DeepClassRooms: a deep learning based digital twin framework for on-campus class rooms

Area of Science:

• Educational Technology
• Computer Science
• Artificial Intelligence

Background:

• Traditional classroom monitoring methods are insufficient for improving educational standards.
• Smart classrooms enhance faculty efficiency but require further analysis of student outcomes and content delivery.
• Digital twins offer a novel approach to improving teaching and learning quality in physical classrooms.

Purpose of the Study:

• To propose DeepClass-Rooms, a cost-effective digital twin framework for monitoring attendance and course content.
• To enhance educational quality in public sector schools in Punjab, Pakistan.
• To integrate on-campus and online class monitoring.

Main Methods:

• Development of a digital twin framework named DeepClass-Rooms.
• Utilizing RFID readers and high-edge computing devices at the Fog layer for data acquisition.
• Employing Convolutional Neural Networks (CNN) for attendance monitoring and content matching.

Main Results:

• DeepClass-Rooms provides a cost-effective solution for classroom monitoring.
• The framework enables efficient tracking of attendance and course content delivery.
• CNN integration facilitates accurate monitoring for both on-campus and online learning environments.

Conclusions:

• Digital twins, like DeepClass-Rooms, can significantly improve educational standards through enhanced monitoring.
• The proposed framework offers a practical and scalable solution for public sector schools.
• DeepClass-Rooms facilitates better analysis of learning outcomes and teacher performance.