GeM-REM: Generative Model-Driven Resource Efficient ECG Monitoring in Body Sensor Networks

Nabar, Sidharth; Banerjee, Ayan; Gupta, Sandeep; Poovendran, Radha

doi:10.1109/bsn.2011.29

Cited by 27 publications

(26 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such models have previously been used in several diverse areas such as Wireless Sensor Networks [11] and music [8]. In our prior work [17], we demonstrated the use of such models for resource-efficient physiological data collection, through an ECG monitoring application. We now describe the basic generative model-driven data reporting methodology and outline the challenges involved in using such a technique for reliable wireless monitoring of PPG.…”

Section: Generative Model Based Physi-ological Data Monitoringmentioning

confidence: 99%

“…These two signals are then temporally aligned and constitute the final output signal available to the physician or caregiver for analysis. This technique was used for ECG monitoring in our prior work [17], where an existing generative model (ECGYSN [14]) was used as G. Evaluation with real ECG data from MIT-BIH [1] database showed significant energy and memory savings at a minimal loss in diagnostic accuracy. However, the effects of wireless channel errors or wearable sensor-induced signal artifacts on the performance of the method were not investigated.…”

Section: Generative Model Based Physi-ological Data Monitoringmentioning

confidence: 99%

“…The sensor transmits data updates whenever the model-generated signal does not match the sensed data, thus capturing temporal variations in the sensed signal. Such a model based data collection technique has been shown to achieve high energy savings for continuous ECG monitoring [17]. Using this technique for wireless PPG monitoring could enable significant energy and bandwidth savings, while maintaining the data accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Resource-efficient and reliable long term wireless monitoring of the photoplethysmographic signal

Nabar

Banerjee

Gupta

et al. 2011

Proceedings of the 2nd Conference on Wireless Health

Self Cite

View full text Add to dashboard Cite

Wearable photoplethysmogram (PPG) sensors are extensively used for remote monitoring of blood oxygen level and flow rate in numerous pervasive healthcare applications with diverse quality of service requirements. These sensors operate under severe resource constraints and communicate over an adverse wireless channel with human body-induced path loss and mobility-caused fading. In this paper, we take a generative model-based data collection approach towards achieving energy-efficient and reliable PPG monitoring. We develop two models that can generate synthetic PPG signals given a set of input parameters. These generative models are then used to design and implement a resource-efficient, reliable data reporting method for wireless PPG sensors. We investigate the performance of our method under realistic wireless channel error models and provide methods to improve accuracy at a marginal energy cost. We implement the proposed technique using existing sensor platforms and evaluate its performance on two datasets: MIMIC database and data collected using commercial wearable sensors. Results show significant bandwidth and energy savings due to data transmission reduction. The average reduction in data size for wearable sensor-based data is 300:1, while maintaining a diagnostic accuracy above 94%.

show abstract

Section: Generative Model Based Physi-ological Data Monitoringmentioning

confidence: 99%

Section: Generative Model Based Physi-ological Data Monitoringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Resource-efficient and reliable long term wireless monitoring of the photoplethysmographic signal

Nabar

Banerjee

Gupta

et al. 2011

Proceedings of the 2nd Conference on Wireless Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…Otherwise, the sensor sends updates to the base station. These updates can be single model parameter values (called feature updates) or set of raw signal samples (called raw signal updates) as explained in [5]. At the server, if no data is received from the sensor, the server uses G to generate a waveform closely resembling the physiological signal of interest.…”

Section: Introductionmentioning

confidence: 99%

Energy-efficient long term physiological monitoring

Banerjee

Nabar

Gupta

et al. 2011

Proceedings of the 2nd Conference on Wireless Health

Self Cite

View full text Add to dashboard Cite

Recently, several wireless body sensor-based systems have been proposed for continuous, long-term physiological monitoring. A major challenge in such systems is that a large amount of data is collected, and transmission of this data incurs significant energy consumption at the sensor. In this work, we demonstrate a data reporting method that significantly reduces energy consumption while maintaining a high diagnostic accuracy of the reported physiological signal. This is achieved by using a generative model of the physiological signal of interest at the sensor, and suppressing data transmission when sensed data matches the model. In this demonstration, we implement the proposed technique for electrocardiogram (ECG) signal and illustrate its performance in terms of energy savings and accuracy of reported data.

show abstract

“…ECG signal is a time-varying signal representing the electrical activity of the heart. It is an effective, non-invasive diagnostic tool for cardiac monitoring [1].…”

Section: Introductionmentioning

confidence: 99%

Design and Implementation of Wireless Body Area Network using physiological parameters

Sindhu

2017

JBEMi

View full text Add to dashboard Cite

Applications of e-Health deals with various physiological signals like body temperature, Blood Pressure, Electrocardiogram(ECG) captured by either wired networks or wireless sensor networks (WSN).ECG is one of the important parameter. A three lead based ECG acquisition system, body temperature; pulse rate monitoring system is presented in the paper below which can store data. The data can be sent wirelessly to the doctor for further analysis. The proposed design makes use of wearable sensors which will not be of discomfort to the patient. The patient can move around easily.

show abstract

GeM-REM: Generative Model-Driven Resource Efficient ECG Monitoring in Body Sensor Networks

Cited by 27 publications

References 5 publications

Resource-efficient and reliable long term wireless monitoring of the photoplethysmographic signal

Resource-efficient and reliable long term wireless monitoring of the photoplethysmographic signal

Energy-efficient long term physiological monitoring

Design and Implementation of Wireless Body Area Network using physiological parameters

Contact Info

Product

Resources

About