A scalable framework for smart COVID surveillance in the workplace using Deep Neural Networks and cloud computing.

Area of Science:

• Computer Science
• Artificial Intelligence
• Public Health

Background:

• The COVID-19 pandemic necessitates intelligent systems for monitoring public health compliance.
• Existing computing infrastructures face challenges in efficiently scheduling diverse machine learning applications for pandemic control.

Purpose of the Study:

• To propose a smart, scalable framework integrating cloud and fog computing for machine learning applications in pandemic control.
• To develop a time-sensitive infrastructure for smart office surveillance to detect COVID-19 guideline violations.

Main Methods:

• Utilized deep neural networks for image analysis.
• Implemented a hybrid cloud and fog computing architecture.
• Developed a system for detecting mask-wearing and social distancing (6 feet).

Main Results:

• The proposed framework demonstrated superior performance compared to traditional cloud environments.
• Achieved lower latency and faster response times in detecting COVID-19 violations.
• Successfully tested for two independent surveillance applications.

Conclusions:

• The framework effectively bridges the gap between machine learning applications and computing infrastructure for pandemic management.
• Offers a scalable and efficient solution for rapid development and deployment of pandemic-related applications.
• Provides a robust system for workplace monitoring to ensure compliance with public health guidelines.