Date on Master's Thesis/Doctoral Dissertation

8-2021

Document Type

Doctoral Dissertation

Degree Name

Ph. D.

Department

Electrical and Computer Engineering

Degree Program

Electrical Engineering, PhD

Committee Chair

Farag, Aly

Committee Co-Chair (if applicable)

Ali, Asem

Committee Member

Tretter, Thomas

Committee Member

Foreman, Chris

Committee Member

Li, Hongxiang

Committee Member

Yampolskiy, Roman

Committee Member

Hindy,Nicholas

Author's Keywords

Student engagement; behavioral engagement; emotional engagement

Abstract

The ability to measure students’ engagement in an educational setting may improve student retention and academic success, revealing which students are disinterested, or which segments of a lesson are causing difficulties. This ability will facilitate timely intervention in both the learning and the teaching process in a variety of classroom settings. In this dissertation, an automatic students engagement measure is proposed through investigating three main engagement components of the engagement: the behavioural engagement, the emotional engagement and the cognitive engagement. The main goal of the proposed technology is to provide the instructors with a tool that could help them estimating both the average class engagement level and the individuals engagement levels while they give the lecture in real-time. Such system could help the instructors to take actions to improve students' engagement. Also, it can be used by the instructor to tailor the presentation of material in class, identify course material that engages and disengages with students, and identify students who are engaged or disengaged and at risk of failure. A biometric sensor network (BSN) is designed to capture data consist of individuals facial capture cameras, wall-mounted cameras and high performance computing machine to capture students head pose, eye gaze, body pose, body movements, and facial expressions. These low level features will be used to train a machine-learning model to estimate the behavioural and emotional engagements in either e-learning or in-class environment. A set of experiments is conducted to compare the proposed technology with the state-of-the-art frameworks in terms of performance. The proposed framework shows better accuracy in estimating both behavioral and emotional engagement. Also, it offers superior flexibility to work in any educational environment. Further, this approach allows quantitative comparison of teaching methods, such as lecture, flipped classrooms, classroom response systems, etc. such that an objective metric can be used for teaching evaluation with immediate closed-loop feedback to the instructor.

Download

Share

COinS