Improved abnormality detection from raw ECG signals using feature enhancement

Diptangshu Pandit; Li Zhang; Nauman Aslam; Changyu Liu; Samiran Chattopadhyay

doi:10.1109/FSKD.2016.7603383

Improved abnormality detection from raw ECG signals using feature enhancement

Diptangshu Pandit, Li Zhang, Nauman Aslam, Changyu Liu, Samiran Chattopadhyay

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

4 Citations (Scopus)

Abstract

This research presents an abnormal beat detection scheme from lead II Electrocardiogram (ECG) signals along with some improvements on feature extraction. A set of 16 features representing positions, durations, amplitudes and shapes of P, Q, R, S and T waves is proposed in this work for heart beat classification. These features carry important medical information for normal and abnormal beat detection. Diverse classifiers are employed for abnormality detection, including K-Nearest Neighbor, Decision Tree, Artificial Neural Network, Naive Bayesian Classifier, Random Forest, and Support Vector Machine along with some ensemble classifiers such as AdaBoostM1 and Bagging. We have evaluated the proposed system on raw one lead signals extracted from MIT-BIH Arrhythmia, QT and European ST-T databases in the Physionet databank. The experiments using this new set of 16 features achieve better performance for the three test databases than our previous system using a subset of these features.

Original language	English
Title of host publication	2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016
Editors	Jiayi Du, Chubo Liu, Kenli Li, Lipo Wang, Zhao Tong, Maozhen Li, Ning Xiong
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1402-1406
Number of pages	5
ISBN (Electronic)	9781509040933
DOIs	https://doi.org/10.1109/FSKD.2016.7603383
Publication status	Published - 24 Oct 2016
Event	12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery - Changsha, China Duration: 13 Aug 2016 → 15 Aug 2016

Conference

Conference	12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery
Abbreviated title	ICNC-FSKD 2016
Country/Territory	China
City	Changsha
Period	13/08/16 → 15/08/16

Access to Document

10.1109/FSKD.2016.7603383Licence: Unspecified

Cite this

Pandit, D., Zhang, L., Aslam, N., Liu, C., & Chattopadhyay, S. (2016). Improved abnormality detection from raw ECG signals using feature enhancement. In J. Du, C. Liu, K. Li, L. Wang, Z. Tong, M. Li, & N. Xiong (Eds.), 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016 (pp. 1402-1406). Article 7603383 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FSKD.2016.7603383

Pandit, Diptangshu ; Zhang, Li ; Aslam, Nauman et al. / Improved abnormality detection from raw ECG signals using feature enhancement. 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016. editor / Jiayi Du ; Chubo Liu ; Kenli Li ; Lipo Wang ; Zhao Tong ; Maozhen Li ; Ning Xiong. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1402-1406

@inproceedings{4318bc4c1705458abb0838344f76b1a1,

title = "Improved abnormality detection from raw ECG signals using feature enhancement",

abstract = "This research presents an abnormal beat detection scheme from lead II Electrocardiogram (ECG) signals along with some improvements on feature extraction. A set of 16 features representing positions, durations, amplitudes and shapes of P, Q, R, S and T waves is proposed in this work for heart beat classification. These features carry important medical information for normal and abnormal beat detection. Diverse classifiers are employed for abnormality detection, including K-Nearest Neighbor, Decision Tree, Artificial Neural Network, Naive Bayesian Classifier, Random Forest, and Support Vector Machine along with some ensemble classifiers such as AdaBoostM1 and Bagging. We have evaluated the proposed system on raw one lead signals extracted from MIT-BIH Arrhythmia, QT and European ST-T databases in the Physionet databank. The experiments using this new set of 16 features achieve better performance for the three test databases than our previous system using a subset of these features.",

author = "Diptangshu Pandit and Li Zhang and Nauman Aslam and Changyu Liu and Samiran Chattopadhyay",

year = "2016",

month = oct,

day = "24",

doi = "10.1109/FSKD.2016.7603383",

language = "English",

pages = "1402--1406",

editor = "Jiayi Du and Chubo Liu and Kenli Li and Lipo Wang and Zhao Tong and Maozhen Li and Ning Xiong",

booktitle = "2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016",

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

address = "United States",

note = "12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016 ; Conference date: 13-08-2016 Through 15-08-2016",

}

Pandit, D, Zhang, L, Aslam, N, Liu, C & Chattopadhyay, S 2016, Improved abnormality detection from raw ECG signals using feature enhancement. in J Du, C Liu, K Li, L Wang, Z Tong, M Li & N Xiong (eds), 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016., 7603383, Institute of Electrical and Electronics Engineers Inc., pp. 1402-1406, 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, Changsha, China, 13/08/16. https://doi.org/10.1109/FSKD.2016.7603383

Improved abnormality detection from raw ECG signals using feature enhancement. / Pandit, Diptangshu; Zhang, Li; Aslam, Nauman et al.
2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016. ed. / Jiayi Du; Chubo Liu; Kenli Li; Lipo Wang; Zhao Tong; Maozhen Li; Ning Xiong. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1402-1406 7603383.

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

TY - GEN

T1 - Improved abnormality detection from raw ECG signals using feature enhancement

AU - Pandit, Diptangshu

AU - Zhang, Li

AU - Aslam, Nauman

AU - Liu, Changyu

AU - Chattopadhyay, Samiran

PY - 2016/10/24

Y1 - 2016/10/24

N2 - This research presents an abnormal beat detection scheme from lead II Electrocardiogram (ECG) signals along with some improvements on feature extraction. A set of 16 features representing positions, durations, amplitudes and shapes of P, Q, R, S and T waves is proposed in this work for heart beat classification. These features carry important medical information for normal and abnormal beat detection. Diverse classifiers are employed for abnormality detection, including K-Nearest Neighbor, Decision Tree, Artificial Neural Network, Naive Bayesian Classifier, Random Forest, and Support Vector Machine along with some ensemble classifiers such as AdaBoostM1 and Bagging. We have evaluated the proposed system on raw one lead signals extracted from MIT-BIH Arrhythmia, QT and European ST-T databases in the Physionet databank. The experiments using this new set of 16 features achieve better performance for the three test databases than our previous system using a subset of these features.

AB - This research presents an abnormal beat detection scheme from lead II Electrocardiogram (ECG) signals along with some improvements on feature extraction. A set of 16 features representing positions, durations, amplitudes and shapes of P, Q, R, S and T waves is proposed in this work for heart beat classification. These features carry important medical information for normal and abnormal beat detection. Diverse classifiers are employed for abnormality detection, including K-Nearest Neighbor, Decision Tree, Artificial Neural Network, Naive Bayesian Classifier, Random Forest, and Support Vector Machine along with some ensemble classifiers such as AdaBoostM1 and Bagging. We have evaluated the proposed system on raw one lead signals extracted from MIT-BIH Arrhythmia, QT and European ST-T databases in the Physionet databank. The experiments using this new set of 16 features achieve better performance for the three test databases than our previous system using a subset of these features.

UR - http://www.scopus.com/inward/record.url?scp=84997839810&partnerID=8YFLogxK

U2 - 10.1109/FSKD.2016.7603383

DO - 10.1109/FSKD.2016.7603383

M3 - Conference contribution

AN - SCOPUS:84997839810

SP - 1402

EP - 1406

BT - 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016

A2 - Du, Jiayi

A2 - Liu, Chubo

A2 - Li, Kenli

A2 - Wang, Lipo

A2 - Tong, Zhao

A2 - Li, Maozhen

A2 - Xiong, Ning

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery

Y2 - 13 August 2016 through 15 August 2016

ER -

Pandit D, Zhang L, Aslam N, Liu C, Chattopadhyay S. Improved abnormality detection from raw ECG signals using feature enhancement. In Du J, Liu C, Li K, Wang L, Tong Z, Li M, Xiong N, editors, 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1402-1406. 7603383 doi: 10.1109/FSKD.2016.7603383

Improved abnormality detection from raw ECG signals using feature enhancement

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this