Low Power Optimisations for IoT Wearable Sensors Based on Evaluation of Nine QRS Detection Algorithms

Abstract

This paper aims to reduce the power consumption of electrocardiography based wearable healthcare devices, by introducing power reduction approaches and considerations at system level design, where we have the highest potential to influence power. It focuses, in particular, on algorithm design and implementation, data acquisition, and transmission under constrained resources. A thorough investigation of the suitability of nine existing algorithms for on-sensor QRS feature detection is conducted, with respect to metrics such as sensitivity, positive predictivity, power consumption, parameter choice and time delay. Optimisation of data acquisition on CPU-based IoT systems is performed, and the current consumption is reduced by a factor of 3 using a combination of direct memory access (DMA) list approach and low-level register manipulations for task delegation. The acquisition data rate, sampling rate, buffer and batch size are also optimised. To reduce the power consumption by data transmission, the effect of on-sensor versus off-sensor processing is investigated. While focusing on CPU-based systems with experiments performed on a generic low-power wearable platform, the design optimisation and considerations proposed in this work could be extended to custom designs and allow further investigation into QRS detection algorithm optimisation for wearable devices. INDEX TERMS Bluetooth low energy, direct memory access, Internet of Things, on-chip processing, QRS detection, wearable sensors.

Interpretable Rule Mining for Real-Time ECG Anomaly Detection in IoT Edge Sensors

“…Singleton features 1) Peak locations: The location (in time) of the R peak and the P, QRS, and T waveform onset times are the most elementary features that are the basis of many other elaborate features below. A complete implementation would need to estimate these features using existing algorithms [34], [35], [36]. In this work we assume, that R-peak detection is done on-chip by the data acquisition analog-front-end circuit, as in the case of commercially available solutions [37].…”

ANNet: A Lightweight Neural Network for ECG Anomaly Detection in IoT Edge Sensors

“…Additionally, we chose to use R-peak location annotations from MIT-BIH database [21] directly instead of implementing our own R-peak detector. Since there are several existing works that achieve good accuracy for R-peak detection [23], [24], [25], we narrowed the scope of this work and focus exclusively on developing the classifier.…”

Prototipo de un monitor cardiaco implementando IOT

“…Esta conexión se conoce como Internet de las Cosas (IoT), con la cual es posible realizar el monitoreo de variables y automatización de procesos de forma rápida y segura, permitiendo conectar una variedad de dispositivos a Internet, logrando una comunicación con las personas y objetos (Luna et al, 2019). Una aplicación de la IoT es en el campo de la salud, con el desarrollo de dispositivos de monitoreo cardíaco, el cual ha crecido en los últimos años, estos dispositivos tienen la ventaja de permitir una mayor movilidad, además de ser útiles en la detección temprana de enfermedades cardiovasculares en comparación con los monitores Holter tradicionales (Li et al, 2020). Es aquí donde se destaca el Internet de las cosas (IoT), el cual tiene el potencial de mejorar las aplicaciones médicas en los dispositivos de electrocardiografía.…”