Position invariance for wearables: interchangeability and single-unit usage via machine learning

Simple item page
buir.contributor.authorYurtman, Aras
buir.contributor.authorBarshan, Billur
buir.contributor.orcidYurtman, Aras|0000-0001-6213-5427
buir.contributor.orcidBarshan, Billur|0000-0001-6783-6572
dc.citation.epage8342en_US
dc.citation.issueNumber10en_US
dc.citation.spage8328en_US
dc.citation.volumeNumber8en_US
dc.contributor.authorYurtman, Aras
dc.contributor.authorBarshan, Billur
dc.contributor.authorRedif, S.
dc.date.accessioned2021-03-08T08:05:11Z
dc.date.available2021-03-08T08:05:11Z
dc.date.issued2021
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractWe propose a new methodology to attain invariance to the positioning of body-worn motion-sensor units for recognizing everyday and sports activities. We first consider random interchangeability of the sensor units so that the user does not need to distinguish between them before wearing. To this end, we propose to use the compact singular value decomposition (SVD) that significantly reduces the accuracy degradation caused by random interchanging of the units. Secondly, we employ three variants of a generalized classifier that requires wearing only a single sensor unit on any one of the body parts to classify the activities. We combine both approaches with our previously developed methods to achieve invariance to both position and orientation, which ultimately allows the user significant flexibility in sensor-unit placement (position and orientation). We assess the performance of our proposed approach on a publicly available activity dataset recorded by body-worn motion-sensor units. Experimental results suggest that there is a tolerable reduction in accuracy, which is justified by the significant flexibility and convenience offered to users when placing the units.en_US
dc.identifier.doi10.1109/JIOT.2020.3044754en_US
dc.identifier.issn2327-4662
dc.identifier.urihttp://hdl.handle.net/11693/75862
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://dx.doi.org/10.1109/JIOT.2020.3044754en_US
dc.source.titleIEEE Internet of Things Journalen_US
dc.subjectActivity monitoring and classificationen_US
dc.subjectWearable sensingen_US
dc.subjectPosition invarianceen_US
dc.subjectOrientation invarianceen_US
dc.subjectInternet of Things (IoT)en_US
dc.subjectMotion sensorsen_US
dc.subjectAccelerometeren_US
dc.subjectGyroscopeen_US
dc.subjectInertial sensorsen_US
dc.subjectMagnetometeren_US
dc.subjectPattern recognitionen_US
dc.subjectMachine learning classifiersen_US
dc.titlePosition invariance for wearables: interchangeability and single-unit usage via machine learningen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Position_invariance_for_wearables_interchangeability_and_single-unit_usage_via_machine_learning.pdf
Size:
4.63 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Electrical and Electronics Engineering