Recognizing the activity performed by users is importantin many application domains, from e-health to home automation. Thispaper explores the use of a fine-grained indoor localization system, basedon ultra-wideband, for activity recognition. The user is supposed to weara number of active tags. The position of active tags is first determinedwith respect to the space where the user is moving, then some position-independent metrics are estimated and given as input to a previouslytrained system. Experimental results show that accuracy values as highas∼95% can be obtained when using a personalized model.
Using an Indoor Localization System for Activity Recognition
CORCUERA BÁRCENA, JOSÉ LUIS;Alessio Vecchio
2020-01-01
Abstract
Recognizing the activity performed by users is importantin many application domains, from e-health to home automation. Thispaper explores the use of a fine-grained indoor localization system, basedon ultra-wideband, for activity recognition. The user is supposed to weara number of active tags. The position of active tags is first determinedwith respect to the space where the user is moving, then some position-independent metrics are estimated and given as input to a previouslytrained system. Experimental results show that accuracy values as highas∼95% can be obtained when using a personalized model.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Using_an_Indoor_Localization_System_for_Activity_Recognition - Copy.pdf
accesso aperto
Tipologia:
Documento in Pre-print
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.4 MB
Formato
Adobe PDF
|
1.4 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
