Migrating Intelligence from Cloud to Ultra-Edge Smart IoT Sensor Based on Deep Learning: An Arrhythmia Monitoring Use-Case
Migrating Intelligence from Cloud to Ultra-Edge Smart IoT Sensor Based on Deep Learning: An Arrhythmia Monitoring Use-Case
复制标题
基于深度学习将智能从云端迁移到超边缘智能物联网传感器：心律失常监测用例
DOI：
10.1109/iwcmc48107.2020.9148134
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
N. Nasser
中科院分区：
文献类型：
--
作者：
S. Sakib;M. Fouda;Z. Fadlullah;N. Nasser
传统上，部署在网络超边缘的物联网（IoT）设备缺乏计算和能源。在本文中，我们强调了超越传统边缘计算领域的必要性（例如，仅限于用户智能手机），并研究如何将智能融入超边缘物联网传感器。在众多用例中，我们选择了一个移动的健康（mHealth）场景，在该场景中，我们将智能物联网传感器概念化，以收集和智能处理单通道心电图（ECG）信号，以检测心律失常，这是一种通常与发病率甚至死亡率相关的心脏病。心律失常检测可以被视为非线性延迟微分方程（DDE）时间序列分析问题，并且由于严格的预处理步骤，该问题的常规解决方案不适合与物联网传感器集成。作为解决方案，本文提出了一种基于卷积神经网络（CNN）的轻量级心律失常分类系统，无需噪声过滤和特征提取步骤。四类心跳被认为符合ANSI/AAMI EC57：1998标准。该系统的性能和推广潜力使用来自PhysioNet的三个数据集进行评估，这些数据集在深度学习工作站上进行训练，然后转移到连接到物联网传感器的虚拟化微控制器。所提出的深度学习模型在心跳分类方面表现出令人鼓舞的性能（准确率为95.27%）。实验和数值结果表明，所提出的深度学习技术优于传统的基于DDE的优化技术和机器学习技术，如K最近邻（KNN）和随机森林（RF）。
Traditionally, the Internet of Things (IoT) devices, deployed on the ultra-edge of the network, lack computation, and energy resources. In this paper, we press on the need to go beyond the realms of traditional edge computing (e.g., limited to user-smartphones) and investigate how to incorporate intelligence into the ultra-edge IoT sensors. Among numerous use-cases, we select a mobile Health (mHealth) scenario where we conceptualize a smart IoT sensor to collect and intelligently process single-channel Electrocardiogram (ECG) signals to detect arrhythmia, a heart-condition often associated with morbidity and even mortality. The arrhythmia detection can be regarded as a non-linear Delay Differential Equation (DDE) time-series analysis problem, and the conventional solutions to this problem are not suitable for integration with IoT sensors due to rigorous pre-processing steps. As a solution, a Convolutional Neural Network (CNN)-based, lightweight Arrhythmia classification system is proposed in the paper without the need for noise-filtering and feature extraction steps. Four classes of the heartbeats are considered to comply with the ANSI/AAMI EC57:1998 standard. The proposed system's performances and generalization potential are assessed using three datasets from PhysioNet trained on a deep learning workstation and then transferred to virtualized micro-controllers connected to IoT sensors. The proposed deep learning model exhibits encouraging performance (accuracy 95.27%) in heartbeat classification. Experimental and numerical results demonstrate that the proposed deep learning technique outperforms conventional DDE-based optimization techniques and machine learning techniques such as K-Nearest Neighbor (KNN), and random forest (RF).