Detecting Activities from Body-Worn Accelerometers via Instance-based Algorithms

Bicocchi, Nicola; Mamei, Marco; Zambonelli, Franco

doi:10.1016/j.pmcj.2010.03.004

The automatic and unobtrusive identification of user’s activities is one of the challenging goals of context-aware computing. This paper discusses and experimentally evaluates instance-based algorithms to infer user’s activities on the basis of data acquired from body-worn accelerometer sensors. We show that instance-based algorithms can classify simple and specific activities with high accuracy. In addition, due to their low requirements, we show how they can be implemented on severely resource-constrained devices. Finally, we propose mechanisms to take advantage of the temporal dimension of the signal, and to identify novel activities at run time.

Detecting Activities from Body-Worn Accelerometers via Instance-based Algorithms / Bicocchi, Nicola; Mamei, Marco; Zambonelli, Franco. - In: PERVASIVE AND MOBILE COMPUTING. - ISSN 1574-1192. - STAMPA. - 6(2010), pp. 482-495. [10.1016/j.pmcj.2010.03.004]

Data di pubblicazione:	2010
Titolo:	Detecting Activities from Body-Worn Accelerometers via Instance-based Algorithms
Autore/i:	Bicocchi, Nicola; Mamei, Marco; Zambonelli, Franco
Autore/i UNIMORE:	BICOCCHI, Nicola MAMEI, Marco ZAMBONELLI, Franco
Digital Object Identifier (DOI):	http://dx.doi.org/10.1016/j.pmcj.2010.03.004
Rivista:	PERVASIVE AND MOBILE COMPUTING
Volume:	6
Pagina iniziale:	482
Pagina finale:	495
Codice identificativo ISI:	WOS:000208192900007
Codice identificativo Scopus:	2-s2.0-77956411876
Citazione:	Detecting Activities from Body-Worn Accelerometers via Instance-based Algorithms / Bicocchi, Nicola; Mamei, Marco; Zambonelli, Franco. - In: PERVASIVE AND MOBILE COMPUTING. - ISSN 1574-1192. - STAMPA. - 6(2010), pp. 482-495. [10.1016/j.pmcj.2010.03.004]
Tipologia	Articolo su rivista

File in questo prodotto:

File	Descrizione	Tipologia
human-pcm.pdf		Post-print dell'autore (bozza post referaggio)	Administrator Richiedi una copia

Pubblicazioni consigliate

Loading suggested articles...

Utilizza questo identificativo per citare o creare un link a questo documento:
http://hdl.handle.net/11380/643710

Citazioni

I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris