No Cover Image

Conference Paper/Proceeding/Abstract 663 views

Recognition of unscripted kitchen activities and eating behaviour for health monitoring

S. Whitehouse, K. Yordanova, A. Paiement, M. Mirmehdi, Adeline Paiement

Proceedings of the 2nd IET International Conference on Technologies for Active and Assisted Living, Pages: 1 - 6

Swansea University Author: Adeline Paiement

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.1049/ic.2016.0050

Abstract

Nutrition related health conditions such as diabetes and obesity can seriously impact quality of life for those who are affected by them. A system able to monitor kitchen activities and patients’ eating behaviours could provide clinicians with important information helping them to improve patients’...

Full description

Published in: Proceedings of the 2nd IET International Conference on Technologies for Active and Assisted Living
ISBN: 978-1-78561-393-7
Published: London 2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016) 2016
Online Access: http://ieeexplore.ieee.org/document/7801334/
URI: https://cronfa.swan.ac.uk/Record/cronfa31411
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2016-12-09T14:59:18Z
last_indexed 2018-02-09T05:18:17Z
id cronfa31411
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2017-08-07T10:38:51.3727064</datestamp><bib-version>v2</bib-version><id>31411</id><entry>2016-12-09</entry><title>Recognition of unscripted kitchen activities and eating behaviour for health monitoring</title><swanseaauthors><author><sid>f50adf4186d930e3a2a0f9a6d643cf53</sid><firstname>Adeline</firstname><surname>Paiement</surname><name>Adeline Paiement</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2016-12-09</date><deptcode>FGHSS</deptcode><abstract>Nutrition related health conditions such as diabetes and obesity can seriously impact quality of life for those who are affected by them. A system able to monitor kitchen activities and patients&#x2019; eating behaviours could provide clinicians with important information helping them to improve patients&#x2019; treatments. We propose a symbolic model able to describe unscripted kitchen activities and eating habits of people in home settings. This model consists of an ontology which describes the problem domain, and a Computational State Space Model (CSSM) which is able to reason in a probabilistic manner about a subject&#x2019;s actions, goals, and causes of any problems during task execution. To validate our model we recorded 15 unscripted kitchen activities involving 9 subjects, with the video data being annotated according to the proposed ontology schemata. We then evaluated the model&#x2019;s ability to recognise activities and potential goals from action sequences by simulating noisy observations from the annotations. The results showed that our model is able to recognise kitchen activities with an average accuracy of 80% when using specialised models, and with an average accuracy of 40% when using the general model.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings of the 2nd IET International Conference on Technologies for Active and Assisted Living</journal><paginationStart>1</paginationStart><paginationEnd>6</paginationEnd><publisher>2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016)</publisher><placeOfPublication>London</placeOfPublication><isbnElectronic>978-1-78561-393-7</isbnElectronic><keywords/><publishedDay>24</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2016</publishedYear><publishedDate>2016-10-24</publishedDate><doi>10.1049/ic.2016.0050</doi><url>http://ieeexplore.ieee.org/document/7801334/</url><notes/><college>COLLEGE NANME</college><department>Humanities and Social Sciences - Faculty</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>FGHSS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2017-08-07T10:38:51.3727064</lastEdited><Created>2016-12-09T12:12:34.1618048</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>S.</firstname><surname>Whitehouse</surname><order>1</order></author><author><firstname>K.</firstname><surname>Yordanova</surname><order>2</order></author><author><firstname>A.</firstname><surname>Paiement</surname><order>3</order></author><author><firstname>M.</firstname><surname>Mirmehdi</surname><order>4</order></author><author><firstname>Adeline</firstname><surname>Paiement</surname><order>5</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2017-08-07T10:38:51.3727064 v2 31411 2016-12-09 Recognition of unscripted kitchen activities and eating behaviour for health monitoring f50adf4186d930e3a2a0f9a6d643cf53 Adeline Paiement Adeline Paiement true false 2016-12-09 FGHSS Nutrition related health conditions such as diabetes and obesity can seriously impact quality of life for those who are affected by them. A system able to monitor kitchen activities and patients’ eating behaviours could provide clinicians with important information helping them to improve patients’ treatments. We propose a symbolic model able to describe unscripted kitchen activities and eating habits of people in home settings. This model consists of an ontology which describes the problem domain, and a Computational State Space Model (CSSM) which is able to reason in a probabilistic manner about a subject’s actions, goals, and causes of any problems during task execution. To validate our model we recorded 15 unscripted kitchen activities involving 9 subjects, with the video data being annotated according to the proposed ontology schemata. We then evaluated the model’s ability to recognise activities and potential goals from action sequences by simulating noisy observations from the annotations. The results showed that our model is able to recognise kitchen activities with an average accuracy of 80% when using specialised models, and with an average accuracy of 40% when using the general model. Conference Paper/Proceeding/Abstract Proceedings of the 2nd IET International Conference on Technologies for Active and Assisted Living 1 6 2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016) London 978-1-78561-393-7 24 10 2016 2016-10-24 10.1049/ic.2016.0050 http://ieeexplore.ieee.org/document/7801334/ COLLEGE NANME Humanities and Social Sciences - Faculty COLLEGE CODE FGHSS Swansea University 2017-08-07T10:38:51.3727064 2016-12-09T12:12:34.1618048 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science S. Whitehouse 1 K. Yordanova 2 A. Paiement 3 M. Mirmehdi 4 Adeline Paiement 5
title Recognition of unscripted kitchen activities and eating behaviour for health monitoring
spellingShingle Recognition of unscripted kitchen activities and eating behaviour for health monitoring
Adeline Paiement
title_short Recognition of unscripted kitchen activities and eating behaviour for health monitoring
title_full Recognition of unscripted kitchen activities and eating behaviour for health monitoring
title_fullStr Recognition of unscripted kitchen activities and eating behaviour for health monitoring
title_full_unstemmed Recognition of unscripted kitchen activities and eating behaviour for health monitoring
title_sort Recognition of unscripted kitchen activities and eating behaviour for health monitoring
author_id_str_mv f50adf4186d930e3a2a0f9a6d643cf53
author_id_fullname_str_mv f50adf4186d930e3a2a0f9a6d643cf53_***_Adeline Paiement
author Adeline Paiement
author2 S. Whitehouse
K. Yordanova
A. Paiement
M. Mirmehdi
Adeline Paiement
format Conference Paper/Proceeding/Abstract
container_title Proceedings of the 2nd IET International Conference on Technologies for Active and Assisted Living
container_start_page 1
publishDate 2016
institution Swansea University
isbn 978-1-78561-393-7
doi_str_mv 10.1049/ic.2016.0050
publisher 2nd IET International Conference on Technologies for Active and Assisted Living (TechAAL 2016)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://ieeexplore.ieee.org/document/7801334/
document_store_str 0
active_str 0
description Nutrition related health conditions such as diabetes and obesity can seriously impact quality of life for those who are affected by them. A system able to monitor kitchen activities and patients’ eating behaviours could provide clinicians with important information helping them to improve patients’ treatments. We propose a symbolic model able to describe unscripted kitchen activities and eating habits of people in home settings. This model consists of an ontology which describes the problem domain, and a Computational State Space Model (CSSM) which is able to reason in a probabilistic manner about a subject’s actions, goals, and causes of any problems during task execution. To validate our model we recorded 15 unscripted kitchen activities involving 9 subjects, with the video data being annotated according to the proposed ontology schemata. We then evaluated the model’s ability to recognise activities and potential goals from action sequences by simulating noisy observations from the annotations. The results showed that our model is able to recognise kitchen activities with an average accuracy of 80% when using specialised models, and with an average accuracy of 40% when using the general model.
published_date 2016-10-24T03:38:22Z
_version_ 1763751706034700288
score 11.012678

Similar Items