Internet of Things and Artificial Intelligence Enabled Smart Classroom

Smart classrooms are now a buzzword in the field of education, both at home and abroad. With the advancement of technology, everything is getting automated and faster. Classrooms are not stepping behind either. In this work, a smart classroom is developed with several important features, like the total number of students in the classroom, a geolocation-based individual students’ attendance system, and student attentiveness detection using eye blink rate.The prediction of the number of students is done using Machine Learning-based techniques based on environmental sensor data. The data collection module is designed using CO <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> , temperature, and humidity sensors. A dataset is prepared by collecting real-time data and building a multiclass prediction model based on sensor data to predict the number of students. The individual students’ attendance system is developed using the existing WiFi system around the classroom, where students are connected to the WiFi network from their registered mobile devices. The geographical location of their devices is compared with the classroom location. A noble approach is also proposed to monitor the attentiveness of students by their eye blink rate, which is also monitored on the mobile device available to them. The results are shown to validate the effectiveness of the proposed systems. Finally, all the features are integrated into a graphical user interface.