Energy-Efficient Real-Time Heart Monitoring on Edge-Fog-Cloud Internet-of-Medical-Things

• Published in: IEEE internet of things journal Vol. 9; no. 14; p. 1
• Main Authors: Demirel, Berken Utku, Bayoumy, Islam Abdelsalam, Faruque, Mohammad Abdullah Al
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 15.07.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Anomalies; Arrhythmia; Artificial neural networks; Classification; Electrocardiogram; Electrocardiography; Energy consumption; Energy efficiency; Feature extraction; Heart Monitoring; Image edge detection; Internet of medical things; Internet of Things; Internet-of-Medical-Things (IoMT); Methodology; Monitoring; Network latency; Noise measurement; Power management; Real time; Real-time systems; Signal monitoring; Signal quality; Telemedicine; Wearable computers; Wearable Systems; Wearable technology
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2021.3138516

The recent developments in wearable devices and the Internet of Medical Things (IoMT) allow real-time monitoring and recording of electrocardiogram (ECG) signals. However, continuous monitoring of ECG signals is challenging in low-power wearable devices due to energy and memory constraints. Therefore, in this paper, we present a novel and energy-efficient methodology for continuously monitoring the heart for low-power wearable devices. The proposed methodology is composed of three different layers: 1) a Noise/Artifact detection layer to grade the quality of the ECG signals; 2) a Normal/Abnormal beat classification layer to detect the anomalies in the ECG signals, and 3) an Abnormal beat classification layer to detect diseases from ECG signals. Moreover, a distributed multi-output Convolutional Neural Network (CNN) architecture is used to decrease the energy consumption and latency between the edge-fog/cloud. Our methodology reaches an accuracy of 99.2% on the well known MIT-BIH Arrhythmia dataset. Evaluation on real hardware shows that our methodology is suitable for devices having a minimum RAM of 32KB. Moreover, the proposed methodology achieves 7× more energy efficiency compared to state-of-the-art works.