A case-driven ambient intelligence system for elderly in-home assistance applications - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews Année : 2011

A case-driven ambient intelligence system for elderly in-home assistance applications

Résumé

Elderly in-home assistance (EHA) has traditionally been tackled by human caregivers to equip the elderly with homecare assistance in their daily living. The emerging ambience intelligence (AmI) technology suggests itself to be of great potential for EHA applications, owing to its effectiveness in building a context-aware environment that is sensitive and responsive to the presence of humans. This paper presents a case-driven AmI (C-AmI) system, aiming to sense, predict, reason, and act in response to the elderly activities of daily living (ADLs) at home. The C-AmI system architecture is developed by synthesizing various sensors, activity recognition, case-based reasoning, along with EHA-customized knowledge, within a coherent framework. An EHA information model is formulated through the activity recognition, case comprehension, and assistive action layers. The rough set theory is applied to model ADLs based on the sensor platform embedded in a smart home. Assistive actions are fulfilled with reference to a priori case solutions and implemented within the AmI system through human-object-environment interactions. Initial findings indicate the potential of C-AmI for enhancing context awareness of EHA applications.
Fichier non déposé

Dates et versions

hal-00670957 , version 1 (16-02-2012)

Identifiants

Citer

Feng Zhou, Jianxin Roger Jiao, Songlin Chen, Daqing Zhang. A case-driven ambient intelligence system for elderly in-home assistance applications. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2011, 41 (2), pp.179-189. ⟨10.1109/TSMCC.2010.2052456⟩. ⟨hal-00670957⟩
105 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More