A Fast and Robust Non-Sparse Signal Recovery Algorithm for Wearable ECG Telemonitoring Using ADMM-Based Block Sparse Bayesian Learning.

Yunfei Cheng,Xuesong Deng,Mengshu Hou,Yalan Ye,Yunxia Li,Wenwen He

doi:10.3390/s18072021

Abstract

Wearable telemonitoring of electrocardiogram (ECG) based on wireless body Area networks (WBAN) is a promising approach in next-generation patient-centric telecardiology solutions. In order to guarantee long-term effective operation of monitoring systems, the power consumption of the sensors must be strictly limited. Compressed sensing (CS) is an effective method to alleviate this problem. However, ECG signals in WBAN are usually non-sparse, and most traditional compressed sensing recovery algorithms have difficulty recovering non-sparse signals. In this paper, we proposed a fast and robust non-sparse signal recovery algorithm for wearable ECG telemonitoring. In the proposed algorithm, the alternating direction method of multipliers (ADMM) is used to accelerate the speed of block sparse Bayesian learning (BSBL) framework. We used the famous MIT-BIH Arrhythmia Database, MIT-BIH Long-Term ECG Database and ECG datasets collected in our practical wearable ECG telemonitoring system to verify the performance of the proposed algorithm. The experimental results show that the proposed algorithm can directly recover ECG signals with a satisfactory accuracy in a time domain without a dictionary matrix. Due to acceleration by ADMM, the proposed algorithm has a fast speed, and also it is robust for different ECG datasets. These results suggest that the proposed algorithm is very promising for wearable ECG telemonitoring.

Highlights

Wearable telemonitoring of electrocardiogram (ECG) via wireless body area networks (WBAN) is a very important topic in telemedicine, and many works focused on the devices, sensor networks and other subjects in ECG telemonitoring [1,2,3], but the most significant challenge of practical application of wearable remote ECG monitoring system is power consumption [4]
After we obtain the analog ECG signals via AD8232, an analog-digital converter is used to sample the analog signals to digital signals at the sampling frequency 250 Hz [35], which is commonly used for ECG monitoring in body area networks
A STM32 microcontroller is used to compress the digital ECG signals by a simple matrix-vector multiplication based on compressed sensing, these compressed data are transmitted to a computer via bluetooth, and the ECG signals are recovered from the compressed data on the computer

Summary

Introduction

Wearable telemonitoring of electrocardiogram (ECG) via wireless body area networks (WBAN) is a very important topic in telemedicine, and many works focused on the devices, sensor networks and other subjects in ECG telemonitoring [1,2,3], but the most significant challenge of practical application of wearable remote ECG monitoring system is power consumption [4]. In common WBAN-based ECG monitors, sensor nodes fall short of energy efficiency due to large data acquired from continuous monitoring and the energy wireless links [7,8], it is desirable to reduce the amount of data that need to be acquired and transmitted. Sensors 2018, 18, 2021 signals are firstly sampled via an analog-digital converter; these samples are compressed by a measurement matrix and transmitted to the remote terminal, and the ECG signals are recovered from the compressed data in the remote terminal. Many studies have focused on the application of compressed sensing in WBAN-based ECG monitoring [12,13,14,15], but it is still in its infancy [16]

Methods

Results

Discussion

Conclusion