izpis_h1_title_alt

Hidden Markov model-based smart annotation for benchmark cyclic activity recognition database using wearables
ID Martindale, Christine F. (Author), ID Šprager, Sebastijan (Author), ID Eskofier, Björn M. (Author)

.pdfPDF - Presentation file, Download (1,80 MB)
MD5: 5060A675F2B14102F73DC144A5FB802E
URLURL - Source URL, Visit https://www.mdpi.com/1424-8220/19/8/1820 This link opens in a new window

Abstract
Activity monitoring using wearables is becoming ubiquitous, although accurate cycle level analysis, such as step-counting and gait analysis, are limited by a lack of realistic and labeled datasets. The effort required to obtain and annotate such datasets is massive, therefore we propose a smart annotation pipeline which reduces the number of events needing manual adjustment to 14%. For scenarios dominated by walking, this annotation effort is as low as 8%. The pipeline consists of three smart annotation approaches, namely edge detection of the pressure data, local cyclicity estimation, and iteratively trained hierarchical hidden Markov models. Using this pipeline, we have collected and labeled a dataset with over 150,000 labeled cycles, each with 2 phases, from 80 subjects, which we have made publicly available. The dataset consists of 12 different task-driven activities, 10 of which are cyclic. These activities include not only straight and steady-state motions, but also transitions, different ranges of bouts, and changing directions. Each participant wore 5 synchronized inertial measurement units (IMUs) on the wrists, shoes, and in a pocket, as well as pressure insoles and video. We believe that this dataset and smart annotation pipeline are a good basis for creating a benchmark dataset for validation of other semi- and unsupervised algorithms.

Language:English
Keywords:activity recognition, benchmark database, gait analysis, inertial measurement unit, gait phases, cyclic activities, home monitoring, smart annotation, semi-supervised learning
Work type:Article
Typology:1.01 - Original Scientific Article
Organization:FRI - Faculty of Computer and Information Science
Publication status:Published
Publication version:Version of Record
Year:2019
Number of pages:21 str.
Numbering:Vol. 19, iss. 8, art. 1820
PID:20.500.12556/RUL-132338 This link opens in a new window
UDC:004.5
ISSN on article:1424-8220
DOI:10.3390/s19081820 This link opens in a new window
COBISS.SI-ID:31415043 This link opens in a new window
Publication date in RUL:22.10.2021
Views:813
Downloads:139
Metadata:XML RDF-CHPDL DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Record is a part of a journal

Title:Sensors
Shortened title:Sensors
Publisher:MDPI
ISSN:1424-8220
COBISS.SI-ID:10176278 This link opens in a new window

Licences

License:CC BY 4.0, Creative Commons Attribution 4.0 International
Link:http://creativecommons.org/licenses/by/4.0/
Description:This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
Licensing start date:16.04.2019

Secondary language

Language:Slovenian
Keywords:prepoznavanje, podatkovne baze

Projects

Funder:Other - Other funder or multiple funders
Funding programme:German Research Foundation (DFG), Heisenberg professorship program
Project number:ES 434/8-1

Funder:EC - European Commission
Funding programme:EIT health innovation projects programme
Acronym:HOOP 2.0

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back