siddiqui, M & Deriche, N 2019, An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification. in 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019., 8893151, 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019, Institute of Electrical and Electronics Engineers Inc., pp. 418-422, 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019, Istanbul, Turkey, 21/03/19. https://doi.org/10.1109/SSD.2019.8893151

An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification. / Deriche, Mohamed; Aljabri, Saeed; Al-Akhras, Mohammed et al.
16th International Multi-Conference on Systems, Signals and Devices, SSD 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 418-422 8893151 (16th International Multi-Conference on Systems, Signals and Devices, SSD 2019).

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

TY - GEN

T1 - An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification

AU - Deriche, Mohamed

AU - Aljabri, Saeed

AU - Al-Akhras, Mohammed

AU - Siddiqui, Mohammed

AU - Deriche, Naziha

PY - 2019/3

Y1 - 2019/3

N2 - The analysis of the ECG signal provides important information useful for heart disease diagnosis. Moreover, it can also help in identifying other problems such as neonatal seizures. Considering the nature of ECG patterns, several features can be extracted and used for the purpose of heartbeat and rhythm classification. In this paper, we discuss a set of 13 ECG geometric features for the purpose of identifying five abnormal types of heart beats. The proposed algorithm for feature extraction is based on the Pan-Tompkins QRS model. The MIT-BIH arrhythmia database is used in this study to test the performance of the proposed algorithm. The results show that different types of ECG based features are optimal for different types of heartbeat abnormalities. More importantly, we show that using the developed 13 features, we can identify at least 5 types of abnormalities with an accuracy of more than 92%.

AB - The analysis of the ECG signal provides important information useful for heart disease diagnosis. Moreover, it can also help in identifying other problems such as neonatal seizures. Considering the nature of ECG patterns, several features can be extracted and used for the purpose of heartbeat and rhythm classification. In this paper, we discuss a set of 13 ECG geometric features for the purpose of identifying five abnormal types of heart beats. The proposed algorithm for feature extraction is based on the Pan-Tompkins QRS model. The MIT-BIH arrhythmia database is used in this study to test the performance of the proposed algorithm. The results show that different types of ECG based features are optimal for different types of heartbeat abnormalities. More importantly, we show that using the developed 13 features, we can identify at least 5 types of abnormalities with an accuracy of more than 92%.

KW - Bayes classifier

KW - Cardiac Signal

KW - ECG feature Extraction

KW - Heart Arrhythmia

UR - https://www.scopus.com/pages/publications/85075630421

U2 - 10.1109/SSD.2019.8893151

DO - 10.1109/SSD.2019.8893151

M3 - Conference contribution

AN - SCOPUS:85075630421

T3 - 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019

SP - 418

EP - 422

BT - 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019

Y2 - 21 March 2019 through 24 March 2019

ER -

Deriche M, Aljabri S, Al-Akhras M, Siddiqui M, Deriche N. An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification. In 16th International Multi-Conference on Systems, Signals and Devices, SSD 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 418-422. 8893151. (16th International Multi-Conference on Systems, Signals and Devices, SSD 2019). doi: 10.1109/SSD.2019.8893151

An Optimal Set of Features for Multi-Class Heart Beat Abnormality Classification

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this