Using IoT to Predict Student Attention Levels in E-Learning Classes: A Review

Abstract

Student attention is of interest to researchers across various academic stages, from elementary classrooms to the most advanced stages of university study. The tools used to assess students’ attention have also developed beyond the traditional methods used by teachers in the classroom, which have been based solely on observing the expressions and movementsof students. During the recent home quarantines related to COVID-19, educational institutions have been pushed to move more rapidly to e-learning, despite this unconventional approach remaining subject to intense debate and polemic, increasing the need to integrate it into the educational process. The resulting learning process is thus widely affected by the development of Artificial Intelligence and Internet of Things techniques, as well as being dependent on the ubiquity of information technology that has become a primary part of modern life. In online only, or even mixed, education, traditional methods of determining the extent of student attention do not work. The Internet of Things, communication technologies, smart controllers, and sensors have thus begun to be used, alongside electroencephalogram (EEG) sensors to examine users’ brains and to determine their mental state based on activity signals, along with eye movements and head inclinations as recorded by a laptop camera or similar device. Heartbeat may also be monitored using a small wearable device. In this research, several research studies on the subject of determining student attention are thus reviewed as a way to identify techniques that can be used to enable teachers to ascertain the degree of student attention receivedduring e-learning tofacilitate the emergence of alerts for students and teachers as necessary.