UC-19 Comparison of Active and Passive Attention Based Tasks Using EEG with Convolutional Neural Network

UC-19 Comparison of Active and Passive Attention Based Tasks Using EEG with Convolutional Neural Network

https://ccse.kennesaw.edu/computing-showcase/cday-programs/spring2021program.php

When considering a student's attentiveness while taking online courses, it is known that they tend to lose focus or get distracted at some point during the lecture. It is said that as humans we are supposed to learn in active environments. Watching a lecture from a screen is considered a passive task. Combining that with another factor like being tired decreases attention even more. Conducting active and passive attention-based trials will reveal varying results in different states of attentiveness. This project compares active and passive attention trial results in two states, wide awake and tired. This has been done in order to answer the questions: Do subjects perform better (as in maintain concentration and attentiveness) on active tasks while both tired and awake? And do they perform worse on passive tasks when tired and better when awake? The data analyzed was collected from electroencephalogram (EEG) waves, and then later processed through a 3D Convolutional Neural Network (CNN) to produce results. Three passive attention trials and three active attention trials were performed on seven subjects, while they were wide awake and again when they were tired.Advisors(s): Dr. Ying XieTopic(s): Data/Data AnalyticsIT 4983

https://digitalcommons.kennesaw.edu/cday/spring/undergraduatecapstone/6