GeM-REM: Generative model-driven resource efficient ECG monitoring in body sensor networks

Sidharth Nabar, Ayan Banerjee, Sandeep Gupta, Radha Poovendran

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

23 Citations (Scopus)

Abstract

With recent advances in smartphones and wearable sensors, Body Sensor Networks (BSNs) have been proposed for use in continuous, remote electrocardiogram (ECG) monitoring. In such systems, sampling the ECG at clinically recommended rates (250 Hz) and wireless transmission of the collected data incurs high energy consumption at the energy-constrained body sensor. The large volume of collected data also makes data storage at the sensor infeasible. Thus, there is a need for reducing the energy consumption and data size at the sensor, while maintaining the ECG quality required for diagnosis. In this paper, we propose GeM-REM, a resource-efficient ECG monitoring method for BSNs. GeM-REM uses a generative ECG model at the base station and its lightweight version at the sensor. The sensor transmits data only when the sensed ECG deviates from model-based values, thus saving transmission energy. Further, the model parameters are continually updated based on the sensed ECG. The proposed approach enables storage of ECG data in terms of model parameters rather than data samples, which reduces the required storage space. Implementation on a sensor platform and evaluation using real ECG data from MIT-BIH dataset shows transmission energy and data storage reduction ratios of 42.1:1 and 37.3:1 respectively, which are better than state of the art ECG data compression schemes.

Original languageEnglish (US)
Title of host publicationProceedings - 2011 International Conference on Body Sensor Networks, BSN 2011
Pages1-6
Number of pages6
DOIs
StatePublished - 2011
Event8th International Conference on Body Sensor Networks, BSN 2011 - Dallas, TX, United States
Duration: May 23 2011May 25 2011

Other

Other8th International Conference on Body Sensor Networks, BSN 2011
CountryUnited States
CityDallas, TX
Period5/23/115/25/11

Fingerprint

Body sensor networks
Electrocardiography
Monitoring
Sensors
Energy utilization
Smartphones
Data compression
Base stations
Energy storage

Keywords

  • Body sensor networks
  • BSN
  • ECG monitoring
  • Generative model
  • Model-based communication
  • Resource-efficient

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Nabar, S., Banerjee, A., Gupta, S., & Poovendran, R. (2011). GeM-REM: Generative model-driven resource efficient ECG monitoring in body sensor networks. In Proceedings - 2011 International Conference on Body Sensor Networks, BSN 2011 (pp. 1-6). [5955287] https://doi.org/10.1109/BSN.2011.29

GeM-REM : Generative model-driven resource efficient ECG monitoring in body sensor networks. / Nabar, Sidharth; Banerjee, Ayan; Gupta, Sandeep; Poovendran, Radha.

Proceedings - 2011 International Conference on Body Sensor Networks, BSN 2011. 2011. p. 1-6 5955287.

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

Nabar, S, Banerjee, A, Gupta, S & Poovendran, R 2011, GeM-REM: Generative model-driven resource efficient ECG monitoring in body sensor networks. in Proceedings - 2011 International Conference on Body Sensor Networks, BSN 2011., 5955287, pp. 1-6, 8th International Conference on Body Sensor Networks, BSN 2011, Dallas, TX, United States, 5/23/11. https://doi.org/10.1109/BSN.2011.29
Nabar S, Banerjee A, Gupta S, Poovendran R. GeM-REM: Generative model-driven resource efficient ECG monitoring in body sensor networks. In Proceedings - 2011 International Conference on Body Sensor Networks, BSN 2011. 2011. p. 1-6. 5955287 https://doi.org/10.1109/BSN.2011.29
Nabar, Sidharth ; Banerjee, Ayan ; Gupta, Sandeep ; Poovendran, Radha. / GeM-REM : Generative model-driven resource efficient ECG monitoring in body sensor networks. Proceedings - 2011 International Conference on Body Sensor Networks, BSN 2011. 2011. pp. 1-6
@inproceedings{2e1530d032b74a498fe992402e9ecaab,
title = "GeM-REM: Generative model-driven resource efficient ECG monitoring in body sensor networks",
abstract = "With recent advances in smartphones and wearable sensors, Body Sensor Networks (BSNs) have been proposed for use in continuous, remote electrocardiogram (ECG) monitoring. In such systems, sampling the ECG at clinically recommended rates (250 Hz) and wireless transmission of the collected data incurs high energy consumption at the energy-constrained body sensor. The large volume of collected data also makes data storage at the sensor infeasible. Thus, there is a need for reducing the energy consumption and data size at the sensor, while maintaining the ECG quality required for diagnosis. In this paper, we propose GeM-REM, a resource-efficient ECG monitoring method for BSNs. GeM-REM uses a generative ECG model at the base station and its lightweight version at the sensor. The sensor transmits data only when the sensed ECG deviates from model-based values, thus saving transmission energy. Further, the model parameters are continually updated based on the sensed ECG. The proposed approach enables storage of ECG data in terms of model parameters rather than data samples, which reduces the required storage space. Implementation on a sensor platform and evaluation using real ECG data from MIT-BIH dataset shows transmission energy and data storage reduction ratios of 42.1:1 and 37.3:1 respectively, which are better than state of the art ECG data compression schemes.",
keywords = "Body sensor networks, BSN, ECG monitoring, Generative model, Model-based communication, Resource-efficient",
author = "Sidharth Nabar and Ayan Banerjee and Sandeep Gupta and Radha Poovendran",
year = "2011",
doi = "10.1109/BSN.2011.29",
language = "English (US)",
isbn = "9780769544311",
pages = "1--6",
booktitle = "Proceedings - 2011 International Conference on Body Sensor Networks, BSN 2011",

}

TY - GEN

T1 - GeM-REM

T2 - Generative model-driven resource efficient ECG monitoring in body sensor networks

AU - Nabar, Sidharth

AU - Banerjee, Ayan

AU - Gupta, Sandeep

AU - Poovendran, Radha

PY - 2011

Y1 - 2011

N2 - With recent advances in smartphones and wearable sensors, Body Sensor Networks (BSNs) have been proposed for use in continuous, remote electrocardiogram (ECG) monitoring. In such systems, sampling the ECG at clinically recommended rates (250 Hz) and wireless transmission of the collected data incurs high energy consumption at the energy-constrained body sensor. The large volume of collected data also makes data storage at the sensor infeasible. Thus, there is a need for reducing the energy consumption and data size at the sensor, while maintaining the ECG quality required for diagnosis. In this paper, we propose GeM-REM, a resource-efficient ECG monitoring method for BSNs. GeM-REM uses a generative ECG model at the base station and its lightweight version at the sensor. The sensor transmits data only when the sensed ECG deviates from model-based values, thus saving transmission energy. Further, the model parameters are continually updated based on the sensed ECG. The proposed approach enables storage of ECG data in terms of model parameters rather than data samples, which reduces the required storage space. Implementation on a sensor platform and evaluation using real ECG data from MIT-BIH dataset shows transmission energy and data storage reduction ratios of 42.1:1 and 37.3:1 respectively, which are better than state of the art ECG data compression schemes.

AB - With recent advances in smartphones and wearable sensors, Body Sensor Networks (BSNs) have been proposed for use in continuous, remote electrocardiogram (ECG) monitoring. In such systems, sampling the ECG at clinically recommended rates (250 Hz) and wireless transmission of the collected data incurs high energy consumption at the energy-constrained body sensor. The large volume of collected data also makes data storage at the sensor infeasible. Thus, there is a need for reducing the energy consumption and data size at the sensor, while maintaining the ECG quality required for diagnosis. In this paper, we propose GeM-REM, a resource-efficient ECG monitoring method for BSNs. GeM-REM uses a generative ECG model at the base station and its lightweight version at the sensor. The sensor transmits data only when the sensed ECG deviates from model-based values, thus saving transmission energy. Further, the model parameters are continually updated based on the sensed ECG. The proposed approach enables storage of ECG data in terms of model parameters rather than data samples, which reduces the required storage space. Implementation on a sensor platform and evaluation using real ECG data from MIT-BIH dataset shows transmission energy and data storage reduction ratios of 42.1:1 and 37.3:1 respectively, which are better than state of the art ECG data compression schemes.

KW - Body sensor networks

KW - BSN

KW - ECG monitoring

KW - Generative model

KW - Model-based communication

KW - Resource-efficient

UR - http://www.scopus.com/inward/record.url?scp=80052003009&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052003009&partnerID=8YFLogxK

U2 - 10.1109/BSN.2011.29

DO - 10.1109/BSN.2011.29

M3 - Conference contribution

AN - SCOPUS:80052003009

SN - 9780769544311

SP - 1

EP - 6

BT - Proceedings - 2011 International Conference on Body Sensor Networks, BSN 2011

ER -