A Computer-Vision Based Application for Student Behavior Monitoring in Classroom

Abstract

Automated learning analytics is becoming an essential topic in the educational area, which needs effective systems to monitor the learning process and provides feedback to the teacher. Recent advances in visual sensors and computer vision methods enable automated monitoring of behavior and affective states of learners at different levels, from university to pre-school. The objective of this research was to build an automatic system that allowed the faculties to capture and make a summary of student behaviors in the classroom as a part of data acquisition for the decision making process. The system records the entire session and identifies when the students pay attention in the classroom, and then reports to the facilities. Our design and experiments show that our system is more flexible and more accurate than previously published work.

A critical evaluation, challenges, and future perspectives of using artificial intelligence and emerging technologies in smart classrooms

“…Recently, automated methods for the behaviour analysis of the students and their engagement estimation are widely utilized in a classroom. Ngoc Anh et al ( 2019 ), presented a system to monitor the behaviour of students in the classroom. Similarly, Thomas and Jayagopi ( 2017 ), used a machine learning algorithm to analyze the students’ engagement in a classroom by analyzing students’ head position, eye gaze direction and facial expressions.…”

Multimodal Fast–Slow Neural Network for learning engagement evaluation

“…Learning motivation does not directly affect learning achievement but affects students' engagement, which has a direct impact on their learning achievement. However, the observation method is limited when there are too many students since the teacher does not have enough energy (Ngoc Anh et al , 2019), while the self-reporting method lacks timeliness (Thomas and Jayagopi, 2017). Learning is a dynamic process, and to achieve real-time tracking or estimate student engagement levels, some researchers have adopted on-task or off-risk rates as indicators (Henrie et al , 2015).…”

“…Traditionally, researchers can intuitively judge a student's engagement level through observation or questionnaires (Dunn and Kennedy, 2019; Goldberg et al , 2021; Leon and Garcia-Martinez, 2021). However, the observation method is hard to focus on multiple students at the same time (Ngoc Anh et al , 2019), and the survey investigation (i.e. self-reporting engagement) lacks timeliness (Thomas and Jayagopi, 2017).…”

Design and Implementation of Intelligent Classroom Framework Through Light-Weight Neural Networks Based on Multimodal Sensor Data Fusion Approach

“…To immediately lip-read speakers using CNN and even RNN models by capturing lip zone utilizing VGG and similar network versions tested with 88.2 percent accuracy on datasets developed [26]. An automated student monitoring device can track teacher and student behavior in the classroom leveraging 1800 frames of 6 videos with 10-20 students participants [27], By designing and implementing a gamified framework for a group of 120 students from higher educational sector had resulted in enhancing the student engagement, enticement, and motivation [28] using ANFIS model.…”