When generalized eating detection machine learning models fail in the field

Shibo Zhang, Rawan Alharbi, Matthew Nicholson, Nabil Alshurafa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

Problematic eating behaviors are a major cause of obesity. To improve our understanding of these eating behaviors, we need to be able to first reliably detect them. In this paper we use a wrist-worn sensor to test a generalized machine learning models' reliability in detecting eating episodes through data processing. We process data from a 6-axis inertial sensor. Since most eating episodes do not occur while moving, we filter out periods of physical activity, and then use an advanced motif-based time-point fusion technique to detect feeding gestures. We also cluster each of the false alarms into four categories in an effort to identify the main behaviors that confound feeding gesture detection. We tested our system on eight participants performing various activities in the wild while wearing a sensing suite: a neck- and a wrist-worn sensor, along with a wearable video camera continuously recording to capture ground truth. Trained annotators further validated the algorithms by identifying feeding gestures, and categorized the false alarms. All eating episodes were detected; however, many false alarms were also detected, yielding a 61% average F-measure in detecting feeding gestures. This result shows clear challenges in characterizing eating episodes by using a single inertial-based wrist-worn sensor.

Original languageEnglish (US)
Title of host publicationUbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers
PublisherAssociation for Computing Machinery, Inc
Pages613-622
Number of pages10
ISBN (Electronic)9781450351904
DOIs
StatePublished - Sep 11 2017
Event2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and ACM International Symposium on Wearable Computers, UbiComp/ISWC 2017 - Maui, United States
Duration: Sep 11 2017Sep 15 2017

Publication series

NameUbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers

Other

Other2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and ACM International Symposium on Wearable Computers, UbiComp/ISWC 2017
CountryUnited States
CityMaui
Period9/11/179/15/17

Keywords

  • Hand-to-mouth gestures
  • Wearables
  • Wrist-worn sensors

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'When generalized eating detection machine learning models fail in the field'. Together they form a unique fingerprint.

Cite this