Automated classroom monitoring with connected visioning system

Internet of Things (IoT) with the concept of integrating connectivity, sensors, data analysis and decision making in an underlying framework has ease many real world problems. In this work, we study the application of IoT for education purpose. Student's behavior and performance in the class is always the main concern of every educator. The instructors are responsible to ensure the smoothness of the classroom activities alongside with monitoring the students' attendance, attention, and activities like entering or leaving the classroom. Manual observation on these could affect the teaching and learning process and causes the distraction from the main syllabus. With the incorporation of IoT devices and computational algorithms such as computer vision techniques, machine learning and data analysis, it can ease the monitoring task and the analysis of students' performance in the class. In advance, it can perform automated real-time observation on the student's behavior through network and react immediately to critical situation if necessary. Nonetheless, the students' long-term performance can be recorded and the data can be used for continuous assessment in the future. In this work, we propose an IoT framework that focused on three analysis modules: Face recognition, motion analysis, and behaviour understanding to effectively perform classroom monitoring tasks such as taking attendance, identify entering and leaving activities and analyse the students concentration level.