A Low Power Cardiovascular Healthcare System With Cross-Layer Optimization From Sensing Patch to Cloud Platform
Authors:
- Chenyu WangCWChenyu Wang
- Yajie QinYQYajie Qin
- Han JinHJHan Jin
- Ikhwan KimIKIkhwan Kim
- Jose David Granados VergaraJVJose David Granados Vergara
- Chenjie DongCDChenjie Dong
- Yizhou JiangYJYizhou Jiang
- Qifan ZhouQZQifan Zhou
- Junshang LiJLJunshang Li
- Zishang HeZHZishang He
- Zhuo ZouZZZhuo Zou
- Li-Rong ZhengLZLi-Rong Zheng
- 11 January 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 13 (2) , 314-329
Abstract
Nowadays, cardiovascular disease is still one of the primary diseases that limit life expectation of humans. To address this challenge, this work reports an Internet of Medical Things (IoMT)-based cardiovascular healthcare system with cross-layer optimization from sensing patch to cloud platform. A wearable ECG patch with a custom System-on-Chip (SoC) features a miniaturized footprint, low power consumption, and embedded signal processing capability. The patch also integrates wireless connectivity with mobile devices and cloud platform for optimizing the complete system. On the big picture, a "wearable patch-mobile-cloud" hybrid computing framework is proposed with cross-layer optimization for performance-power trade-off in embedded-computing. The measurement results demonstrate that the on-patch compression ratio of the raw ECG signal can reach 12.07 yielding a percentage root mean square variation of 2.29%. In the test with the MIT-BIH database, the average improvement of signal to noise ratio and mean square error are 12.63 dB and 94.47%, respectively. The average accuracy of disease prediction operation executed in cloud platform is 97%.Keywords
Funding Information
- National Natural Science Foundation of China (61571137)
- Science and Technology Commission of Shanghai Municipality (17JC1401400, 134419002800)
This publication has 42 references indexed in Scilit:
- A Wearable Patch to Enable Long-Term Monitoring of Environmental, Activity and Hemodynamics VariablesIEEE Transactions on Biomedical Circuits and Systems, 2015
- AIWAC: affective interaction through wearable computing and cloud technologyIEEE Wireless Communications, 2015
- Just-in-Time Code Offloading for Wearable ComputingIEEE Transactions on Emerging Topics in Computing, 2015
- Low-Power Wireless ECG Acquisition and Classification System for Body Sensor NetworksIEEE Journal of Biomedical and Health Informatics, 2015
- A Wearable Healthcare System With a 13.7 $\mu$ A Noise Tolerant ECG ProcessorIEEE Transactions on Biomedical Circuits and Systems, 2014
- Comparative study of ECG signal denoising by wavelet thresholding in empirical and variational mode decomposition domainsHealthcare Technology Letters, 2014
- A Novel ECG Data Compression Method Using Adaptive Fourier Decomposition With Security Guarantee in e-Health ApplicationsIEEE Journal of Biomedical and Health Informatics, 2014
- An ECG-on-Chip With 535 nW/Channel Integrated Lossless Data Compressor for Wireless SensorsIEEE Journal of Solid-State Circuits, 2014
- A Configurable and Low-Power Mixed Signal SoC for Portable ECG Monitoring ApplicationsIEEE Transactions on Biomedical Circuits and Systems, 2013
- Design of Wavelet-Based ECG Detector for Implantable Cardiac PacemakersIEEE Transactions on Biomedical Circuits and Systems, 2013