*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Automated Eating Detection Systems to Investigate Eating Behavior and Mental Well-being
Mehrab Bin Morshed
Ph.D. Student, Computer Science
School of Interactive Computing
Georgia Institute of Technology
Date: Wednesday, February 17, 2021
Time: 7:30 AM - 9:30 AM (EST)
Location (remote via BlueJeans): https://bluejeans.com/2499035930
Committee:
----------------
Dr. Gregory D. Abowd (Co-Advisor), School of Interactive Computing, Georgia Institute of Technology
Dr. Thomas Plötz (Co-Advisor), School of Interactive Computing, Georgia Institute of Technology
Dr. Munmun De Choudhury, School of Interactive Computing, Georgia Institute of Technology
Dr. Andrea G. Parker, School of Interactive Computing, Georgia Institute of Technology
Dr. James M. Rehg, School of Interactive Computing, Georgia Institute of Technology
Dr. Tanzeem Choudhury, Information Science, Cornell Tech
Abstract:
-------------
Eating is one of the most commonly performed activities by humans. The motivation of eating is beyond survival. Eating serves as means for socializing, exploring cultures, etc. Computing researchers have developed a variety of eating detection technologies that can leverage passive sensors available on smart devices to automatically infer when an individual is eating. However, despite their significance in eating literature, important contextual information such as meal company, type of food, location of meals, the motivation of eating episodes, etc, are difficult to detect through passive means. My work focuses on addressing these challenges by developing a real-time meal detection system that can trigger questions in the form of EMAs to gather important contextual information. EMAs are a widely adopted tool, used across a variety of disciplines, that can gather in-situ information about individual experiences. By triggering EMAs to gather eating-related information, in my work, I show the relationship between a variety of eating contexts and mental well-being for college students.
Due to COVID-19, a significant amount of the workforce is working from home. As a result, the place of relaxation, home, has become the new workplace, blurring boundaries between workplace and home. Such a shift in the workplace has caused routine disruption and change in eating behavior, especially for people living with their families. In my previous studies, I found that deviation from regularity in meal-timing is significantly associated with one’s mood. As a follow-up of this observation, in my first proposed work, I will address the causal relationship between the deviation of meal-timing and mood for people working from home and living with their family. Besides, in my past work, I found that a wrist-mounted eating detection system is not a good proxy for detecting short eating episodes such as snacking. For addressing this limitation, I will propose a novel snacking detection system by using passive sensing technologies.
