Assessing Eating Behaviour Using Upper Limb Mounted Motion Sensors: A Systematic Review
Wearable motion tracking sensors are now widely used to monitor physical activity, and have recently gained more attention in dietary monitoring research. The aim of this review is to synthesise research to date that utilises upper limb motion tracking sensors, either individually or in combination...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-05-01
|
Series: | Nutrients |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6643/11/5/1168 |
id |
doaj-792860ed6e03412897a2596bc9167b83 |
---|---|
record_format |
Article |
spelling |
doaj-792860ed6e03412897a2596bc9167b832020-11-25T01:36:38ZengMDPI AGNutrients2072-66432019-05-01115116810.3390/nu11051168nu11051168Assessing Eating Behaviour Using Upper Limb Mounted Motion Sensors: A Systematic ReviewHamid Heydarian0Marc Adam1Tracy Burrows2Clare Collins3Megan E. Rollo4School of Electrical Engineering and Computing, Faculty of Engineering and Built Environment, The University of Newcastle, Callaghan, NSW 2308, AustraliaSchool of Electrical Engineering and Computing, Faculty of Engineering and Built Environment, The University of Newcastle, Callaghan, NSW 2308, AustraliaPriority Research Centre for Physical Activity and Nutrition, The University of Newcastle, Callaghan, NSW 2308, AustraliaPriority Research Centre for Physical Activity and Nutrition, The University of Newcastle, Callaghan, NSW 2308, AustraliaPriority Research Centre for Physical Activity and Nutrition, The University of Newcastle, Callaghan, NSW 2308, AustraliaWearable motion tracking sensors are now widely used to monitor physical activity, and have recently gained more attention in dietary monitoring research. The aim of this review is to synthesise research to date that utilises upper limb motion tracking sensors, either individually or in combination with other technologies (e.g., cameras, microphones), to objectively assess eating behaviour. Eleven electronic databases were searched in January 2019, and 653 distinct records were obtained. Including 10 studies found in backward and forward searches, a total of 69 studies met the inclusion criteria, with 28 published since 2017. Fifty studies were conducted exclusively in laboratory settings, 13 exclusively in free-living settings, and three in both settings. The most commonly used motion sensor was an accelerometer (64) worn on the wrist (60) or lower arm (5), while in most studies (45), accelerometers were used in combination with gyroscopes. Twenty-six studies used commercial-grade smartwatches or fitness bands, 11 used professional grade devices, and 32 used standalone sensor chipsets. The most used machine learning approaches were Support Vector Machine (SVM, <i>n</i> = 21), Random Forest (<i>n</i> = 19), Decision Tree (<i>n</i> = 16), Hidden Markov Model (HMM, <i>n</i> = 10) algorithms, and from 2017 Deep Learning (<i>n</i> = 5). While comparisons of the detection models are not valid due to the use of different datasets, the models that consider the sequential context of data across time, such as HMM and Deep Learning, show promising results for eating activity detection. We discuss opportunities for future research and emerging applications in the context of dietary assessment and monitoring.https://www.mdpi.com/2072-6643/11/5/1168eating activity detectionhand-to-mouth movementwrist-mounted motion tracking sensoraccelerometergyroscope |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hamid Heydarian Marc Adam Tracy Burrows Clare Collins Megan E. Rollo |
spellingShingle |
Hamid Heydarian Marc Adam Tracy Burrows Clare Collins Megan E. Rollo Assessing Eating Behaviour Using Upper Limb Mounted Motion Sensors: A Systematic Review Nutrients eating activity detection hand-to-mouth movement wrist-mounted motion tracking sensor accelerometer gyroscope |
author_facet |
Hamid Heydarian Marc Adam Tracy Burrows Clare Collins Megan E. Rollo |
author_sort |
Hamid Heydarian |
title |
Assessing Eating Behaviour Using Upper Limb Mounted Motion Sensors: A Systematic Review |
title_short |
Assessing Eating Behaviour Using Upper Limb Mounted Motion Sensors: A Systematic Review |
title_full |
Assessing Eating Behaviour Using Upper Limb Mounted Motion Sensors: A Systematic Review |
title_fullStr |
Assessing Eating Behaviour Using Upper Limb Mounted Motion Sensors: A Systematic Review |
title_full_unstemmed |
Assessing Eating Behaviour Using Upper Limb Mounted Motion Sensors: A Systematic Review |
title_sort |
assessing eating behaviour using upper limb mounted motion sensors: a systematic review |
publisher |
MDPI AG |
series |
Nutrients |
issn |
2072-6643 |
publishDate |
2019-05-01 |
description |
Wearable motion tracking sensors are now widely used to monitor physical activity, and have recently gained more attention in dietary monitoring research. The aim of this review is to synthesise research to date that utilises upper limb motion tracking sensors, either individually or in combination with other technologies (e.g., cameras, microphones), to objectively assess eating behaviour. Eleven electronic databases were searched in January 2019, and 653 distinct records were obtained. Including 10 studies found in backward and forward searches, a total of 69 studies met the inclusion criteria, with 28 published since 2017. Fifty studies were conducted exclusively in laboratory settings, 13 exclusively in free-living settings, and three in both settings. The most commonly used motion sensor was an accelerometer (64) worn on the wrist (60) or lower arm (5), while in most studies (45), accelerometers were used in combination with gyroscopes. Twenty-six studies used commercial-grade smartwatches or fitness bands, 11 used professional grade devices, and 32 used standalone sensor chipsets. The most used machine learning approaches were Support Vector Machine (SVM, <i>n</i> = 21), Random Forest (<i>n</i> = 19), Decision Tree (<i>n</i> = 16), Hidden Markov Model (HMM, <i>n</i> = 10) algorithms, and from 2017 Deep Learning (<i>n</i> = 5). While comparisons of the detection models are not valid due to the use of different datasets, the models that consider the sequential context of data across time, such as HMM and Deep Learning, show promising results for eating activity detection. We discuss opportunities for future research and emerging applications in the context of dietary assessment and monitoring. |
topic |
eating activity detection hand-to-mouth movement wrist-mounted motion tracking sensor accelerometer gyroscope |
url |
https://www.mdpi.com/2072-6643/11/5/1168 |
work_keys_str_mv |
AT hamidheydarian assessingeatingbehaviourusingupperlimbmountedmotionsensorsasystematicreview AT marcadam assessingeatingbehaviourusingupperlimbmountedmotionsensorsasystematicreview AT tracyburrows assessingeatingbehaviourusingupperlimbmountedmotionsensorsasystematicreview AT clarecollins assessingeatingbehaviourusingupperlimbmountedmotionsensorsasystematicreview AT meganerollo assessingeatingbehaviourusingupperlimbmountedmotionsensorsasystematicreview |
_version_ |
1725061829593399296 |