Older people would like to live independently in their home as long as possible. They want to reduce the risk of domestic accidents because of polypharmacy, physical weakness and other mental illnesses, which could increase the risks of domestic accidents (i.e. a fall). Changes in the behaviour of healthy older people could be correlated with cognitive disorders; consequently, early intervention could delay the deterioration of the disease. Over the last few years, activity recognition systems have been developed to support the management of senior citizens’ daily life. In this context, this paper aims to go beyond the state-of-the-art presenting a proof of concept where information on body movement, vital signs and user’s indoor locations are aggregated to improve the activity recognition task. The presented system has been tested in a realistic environment with three users in order to assess the feasibility of the proposed method. These results encouraged the use of this approach in activity recognition applications; indeed, the overall accuracy values, amongst others, are satisfactory increased (+2.67% DT, +7.39% SVM, +147.37% NN).

User indoor localisation system enhances activity recognition: A proof of concept / FIORINI, Laura; BONACCORSI, Manuele; BETTI, STEFANO; DARIO, Paolo; CAVALLO, Filippo. - ELETTRONICO. - 426:(2017), pp. 251-268. (Intervento presentato al convegno 7th Italian Forum on Ambient Assisted Living, ForitAAL 2016 tenutosi a ita nel 2016) [10.1007/978-3-319-54283-6_19].

User indoor localisation system enhances activity recognition: A proof of concept

FIORINI, Laura;CAVALLO, Filippo
2017

Abstract

Older people would like to live independently in their home as long as possible. They want to reduce the risk of domestic accidents because of polypharmacy, physical weakness and other mental illnesses, which could increase the risks of domestic accidents (i.e. a fall). Changes in the behaviour of healthy older people could be correlated with cognitive disorders; consequently, early intervention could delay the deterioration of the disease. Over the last few years, activity recognition systems have been developed to support the management of senior citizens’ daily life. In this context, this paper aims to go beyond the state-of-the-art presenting a proof of concept where information on body movement, vital signs and user’s indoor locations are aggregated to improve the activity recognition task. The presented system has been tested in a realistic environment with three users in order to assess the feasibility of the proposed method. These results encouraged the use of this approach in activity recognition applications; indeed, the overall accuracy values, amongst others, are satisfactory increased (+2.67% DT, +7.39% SVM, +147.37% NN).
2017
Lecture Notes in Electrical Engineering
7th Italian Forum on Ambient Assisted Living, ForitAAL 2016
ita
2016
FIORINI, Laura; BONACCORSI, Manuele; BETTI, STEFANO; DARIO, Paolo; CAVALLO, Filippo
File in questo prodotto:
File Dimensione Formato  
C031 - User Indoor Localisation System enhances Activity Recognition.pdf

Accesso chiuso

Dimensione 1.3 MB
Formato Adobe PDF
1.3 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1210814
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact