Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A new approach based on temporal sub-windows for online sensor-based activity recognition
Department of Computer Science, University of Jaén, Jaén, Spain.
Department of Computer Science, University of Jaén, Jaén, Spain.
Luleå tekniska universitet, Institutionen för system- och rymdteknik, Datavetenskap.ORCID-id: 0000-0003-3191-8335
School of Computing and Mathematics, Ulster University, Coleraine, UK.
2018 (engelsk)Inngår i: Journal of Ambient Intelligence and Humanized Computing, ISSN 1868-5137, E-ISSN 1868-5145Artikkel i tidsskrift (Fagfellevurdert) Epub ahead of print
Abstract [en]

Usually, approaches driven by data proposed in literature for sensor-based activity recognition use the begin label and the end label of each activity in the dataset, fixing a temporal window with sensor data events to identify the activity carried out in this window. This type of approach cannot be carried out in real time because it is not possible to predict the start time of an activity, i.e., the class of the future activity that an inhabitant will perform, neither when he/she will begin to carry out this activity. However, an activity can be marked as finished in real time only with the previous observations. Therefore, there is a need of online activity recognition approaches that classify activities using only the end label of the activity. In this paper, we propose and evaluate a new approach for online activity recognition with three temporal sub-windows that uses only the end label of the activity. The advantage of our approach is that the temporal sub-windows keep a partial order in the sensor data stream from the end time of the activity in a short-term, medium-term, long-term. The experiments conducted to evaluate our approach suggest the importance of the use of temporal sub-windows versus a single temporal window in terms of accuracy, using only the end time of the activity. The use of temporal sub-windows has improved the accuracy in the 98.95% of experiments carried out.

sted, utgiver, år, opplag, sider
Springer, 2018.
Emneord [en]
Activity recognition, Data sensor stream, Fuzzy linguistic modelling, Sensor data stream processing, Smart environments
HSV kategori
Forskningsprogram
Distribuerade datorsystem
Identifikatorer
URN: urn:nbn:se:ltu:diva-67907DOI: 10.1007/s12652-018-0746-yOAI: oai:DiVA.org:ltu-67907DiVA, id: diva2:1189482
Tilgjengelig fra: 2018-03-11 Laget: 2018-03-11 Sist oppdatert: 2018-03-11

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekst

Søk i DiVA

Av forfatter/redaktør
Hallberg, Josef
Av organisasjonen
I samme tidsskrift
Journal of Ambient Intelligence and Humanized Computing

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 1723 treff
RefereraExporteraLink to record
Permanent link

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