Repository logo
 
Publication

Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering

2017Journal article Open access
Simple item page
dc.contributor.authorZdravevski, Eftim
dc.contributor.authorLameski, Petre
dc.contributor.authorTrajkovik, Vladimir
dc.contributor.authorKulakov, Andrea
dc.contributor.authorChorbev, Ivan
dc.contributor.authorGoleva, Rossitza
dc.contributor.authorPombo, Nuno
dc.contributor.authorGarcia, Nuno M.
dc.date.accessioned2020-01-14T16:31:39Z
dc.date.available2020-01-14T16:31:39Z
dc.date.issued2017
dc.description.abstractAmbient-assisted living (AAL) is promising to become a supplement of the current care models, providing enhanced living experience to people within context-aware homes and smart environments. Activity recognition based on sensory data in AAL systems is an important task because 1) it can be used for estimation of levels of physical activity, 2) it can lead to detecting changes of daily patterns that may indicate an emerging medical condition, or 3) it can be used for detection of accidents and emergencies. To be accepted, AAL systems must be affordable while providing reliable performance. These two factors hugely depend on optimizing the number of utilized sensors and extracting robust features from them. This paper proposes a generic feature engineering method for selecting robust features from a variety of sensors, which can be used for generating reliable classi cation models. From the originally recorded time series and some newly generated time series [i.e., magnitudes, rst derivatives, delta series, and fast Fourier transformation (FFT)-based series], a variety of time and frequency domain features are extracted. Then, using two-phase feature selection, the number of generated features is greatly reduced. Finally, different classi cation models are trained and evaluated on an independent test set. The proposed method was evaluated on ve publicly available data sets, and on all of them, it yielded better accuracy than when using hand-tailored features. The bene ts of the proposed systematic feature engineering method are quickly discovering good feature sets for any given task than manually nding ones suitable for a particular task, selecting a small feature set that outperforms manually determined features in both execution time and accuracy, and identi cation of relevant sensor types and body locations automatically. Ultimately, the proposed method could reduce the cost of AAL systems by facilitating execution of algorithms on devices with limited resources and by using as few sensors as possible.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1109/ACCESS.2017.2684913pt_PT
dc.identifier.urihttp://hdl.handle.net/10400.6/8267
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.subjectFeature extractionpt_PT
dc.subjectTime series analysispt_PT
dc.subjectAmbient intelligencept_PT
dc.subjectWearable sensorspt_PT
dc.subjectSensor fusionpt_PT
dc.subjectPattern recognitionpt_PT
dc.subjectData miningpt_PT
dc.subjectData preprocessingpt_PT
dc.subjectBody sensor networkspt_PT
dc.titleImproving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineeringpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/5876/UID%2FEEA%2F50008%2F2013/PT
oaire.citation.endPage5280pt_PT
oaire.citation.startPage5262pt_PT
oaire.citation.titleIEEE Accesspt_PT
oaire.citation.volume5pt_PT
oaire.fundingStream5876
person.familyNameZdravevski
person.familyNameLameski
person.familyNameTrajkovik
person.familyNameKulakov
person.familyNameChorbev
person.familyNameGoleva
person.familyNamePombo
person.familyNameGarcia dos Santos
person.givenNameEftim
person.givenNamePetre
person.givenNameVladimir
person.givenNameAndrea
person.givenNameIvan
person.givenNameRossitza
person.givenNameNuno
person.givenNameNuno Manuel
person.identifier.ciencia-id0F16-A18D-96BA
person.identifier.ciencia-idE719-0DEC-9751
person.identifier.orcid0000-0001-7664-0168
person.identifier.orcid0000-0002-5336-1796
person.identifier.orcid0000-0001-8103-8059
person.identifier.orcid0000-0002-7075-0953
person.identifier.orcid0000-0002-9648-4438
person.identifier.orcid0000-0002-6268-0756
person.identifier.orcid0000-0001-7797-8849
person.identifier.orcid0000-0002-3195-3168
person.identifier.ridK-5276-2014
person.identifier.ridP-9024-2014
person.identifier.ridC-2465-2016
person.identifier.scopus-author-id55376768000
person.identifier.scopus-author-id55389546100
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication4bca70b3-f753-4695-8e59-3475c4b3979a
relation.isAuthorOfPublicationc1a2be18-5e14-4687-8766-e617687cad49
relation.isAuthorOfPublication20135236-5d7d-4906-84b7-3c60776f159b
relation.isAuthorOfPublicationd42bb3cd-41db-4739-a1ca-67687cbd1ff0
relation.isAuthorOfPublicationd7d5f36c-af36-44f8-80f0-497098bfa12d
relation.isAuthorOfPublication0513ad97-c65e-4932-b865-10680fd83296
relation.isAuthorOfPublication73519920-9c7f-4fcd-9207-1b8e9a8b1738
relation.isAuthorOfPublication3648e9b2-25ee-4d13-9af2-4addc30dae7c
relation.isAuthorOfPublication.latestForDiscovery20135236-5d7d-4906-84b7-3c60776f159b
relation.isProjectOfPublication6051e784-a228-452a-ad8e-90f4372bc6bf
relation.isProjectOfPublication.latestForDiscovery6051e784-a228-452a-ad8e-90f4372bc6bf

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2017 - Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature Engineering 07883880.pdf
Size:
15.2 MB
Format:
Adobe Portable Document Format
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

FE - DI | Documentos por Auto-Depósito
ICI - IT-UBI | Documentos por Auto-Depósito