Abstract

The switch to online learning due to the COVID-19 revealed flaws in the existing learning methods, especially with online proctored assessments. Hence, online proctoring using computers was needed for a fair evaluation. Many studies develop cheating detection systems using several approaches. However, to the best of our knowledge, none of the existing studies investigated the impact of their system components in detecting cheating behaviors. Combining system components, even if they do not significantly improve the system performance in cheating detection, can cause an overload on the system. Therefore, our goal is to investigate the system components’ impact, individually and combined, on cheating cue detection system accuracy. Moreover, we want to observe how system components affect each other when used to detect cheating cues. To be able to achieve these goals, we design a component-based cheating detection system. Our system includes three main components: (1) video. (2) audio. (3) system monitoring. By combining the continuous estimation of the components and enforcing a temporal window, we design a cheating cue detection system. This system can detect and classify cheating behavior signals at any moment during the exam. For system evaluation, we collect multimedia: video, audio, and system data that is automatically annotated from 25 subjects performing different types of cheating behaviors during a mock online assessment. Our study successfully assesses the impact of system components on detecting cheating signals and their relationships with each other. This is done by developing a component-based analysis that includes video, audio, and system features.

School

School of Sciences and Engineering

Department

Computer Science & Engineering Department

Degree Name

MS in Computer Science

Graduation Date

Spring 4-4-2022

Submission Date

5-23-2022

First Advisor

Nourhan Sakr

Second Advisor

Sherif Aly

Committee Member 1

Motaaz El Saban

Committee Member 2

Hossam Sharara

Extent

45p.

Document Type

Master's Thesis

Institutional Review Board (IRB) Approval

Approval has been obtained for this item

Available for download on Wednesday, May 22, 2024

Share

COinS