FETCH: A Deep Learning-Based Fog Computing and IoT Integrated Environment for Healthcare Monitoring and Diagnosis

Abstract

These days cloud-based infrastructure is facing many challenges, out of which the major issue is their syncing data before cutover and data migration. Due to the limited scalability in terms of security concerns of cloud computing, the need for a centralized IoTs based environment has been constrained to a limited extent. The sensitivity of device latency emerged during healthy systems such as health monitoring, etc. is the main reason, because healthy systems require computing operations on high-volume data. Fog computing provides an innovative solution to improve the performance of cloud computing, providing the ability to take the necessary resources and those that are closer to the end-users. Existing fog computing models retain several limitations, such as either considering result accuracy or overestimating response time, but managing both together impairs system compatibility. FETCH is a proposed framework that integrates with edge computing devices to work on deep learning technology and automated monitoring and offers a highly useful framework for real-life health care systems such as heart disease and more. The proposed Fog-enabled cloud computing framework uses FogBus, which demonstrates utility in the form of consumption of power, network bandwidth, jitter, latency, process execution time, and their accuracy as well.

Keywords

• Fog computing
• edge computing
• healthcare
• machine learning (ML)
• deep learning (DL)
• Internet of Things (IoT)