Title:
Automatic eating detection in real-world settings with commodity sensing

dc.contributor.advisor Abowd, Gregory D.
dc.contributor.advisor Essa, Irfan
dc.contributor.author Thomaz, Edison
dc.contributor.committeeMember Mynatt, Elizabeth D.
dc.contributor.committeeMember Starner, Thad
dc.contributor.committeeMember Conroy, David
dc.contributor.committeeMember Choudhury, Tanzeem
dc.contributor.department Interactive Computing
dc.date.accessioned 2016-05-27T13:11:41Z
dc.date.available 2016-05-27T13:11:41Z
dc.date.created 2016-05
dc.date.issued 2016-01-07
dc.date.submitted May 2016
dc.date.updated 2016-05-27T13:11:41Z
dc.description.abstract Motivated by challenges and opportunities in nutritional epidemiology and food journaling, ubiquitous computing researchers have proposed numerous techniques for automated dietary monitoring (ADM) over the years. Although progress has been made, a truly practical system that can automatically recognize what people eat in real-world settings remains elusive. This dissertation addresses the problem of ADM by focusing on practical eating moment detection. Eating detection is a foundational element of ADM since automatically recognizing when a person is eating is required before identifying what and how much is being consumed. Additionally, eating detection can serve as the basis for new types of dietary self-monitoring practices such as semi-automated food journaling. In this thesis, I show that everyday eating moments such as breakfast, lunch, and dinner can be automatically detected in real-world settings by opportunistically leveraging sensors in practical, off-the-shelf wearable devices. I refer to this instrumentation approach as "commodity sensing". The work covered by this thesis encompasses a series of experiments I conducted with a total of 106 participants where I explored a variety of sensing modalities for automatic eating moment detection. The modalities studied include first-person images taken with wearable cameras, ambient sounds, and on-body inertial sensors. I discuss the extent to which first-person images reflecting everyday experiences can be used to identify eating moments using two approaches: human computation, and by employing a combination of state-of-the-art machine learning and computer vision techniques. Furthermore, I also describe privacy challenges that arise with first-person photographs. Next, I present results showing how certain sounds associated with eating can be recognized and used to infer eating activities. Finally, I elaborate on findings from three studies focused on the use of on-body inertial sensors (head and wrists) to recognize eating moments both in a semi-controlled laboratory setting and in real-world conditions. I conclude by relating findings and insights to practical applications, and highlighting opportunities for future work.
dc.description.degree Ph.D.
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/54933
dc.language.iso en_US
dc.publisher Georgia Institute of Technology
dc.subject Dietary self-monitoring
dc.subject Eating detection
dc.subject Food logging
dc.subject Food journaling
dc.subject Automated dietary monitoring
dc.subject Human behavior modeling
dc.title Automatic eating detection in real-world settings with commodity sensing
dc.type Text
dc.type.genre Dissertation
dspace.entity.type Publication
local.contributor.advisor Essa, Irfan
local.contributor.advisor Abowd, Gregory D.
local.contributor.corporatename School of Interactive Computing
local.contributor.corporatename College of Computing
relation.isAdvisorOfPublication 84ae0044-6f5b-4733-8388-4f6427a0f817
relation.isAdvisorOfPublication a9e4f620-85d6-4fb9-8851-8b0c3a0e66b4
relation.isOrgUnitOfPublication aac3f010-e629-4d08-8276-81143eeaf5cc
relation.isOrgUnitOfPublication c8892b3c-8db6-4b7b-a33a-1b67f7db2021
thesis.degree.level Doctoral
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
THOMAZ-DISSERTATION-2016.pdf
Size:
6.98 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
LICENSE.txt
Size:
3.87 KB
Format:
Plain Text
Description: