Repository logo
 
Publication

Human activity recognition for indoor localization using smartphone inertial sensors

2021-09-21Journal article Open access
Simple item page
dc.contributor.authorMoreira, Dinis
dc.contributor.authorBarandas, Marília
dc.contributor.authorRocha, Tiago
dc.contributor.authorAlves, Pedro
dc.contributor.authorSantos, Ricardo
dc.contributor.authorLeonardo, Ricardo
dc.contributor.authorVieira, Pedro
dc.contributor.authorGamboa, Hugo
dc.date.accessioned2021-10-13T07:57:14Z
dc.date.available2021-10-13T07:57:14Z
dc.date.issued2021-09-21
dc.description.abstractWith the fast increase in the demand for location-based services and the proliferation of smartphones, the topic of indoor localization is attracting great interest. In indoor environments, users' performed activities carry useful semantic information. These activities can then be used by indoor localization systems to confirm users' current relative locations in a building. In this paper, we propose a deep-learning model based on a Convolutional Long Short-Term Memory (ConvLSTM) network to classify human activities within the indoor localization scenario using smartphone inertial sensor data. Results show that the proposed human activity recognition (HAR) model accurately identifies nine types of activities: not moving, walking, running, going up in an elevator, going down in an elevator, walking upstairs, walking downstairs, or going up and down a ramp. Moreover, predicted human activities were integrated within an existing indoor positioning system and evaluated in a multi-story building across several testing routes, with an average positioning error of 2.4 m. The results show that the inclusion of human activity information can reduce the overall localization error of the system and actively contribute to the better identification of floor transitions within a building. The conducted experiments demonstrated promising results and verified the effectiveness of using human activity-related information for indoor localization.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationMOREIRA, Dinis; [et al] – Human activity recognition for indoor localization using smartphone inertial sensors. Sensors. eISSN 1424-8220. Vol. 21, N.º 18 (2021), pp. 1-19pt_PT
dc.identifier.doi10.3390/s21186316pt_PT
dc.identifier.eissn1424-8220
dc.identifier.urihttp://hdl.handle.net/10400.21/13880
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherMDPIpt_PT
dc.relationPOCI-01-0247-FEDER-033479 - European Regional Development Fund (ERDF) from European Union (EU)pt_PT
dc.subjectSmartphonept_PT
dc.subjectInertial sensorspt_PT
dc.subjectDeep learningpt_PT
dc.subjectHuman activity recognitionpt_PT
dc.subjectIndoor locationpt_PT
dc.titleHuman activity recognition for indoor localization using smartphone inertial sensorspt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage19pt_PT
oaire.citation.issue18pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleSensorspt_PT
oaire.citation.volume21pt_PT
person.familyNameMoreira
person.familyNameBarandas
person.familyNameRocha
person.familyNameLeonardo
person.familyNameVieira
person.familyNameGamboa
person.givenNameDinis Benjamim Ferreira
person.givenNameMarília
person.givenNameTiago
person.givenNameRicardo
person.givenNamePedro
person.givenNameHugo
person.identifierWUT6e0IAAAAJ&hl
person.identifierYCNIhnAAAAAJ
person.identifierhttps://scholar.google.pt/citations?hl=pt-PT&user=PI0mUk4AAAAJ
person.identifier.ciencia-id8A1E-D1BE-6B91
person.identifier.ciencia-idDC18-B5F8-1C36
person.identifier.ciencia-id2412-23F0-0DA0
person.identifier.ciencia-id451A-A52C-A01D
person.identifier.ciencia-id071B-9A70-15B8
person.identifier.ciencia-id841F-7D22-F80E
person.identifier.orcid0000-0003-0719-6096
person.identifier.orcid0000-0002-9445-4809
person.identifier.orcid0000-0002-2364-0196
person.identifier.orcid0000-0003-2695-4462
person.identifier.orcid0000-0003-0279-8741
person.identifier.orcid0000-0002-4022-7424
person.identifier.scopus-author-id56436894500
person.identifier.scopus-author-id7004567421
person.identifier.scopus-author-id57200265948
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication1b42897f-a87c-4bde-80d5-c982662b8ddd
relation.isAuthorOfPublicationf88885be-dff2-433d-a26a-4ebf0d81c5ed
relation.isAuthorOfPublication2c54344e-c318-4585-a9aa-32e1daa297e3
relation.isAuthorOfPublicationd36f6bad-74f6-4896-840b-0588906780b5
relation.isAuthorOfPublication51ae3527-d4ea-46f4-b6c9-62c7b77ac728
relation.isAuthorOfPublicationdb7b919d-d2ae-4360-b8b3-15de99a25c44
relation.isAuthorOfPublication.latestForDiscovery51ae3527-d4ea-46f4-b6c9-62c7b77ac728

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Human_PVieira.pdf
Size:
2.32 MB
Format:
Adobe Portable Document Format
Download

Collections

ISEL - Eng. Elect. Tel. Comp. - Artigos