dc.creatorNugent, Chris D.
dc.creatorSynnott, Jonathan
dc.creatorGabrielli, Celeste
dc.creatorZhang, Shuai
dc.creatorEspinilla, Macarena
dc.creatorCalzada, Alberto
dc.creatorLundström, Jens
dc.creatorCleland, Ian
dc.creatorSynnes, Kåre
dc.creatorHallberg, Josef
dc.creatorSpinsante, Susanna
dc.creatorOrtiz Barrios, Miguel Angel
dc.date2018-11-20T12:37:15Z
dc.date2018-11-20T12:37:15Z
dc.date2016
dc.date.accessioned2023-10-03T19:56:14Z
dc.date.available2023-10-03T19:56:14Z
dc.identifier978-331948798-4
dc.identifier03029743
dc.identifierhttp://hdl.handle.net/11323/1387
dc.identifier10.1007/978-3-319-48799-1_13
dc.identifierCorporación Universidad de la Costa
dc.identifierREDICUC - Repositorio CUC
dc.identifierhttps://repositorio.cuc.edu.co/
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/9173440
dc.descriptionIt is fully appreciated that progress in the development of data driven approaches to activity recognition are being hampered due to the lack of large scale, high quality, annotated data sets. In an effort to address this the Open Data Initiative (ODI) was conceived as a potential solution for the creation of shared resources for the collection and sharing of open data sets. As part of this process, an analysis was undertaken of datasets collected using a smart environment simulation tool. A noticeable difference was found in the first 1–2 cycles of users generating data. Further analysis demonstrated the effects that this had on the development of activity recognition models with a decrease of performance for both support vector machine and decision tree based classifiers. The outcome of the study has led to the production of a strategy to ensure an initial training phase is considered prior to full scale collection of the data.
dc.formatapplication/pdf
dc.languageeng
dc.rightsAtribución – No comercial – Compartir igual
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.subjectActivity recognition
dc.subjectData driven classification
dc.subjectData validation
dc.subjectOpen data sets
dc.titleImproving the quality of user generated data sets for activity recognition
dc.typeArtículo de revista
dc.typehttp://purl.org/coar/resource_type/c_6501
dc.typeText
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.typehttp://purl.org/redcol/resource_type/ART
dc.typeinfo:eu-repo/semantics/acceptedVersion
dc.typehttp://purl.org/coar/version/c_ab4af688f83e57aa


Este ítem pertenece a la siguiente institución