A Lightweight Smart Camera Solution for Covid-19

With the growth of IoT devices and edge computing technologies, a challenge is to deal with the network capacity and response latency in real-time applications. Such an approach to the solutions is to deploy the Artificial Intelligence (AI) and Internet of Thing (IoT) applications, namely AIoT and Internet of Things (IoT) applications at the edge. In this paper, we introduce a smart AIoT solution to support the control of covid-19 epidemic with two main features: social distance application to control social distance violators in different areas and facemask detection to identify violators who didn't wear a mask. The proposed design architecture comprises three layers: the first one is the Centralized Cloud, which implements the backend, a web server connects to a secure database. The web dashboard helps the administrators manage the streams of surveillance cameras, visualize the number of social distance violators in different areas, and show recorded facemask violators in table for convenient;the second layer is the Edge, social distance and facemask services are packaged into Docker container and deployed in a lightweight Kubernetes (K3s) cluster which have GPU. The Cluster should be deployed on both Jetson Nano and Raspberry Pi 3 devices. This design intends to increase high availability, scalability, self-healing, resource utilization, stability, and automation deployment for the edge services;and the final layer - the End Devices, which includes multiple cameras connected directly to the AI services at Edge. These cameras help us collect and send data to the edge servers for analyzing purpose. The results show that the proposed system works correctly, edge services run at an acceptable framerate. © 2022 IEEE.

Examining factors that boost intention and loyalty to use Fintech post-COVID-19 lockdown as a new normal behavior.

This study predicts factors affecting the tendency to use financial technology (Fintech) services post-COVID-19 lockdown as a new normal behavior. Fintech services have boosted the number of users during the COVID-19 lockdown. However, to maintain the loyal behavior of consumers after usage, firms need to predict key reasons to enhance their intention to use the service and maintain current consumers in the long term. This study offers a model to assess the components of the perceived usefulness toward Fintech. Data were collected via Mechanical Turk (MTurk), and structural equation modeling was used to predict the factors that influence the intention and loyalty to use Fintech post-COVID-19 lockdown. The findings reveal that the COVID-19 lockdown, trust, data security and privacy, and especially staff services are factors that enhance the intention to use through perceived usefulness. In return, it builds consumers' loyalty toward Fintech services and is considered a new normal behavior. This research sheds light on how Fintech firms develop their capabilities and increase their competitive advantages. Both theoretical and practical implications are also discussed.