Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorJusta, Josef
dc.contributor.authorŠmídl, Václav
dc.contributor.authorHamáček, Aleš
dc.date.accessioned2022-07-25T10:00:11Z-
dc.date.available2022-07-25T10:00:11Z-
dc.date.issued2022
dc.identifier.citationJUSTA, J. ŠMÍDL, V. HAMÁČEK, A. Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors. SENSORS, 2022, roč. 22, č. 10, s. 1-16. ISSN: 1424-8220cs
dc.identifier.issn1424-8220
dc.identifier.uri2-s2.0-85130456586
dc.identifier.urihttp://hdl.handle.net/11025/49273
dc.format16 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherMDPIen
dc.relation.ispartofseriesSENSORSen
dc.rights© authorsen
dc.titleDeep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensorsen
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedThe estimation of the speed of human motion from wearable IMU sensors is required in applications such as pedestrian dead reckoning. In this paper, we test deep learning methods for the prediction of the motion speed from raw readings of a low-cost IMU sensor. Each subject was observed using three sensors at the shoe, shin, and thigh. We show that existing general-purpose architectures outperform classical feature-based approaches and propose a novel architecture tailored for this task. The proposed architecture is based on a semi-supervised variational auto-encoder structure with innovated decoder in the form of a dense layer with a sinusoidal activation function. The proposed architecture achieved the lowest average error on the test data. Analysis of sensor placement reveals that the best location for the sensor is the shoe. Significant accuracy gain was observed when all three sensors were available. All data acquired in this experiment and the code of the estimation methods are available for download.en
dc.subject.translatedmotion speed estimationen
dc.subject.translatedinertial measurement uniten
dc.subject.translateddeep learningen
dc.subject.translatedwalking speeden
dc.subject.translatedautoencoder architectureen
dc.identifier.doi10.3390/s22103865
dc.type.statusPeer-revieweden
dc.identifier.document-number802493900001
dc.identifier.obd43936367
dc.project.IDFW01010189/Nástroje virtuální reality pro interaktivní simulátory s pohyblivou plošinoucs
Vyskytuje se v kolekcích:Články / Articles (RICE)
Články / Articles (KET)
OBD

Soubory připojené k záznamu:
Soubor VelikostFormát 
Justa_sensors-22-03865.pdf2,65 MBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/49273

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.

hledání
navigace
  1. DSpace at University of West Bohemia
  2. Publikační činnost / Publications
  3. OBD