Publikationer från Malmö universitet
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A weakly-supervised deep domain adaptation method for multi-modal sensor data
Malmö universitet, Internet of Things and People (IOTAP). Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT). Malmo Univ, Dept Comp Sci, Internet Things & People Res Ctr, S-20506 Malmo, Sweden..
2021 (Engelska)Ingår i: 2021 IEEE GLOBAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INTERNET OF THINGS (GCAIOT), IEEE , 2021, s. 45-50Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Nearly every real-world deployment of machine learning models suffers from some form of shift in data distributions in relation to the data encountered in production. This aspect is particularly pronounced when dealing with streaming data or in dynamic settings (e.g. changes in data sources, behaviour and the environment). As a result, the performance of the models degrades during deployment. In order to account for these contextual changes, domain adaptation techniques have been designed for scenarios where the aim is to learn a model from a source data distribution, which can perform well on a different, but related target data distribution. In this paper we introduce a variational autoencoder-based multi-modal approach for the task of domain adaptation, that can be trained on a large amount of labelled data from the source domain, coupled with a comparably small amount of labelled data from the target domain. We demonstrate our approach in the context of human activity recognition using various IoT sensing modalities and report superior results when benchmarking against the effective mSDA method for domain adaptation.

Ort, förlag, år, upplaga, sidor
IEEE , 2021. s. 45-50
Nyckelord [en]
Domain adaptation, Neural Networks, Internet of Things, Human Activity Recognition
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
URN: urn:nbn:se:mau:diva-51709DOI: 10.1109/GCAIoT53516.2021.9693050ISI: 000790983800008Scopus ID: 2-s2.0-85126734760ISBN: 978-1-6654-3841-4 (tryckt)OAI: oai:DiVA.org:mau-51709DiVA, id: diva2:1661930
Konferens
IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT), DEC 12-16, 2021, Dubai, U ARAB EMIRATES
Tillgänglig från: 2022-05-30 Skapad: 2022-05-30 Senast uppdaterad: 2024-02-05Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Mihailescu, Radu-Casian

Sök vidare i DiVA

Av författaren/redaktören
Mihailescu, Radu-Casian
Av organisationen
Internet of Things and People (IOTAP)Institutionen för datavetenskap och medieteknik (DVMT)
Data- och informationsvetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 73 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf