ECG Signal Reconstruction on the IoT-Gateway and Efficacy of Compressive Sensing Under Real-time Constraints

Abstract

Remote health monitoring is becoming indispensable, though, Internet of Things (IoTs)-based solutions have many implementation challenges, including energy consumption at the sensing node, and delay and instability due to cloud computing. Compressive sensing (CS) has been explored as a method to extend the battery lifetime of medical wearable devices. However, it is usually associated with computational complexity at the decoding end, increasing the latency of the system. Meanwhile, mobile processors are becoming computationally stronger and more efficient. Heterogeneous multicore platforms (HMPs) offer a local processing solution that can alleviate the limitations of remote signal processing. This paper demonstrates the real-time performance of compressed ECG reconstruction on ARM's big.LITTLE HMP and the advantages they provide as the primary processing unit of the IoT architecture. It also investigates the efficacy of CS in minimizing power consumption of a wearable device under real-time and hardware constraints. Results show that both the orthogonal matching pursuit and subspace pursuit reconstruction algorithms can be executed on the platform in real time and yield optimum performance on a single A15 core at minimum frequency. The CS extends the battery life of wearable medical devices up to 15.4% considering ECGs suitable for wellness applications and up to 6.6% for clinical grade ECGs. Energy consumption at the gateway is largely due to an active internet connection; hence, processing the signals locally both mitigates system's latency and improves gateway's battery life. Many remote health solutions can benefit from an architecture centered around the use of HMPs, a step toward better remote health monitoring systems.