Deep ECG estimation using a bed-attached geophone

Jae Yeon Park, Hyeon Cho, Wonjun Hwang, Rajesh Krishna Balan, Jeong Gil Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Electrocardiogram (ECG) signals offer rich information for analyzing and understanding the cardiac activity of a person. The continuous monitoring of ECG can help diagnose cardiac disorders, such as arrhythmia, effectively. While many wearable healthcare platforms offer continuous ECG monitoring, these devices are cumbersome in the fact that they need to be continuously attached to the human body, which causes uncomfortableness, and limits their usage when monitoring a person's ECG throughout the night as they sleep. In this work, we propose a fully non-intrusive sensing system for monitoring the ECG of a person while in bed. Specifically, we present Heartquake, a geophone-based sensing system for extracting ECG patterns using heartbeat vibrations that penetrate through the mattress. The cardiac activity-originated vibration patterns are captured on the geophone and sent to a server, where the data is filtered to remove external noise and passed on to a bidirectional long short term memory (Bi-LSTM) deep learning model for ECG waveform extraction. Our experimental results with 21study participants suggest that Heartquake can detect all five ECG peaks (e.g., P, Q, R, S, T) with an average error of as low as 16 msec when participants are stationary on the bed. With additional noise factors, this error shows an increase, but can be mitigated from model personalization to still be sufficient enough as a screening tool to detect urgent situations.

Original languageEnglish
Title of host publicationMobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services
PublisherAssociation for Computing Machinery, Inc
Pages568-569
Number of pages2
ISBN (Electronic)9781450366618
DOIs
Publication statusPublished - 2019 Jun 12
Event17th ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2019 - Seoul, Korea, Republic of
Duration: 2019 Jun 172019 Jun 21

Publication series

NameMobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services

Conference

Conference17th ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2019
CountryKorea, Republic of
CitySeoul
Period19/6/1719/6/21

Fingerprint

Seismographs
Electrocardiography
Monitoring
Screening
Servers

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Networks and Communications

Cite this

Park, J. Y., Cho, H., Hwang, W., Balan, R. K., & Ko, J. G. (2019). Deep ECG estimation using a bed-attached geophone. In MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services (pp. 568-569). (MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services). Association for Computing Machinery, Inc. https://doi.org/10.1145/3307334.3328629
Park, Jae Yeon ; Cho, Hyeon ; Hwang, Wonjun ; Balan, Rajesh Krishna ; Ko, Jeong Gil. / Deep ECG estimation using a bed-attached geophone. MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services. Association for Computing Machinery, Inc, 2019. pp. 568-569 (MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services).
@inproceedings{fdc3c530e03a4fe8a76574a49fac243e,
title = "Deep ECG estimation using a bed-attached geophone",
abstract = "Electrocardiogram (ECG) signals offer rich information for analyzing and understanding the cardiac activity of a person. The continuous monitoring of ECG can help diagnose cardiac disorders, such as arrhythmia, effectively. While many wearable healthcare platforms offer continuous ECG monitoring, these devices are cumbersome in the fact that they need to be continuously attached to the human body, which causes uncomfortableness, and limits their usage when monitoring a person's ECG throughout the night as they sleep. In this work, we propose a fully non-intrusive sensing system for monitoring the ECG of a person while in bed. Specifically, we present Heartquake, a geophone-based sensing system for extracting ECG patterns using heartbeat vibrations that penetrate through the mattress. The cardiac activity-originated vibration patterns are captured on the geophone and sent to a server, where the data is filtered to remove external noise and passed on to a bidirectional long short term memory (Bi-LSTM) deep learning model for ECG waveform extraction. Our experimental results with 21study participants suggest that Heartquake can detect all five ECG peaks (e.g., P, Q, R, S, T) with an average error of as low as 16 msec when participants are stationary on the bed. With additional noise factors, this error shows an increase, but can be mitigated from model personalization to still be sufficient enough as a screening tool to detect urgent situations.",
author = "Park, {Jae Yeon} and Hyeon Cho and Wonjun Hwang and Balan, {Rajesh Krishna} and Ko, {Jeong Gil}",
year = "2019",
month = "6",
day = "12",
doi = "10.1145/3307334.3328629",
language = "English",
series = "MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services",
publisher = "Association for Computing Machinery, Inc",
pages = "568--569",
booktitle = "MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services",

}

Park, JY, Cho, H, Hwang, W, Balan, RK & Ko, JG 2019, Deep ECG estimation using a bed-attached geophone. in MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services. MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services, Association for Computing Machinery, Inc, pp. 568-569, 17th ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2019, Seoul, Korea, Republic of, 19/6/17. https://doi.org/10.1145/3307334.3328629

Deep ECG estimation using a bed-attached geophone. / Park, Jae Yeon; Cho, Hyeon; Hwang, Wonjun; Balan, Rajesh Krishna; Ko, Jeong Gil.

MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services. Association for Computing Machinery, Inc, 2019. p. 568-569 (MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Deep ECG estimation using a bed-attached geophone

AU - Park, Jae Yeon

AU - Cho, Hyeon

AU - Hwang, Wonjun

AU - Balan, Rajesh Krishna

AU - Ko, Jeong Gil

PY - 2019/6/12

Y1 - 2019/6/12

N2 - Electrocardiogram (ECG) signals offer rich information for analyzing and understanding the cardiac activity of a person. The continuous monitoring of ECG can help diagnose cardiac disorders, such as arrhythmia, effectively. While many wearable healthcare platforms offer continuous ECG monitoring, these devices are cumbersome in the fact that they need to be continuously attached to the human body, which causes uncomfortableness, and limits their usage when monitoring a person's ECG throughout the night as they sleep. In this work, we propose a fully non-intrusive sensing system for monitoring the ECG of a person while in bed. Specifically, we present Heartquake, a geophone-based sensing system for extracting ECG patterns using heartbeat vibrations that penetrate through the mattress. The cardiac activity-originated vibration patterns are captured on the geophone and sent to a server, where the data is filtered to remove external noise and passed on to a bidirectional long short term memory (Bi-LSTM) deep learning model for ECG waveform extraction. Our experimental results with 21study participants suggest that Heartquake can detect all five ECG peaks (e.g., P, Q, R, S, T) with an average error of as low as 16 msec when participants are stationary on the bed. With additional noise factors, this error shows an increase, but can be mitigated from model personalization to still be sufficient enough as a screening tool to detect urgent situations.

AB - Electrocardiogram (ECG) signals offer rich information for analyzing and understanding the cardiac activity of a person. The continuous monitoring of ECG can help diagnose cardiac disorders, such as arrhythmia, effectively. While many wearable healthcare platforms offer continuous ECG monitoring, these devices are cumbersome in the fact that they need to be continuously attached to the human body, which causes uncomfortableness, and limits their usage when monitoring a person's ECG throughout the night as they sleep. In this work, we propose a fully non-intrusive sensing system for monitoring the ECG of a person while in bed. Specifically, we present Heartquake, a geophone-based sensing system for extracting ECG patterns using heartbeat vibrations that penetrate through the mattress. The cardiac activity-originated vibration patterns are captured on the geophone and sent to a server, where the data is filtered to remove external noise and passed on to a bidirectional long short term memory (Bi-LSTM) deep learning model for ECG waveform extraction. Our experimental results with 21study participants suggest that Heartquake can detect all five ECG peaks (e.g., P, Q, R, S, T) with an average error of as low as 16 msec when participants are stationary on the bed. With additional noise factors, this error shows an increase, but can be mitigated from model personalization to still be sufficient enough as a screening tool to detect urgent situations.

UR - http://www.scopus.com/inward/record.url?scp=85069221880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069221880&partnerID=8YFLogxK

U2 - 10.1145/3307334.3328629

DO - 10.1145/3307334.3328629

M3 - Conference contribution

AN - SCOPUS:85069221880

T3 - MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services

SP - 568

EP - 569

BT - MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services

PB - Association for Computing Machinery, Inc

ER -

Park JY, Cho H, Hwang W, Balan RK, Ko JG. Deep ECG estimation using a bed-attached geophone. In MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services. Association for Computing Machinery, Inc. 2019. p. 568-569. (MobiSys 2019 - Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services). https://doi.org/10.1145/3307334.3328629