A Three Layered Decentralized IoT Biometric Architecture for City Lockdown During COVID-19 Outbreak.

Manjur Kolhar,Abdalla Alameen,Mosleh M Abualhaj,Fadi Al-Turjman

doi:10.1109/access.2020.3021983

Abstract

In this article, we have built a prototype of a decentralized IoT based biometric face detection framework for cities that are under lockdown during COVID-19 outbreaks. To impose restrictions on public movements, we have utilized face detection using three-layered edge computing architecture. We have built a deep learning framework of multi-task cascading to recognize the face. For the face detection proposal we have compared with the state of the art methods on various benchmarking dataset such as FDDB and WIDER FACE. Furthermore, we have also conducted various experiments on latency and face detection load on three-layer and cloud computing architectures. It shows that our proposal has an edge over cloud computing architecture.

Highlights

It is reported that by 2020, more than 50 billion devices will be connected through radio communications
A THREE LAYERED DECENTRALIZED IoT BIOMETRIC ARCHITECTURE To have scalability and management of the complete proposed system we have proposed edge-based monitoring and control system for the residents
We have validated our proposal against the state-of-theart face detection and recognition methods under distributed and centralized architecture in terms of a load of devices and their work is done with respect to response time

Summary

Introduction

It is reported that by 2020, more than 50 billion devices will be connected through radio communications. IoT network, are employed in many fields including security, agriculture, utility management, smart homes and health care systems [1]–[6]. These capabilities are further extended to IoT enabled services with smart devices. Such combinations of services are more suitable to users. Because they have certain features which makes more competitive among other wireless devices, and these features are long range communications, low data rate, consumption of less energy and less cost.

Objectives

Results

Conclusion