Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Automatic annotation for human activity recognition in free living using a smartphone
Computer Science Research Institute, Ulster University, Newtownabbey BT370QB, UK.ORCID iD: 0000-0002-1870-0203
Computer Science Research Institute, Ulster University, Newtownabbey BT370QB, UK.
Computer Science Research Institute, Ulster University, Newtownabbey BT370QB, UK.
Computer Science Research Institute, Ulster University, Newtownabbey BT370QB, UK.
Show others and affiliations
2018 (English)In: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 18, no 7, article id 2203Article in journal (Refereed) Published
Abstract [en]

Data annotation is a time-consuming process posing major limitations to the development of Human Activity Recognition (HAR) systems. The availability of a large amount of labeled data is required for supervised Machine Learning (ML) approaches, especially in the case of online and personalized approaches requiring user specific datasets to be labeled. The availability of such datasets has the potential to help address common problems of smartphone-based HAR, such as inter-person variability. In this work, we present (i) an automatic labeling method facilitating the collection of labeled datasets in free-living conditions using the smartphone, and (ii) we investigate the robustness of common supervised classification approaches under instances of noisy data. We evaluated the results with a dataset consisting of 38 days of manually labeled data collected in free living. The comparison between the manually and the automatically labeled ground truth demonstrated that it was possible to obtain labels automatically with an 80–85% average precision rate. Results obtained also show how a supervised approach trained using automatically generated labels achieved an 84% f-score (using Neural Networks and Random Forests); however, results also demonstrated how the presence of label noise could lower the f-score up to 64–74% depending on the classification approach (Nearest Centroid and Multi-Class Support Vector Machine).

Place, publisher, year, edition, pages
MDPI, 2018. Vol. 18, no 7, article id 2203
National Category
Media and Communication Technology
Research subject
Pervasive Mobile Computing
Identifiers
URN: urn:nbn:se:ltu:diva-70137DOI: 10.3390/s18072203PubMedID: 29987218Scopus ID: 2-s2.0-85050029995OAI: oai:DiVA.org:ltu-70137DiVA, id: diva2:1233786
Note

Validerad;2018;Nivå 2;2018-07-19 (inah)

Available from: 2018-07-19 Created: 2018-07-19 Last updated: 2018-08-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records BETA

Synnes, KåreHallberg, Josef

Search in DiVA

By author/editor
Cruciani, FredericoSynnes, KåreHallberg, Josef
By organisation
Computer Science
In the same journal
Sensors
Media and Communication Technology

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 59 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf