Show simple item record

dc.contributor.authorTangrand, Kristoffer
dc.contributor.authorBremdal, Bernt Arild
dc.date.accessioned2021-05-17T19:52:31Z
dc.date.available2021-05-17T19:52:31Z
dc.date.issued2020-02-06
dc.description.abstractThis paper presents results from ongoing research with a goal to use a combination of time series from non-intrusive ambient sensors and deep recurrent neural networks to predict room usage at a university campus. Training data was created by collecting measurements from ambient sensors measuring room CO2, humidity, temperature, light, motion and sound, while the ground-truth counts was created manually by human observers. Results include analyses of relationships between different sensor data sequences and recommendations for a prototype predictive model using deep recurrent neural networks.en_US
dc.identifier.citationTangrand, Bremdal. Using Deep Learning Methods to Monitor Non-Observable States in a Building. Proceedings of the Northern Lights Deep Learning Workshop. 2020en_US
dc.identifier.cristinIDFRIDAID 1881096
dc.identifier.doi10.7557/18.5159
dc.identifier.issn2703-6928
dc.identifier.urihttps://hdl.handle.net/10037/21194
dc.language.isoengen_US
dc.publisherSeptentrioen_US
dc.relation.ispartofTangrand, K.M. (2023). Some new Contributions to Neural Networks and Wavelets with Applications. (Doctoral thesis). <a href=https://hdl.handle.net/10037/28699>https://hdl.handle.net/10037/28699</a>.
dc.relation.journalProceedings of the Northern Lights Deep Learning Workshop
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2020 The Author(s)en_US
dc.subjectVDP::Technology: 500::Information and communication technology: 550en_US
dc.subjectVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550en_US
dc.subjectVDP::Mathematics and natural science: 400::Information and communication science: 420::Knowledge based systems: 425en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Kunnskapsbaserte systemer: 425en_US
dc.titleUsing Deep Learning Methods to Monitor Non-Observable States in a Buildingen_US
dc.type.versionpublishedVersionen_US
dc.typeConference objecten_US
dc.typeKonferansebidragen_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record