Activity recognition invariant to sensor orientation with wearable motion sensors

Simple item page
dc.citation.issueNumber8en_US
dc.citation.volumeNumber17en_US
dc.contributor.authorYurtman, A.en_US
dc.contributor.authorBarshan, B.en_US
dc.date.accessioned2018-04-12T10:59:45Z
dc.date.available2018-04-12T10:59:45Z
dc.date.issued2017en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractMost activity recognition studies that employ wearable sensors assume that the sensors are attached at pre-determined positions and orientations that do not change over time. Since this is not the case in practice, it is of interest to develop wearable systems that operate invariantly to sensor position and orientation. We focus on invariance to sensor orientation and develop two alternative transformations to remove the effect of absolute sensor orientation from the raw sensor data. We test the proposed methodology in activity recognition with four state-of-the-art classifiers using five publicly available datasets containing various types of human activities acquired by different sensor configurations. While the ordinary activity recognition system cannot handle incorrectly oriented sensors, the proposed transformations allow the sensors to be worn at any orientation at a given position on the body, and achieve nearly the same activity recognition performance as the ordinary system for which the sensor units are not rotatable. The proposed techniques can be applied to existing wearable systems without much effort, by simply transforming the time-domain sensor data at the pre-processing stage. © 2017 by the authors. Licensee MDPI, Basel, Switzerland.en_US
dc.description.provenanceMade available in DSpace on 2018-04-12T10:59:45Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 179475 bytes, checksum: ea0bedeb05ac9ccfb983c327e155f0c2 (MD5) Previous issue date: 2017en
dc.identifier.doi10.3390/s17081838en_US
dc.identifier.issn1424-8220
dc.identifier.urihttp://hdl.handle.net/11693/37003
dc.language.isoEnglishen_US
dc.publisherMDPI AGen_US
dc.relation.isversionofhttp://dx.doi.org/10.3390/s17081838en_US
dc.source.titleSensors (Switzerland)en_US
dc.subjectAccelerometeren_US
dc.subjectArtificial neural networksen_US
dc.subjectBayesian decision makingen_US
dc.subjectHuman activity recognitionen_US
dc.subjectInertial sensorsen_US
dc.subjectK-nearest-neighbor classifieren_US
dc.subjectMachine learningen_US
dc.subjectMagnetometeren_US
dc.subjectMotion sensorsen_US
dc.subjectOrientation-invariant sensingen_US
dc.subjectSensor orientationen_US
dc.subjectSingular value decompositionen_US
dc.subjectSupport vector machinesen_US
dc.subjectWearable sensingen_US
dc.subjectAccelerometersen_US
dc.subjectBayesian networksen_US
dc.subjectClassification (of information)en_US
dc.subjectDecision makingen_US
dc.subjectGyroscopesen_US
dc.subjectLearning systemsen_US
dc.subjectMagnetometersen_US
dc.subjectMetadataen_US
dc.subjectNearest neighbor searchen_US
dc.subjectNeural networksen_US
dc.subjectPattern recognitionen_US
dc.subjectSingular value decompositionen_US
dc.subjectSupport vector machinesen_US
dc.subjectTime domain analysisen_US
dc.subjectWearable technologyen_US
dc.subjectBayesian decision makingsen_US
dc.subjectHuman activity recognitionen_US
dc.subjectInertial sensoren_US
dc.subjectK-nearest neighbor classifieren_US
dc.subjectSensor orientationen_US
dc.subjectWearable sensingen_US
dc.subjectWearable sensorsen_US
dc.titleActivity recognition invariant to sensor orientation with wearable motion sensorsen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Activity Recognition Invariant to Sensor Orientation with Wearable Motion Sensors.pdf
Size:
4.8 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Scholarly Publications - Electrical and Electronics Engineering