Dimensionality reduction for anomaly detection in electrocardiography: A manifold approach

Zhinan Li; Wenyao Xu; Anpeng Huang; Majid Sarrafzadeh

doi:10.1109/BSN.2012.12

Dimensionality reduction for anomaly detection in electrocardiography: A manifold approach

Zhinan Li
, Wenyao Xu
, Anpeng Huang
, Majid Sarrafzadeh

Department of Computer Science and Engineering

Peking University
University of California at Los Angeles

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

18 Scopus citations

Abstract

ECG analysis is universal and important in miscellaneous medical applications. However, high computation complexity is a problem which has been shown in several levels of conventional data mining algorithms for ECG analysis. In this paper, we presented a novel manifold approach to visualize and analyze the ECG signal. According to regularity of the data, our algorithm can discover the intrinsic structure and represent the streaming data with a 1-D manifold on a 2-D space. Furthermore, the proposed algorithm can reliably detect the anomaly in ECG streaming data. We evaluated the performance of the algorithm with two different anomalies in wearable applications: for the anomaly from heart disorders such as apnea, arrythmia, our algorithm could achieve up to 90%; recognition rate, for the anomaly from the ECG device, our algorithm could detect the outlier with 100%;.

Original language	English
Title of host publication	Proceedings - BSN 2012
Subtitle of host publication	9th International Workshop on Wearable and Implantable Body Sensor Networks
Pages	161-165
Number of pages	5
DOIs	https://doi.org/10.1109/BSN.2012.12
State	Published - 2012
Event	9th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2012 - London, United Kingdom Duration: May 9 2012 → May 12 2012

Publication series

Name	Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks

Conference

Conference	9th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2012
Country/Territory	United Kingdom
City	London
Period	05/9/12 → 05/12/12

Keywords

Dimensionality Reduction
Electrocardiography
Locally Linear Embedding
Manifold

Access to Document

10.1109/BSN.2012.12

Cite this

Li, Z., Xu, W., Huang, A., & Sarrafzadeh, M. (2012). Dimensionality reduction for anomaly detection in electrocardiography: A manifold approach. In Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks (pp. 161-165). Article 6200560 (Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks). https://doi.org/10.1109/BSN.2012.12

@inproceedings{b1745adc970c43b8852e3e7cd5ccf43a,

title = "Dimensionality reduction for anomaly detection in electrocardiography: A manifold approach",

abstract = "ECG analysis is universal and important in miscellaneous medical applications. However, high computation complexity is a problem which has been shown in several levels of conventional data mining algorithms for ECG analysis. In this paper, we presented a novel manifold approach to visualize and analyze the ECG signal. According to regularity of the data, our algorithm can discover the intrinsic structure and represent the streaming data with a 1-D manifold on a 2-D space. Furthermore, the proposed algorithm can reliably detect the anomaly in ECG streaming data. We evaluated the performance of the algorithm with two different anomalies in wearable applications: for the anomaly from heart disorders such as apnea, arrythmia, our algorithm could achieve up to 90\%; recognition rate, for the anomaly from the ECG device, our algorithm could detect the outlier with 100\%;.",

keywords = "Dimensionality Reduction, Electrocardiography, Locally Linear Embedding, Manifold",

author = "Zhinan Li and Wenyao Xu and Anpeng Huang and Majid Sarrafzadeh",

year = "2012",

doi = "10.1109/BSN.2012.12",

language = "English",

isbn = "9780769546988",

series = "Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks",

pages = "161--165",

booktitle = "Proceedings - BSN 2012",

note = "9th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2012 ; Conference date: 09-05-2012 Through 12-05-2012",

}

Li, Z, Xu, W, Huang, A & Sarrafzadeh, M 2012, Dimensionality reduction for anomaly detection in electrocardiography: A manifold approach. in Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks., 6200560, Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks, pp. 161-165, 9th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2012, London, United Kingdom, 05/9/12. https://doi.org/10.1109/BSN.2012.12

Dimensionality reduction for anomaly detection in electrocardiography: A manifold approach. / Li, Zhinan; Xu, Wenyao; Huang, Anpeng et al.
Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks. 2012. p. 161-165 6200560 (Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks).

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

TY - GEN

T1 - Dimensionality reduction for anomaly detection in electrocardiography

T2 - 9th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2012

AU - Li, Zhinan

AU - Xu, Wenyao

AU - Huang, Anpeng

AU - Sarrafzadeh, Majid

PY - 2012

Y1 - 2012

N2 - ECG analysis is universal and important in miscellaneous medical applications. However, high computation complexity is a problem which has been shown in several levels of conventional data mining algorithms for ECG analysis. In this paper, we presented a novel manifold approach to visualize and analyze the ECG signal. According to regularity of the data, our algorithm can discover the intrinsic structure and represent the streaming data with a 1-D manifold on a 2-D space. Furthermore, the proposed algorithm can reliably detect the anomaly in ECG streaming data. We evaluated the performance of the algorithm with two different anomalies in wearable applications: for the anomaly from heart disorders such as apnea, arrythmia, our algorithm could achieve up to 90%; recognition rate, for the anomaly from the ECG device, our algorithm could detect the outlier with 100%;.

AB - ECG analysis is universal and important in miscellaneous medical applications. However, high computation complexity is a problem which has been shown in several levels of conventional data mining algorithms for ECG analysis. In this paper, we presented a novel manifold approach to visualize and analyze the ECG signal. According to regularity of the data, our algorithm can discover the intrinsic structure and represent the streaming data with a 1-D manifold on a 2-D space. Furthermore, the proposed algorithm can reliably detect the anomaly in ECG streaming data. We evaluated the performance of the algorithm with two different anomalies in wearable applications: for the anomaly from heart disorders such as apnea, arrythmia, our algorithm could achieve up to 90%; recognition rate, for the anomaly from the ECG device, our algorithm could detect the outlier with 100%;.

KW - Dimensionality Reduction

KW - Electrocardiography

KW - Locally Linear Embedding

KW - Manifold

UR - https://www.scopus.com/pages/publications/84862291402

U2 - 10.1109/BSN.2012.12

DO - 10.1109/BSN.2012.12

M3 - Conference contribution

AN - SCOPUS:84862291402

SN - 9780769546988

T3 - Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks

SP - 161

EP - 165

BT - Proceedings - BSN 2012

Y2 - 9 May 2012 through 12 May 2012

ER -

Li Z, Xu W, Huang A, Sarrafzadeh M. Dimensionality reduction for anomaly detection in electrocardiography: A manifold approach. In Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks. 2012. p. 161-165. 6200560. (Proceedings - BSN 2012: 9th International Workshop on Wearable and Implantable Body Sensor Networks). doi: 10.1109/BSN.2012.12

Dimensionality reduction for anomaly detection in electrocardiography: A manifold approach

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this