Activity recognition using a hierarchical framework

Author

Naeem, Usman ; Bigham, John

Author_Institution

Dept. of Electron. Eng., Queen Mary Univ. of London, London

fYear

2008

fDate

Jan. 30 2008-Feb. 1 2008

Firstpage

24

Lastpage

27

Abstract

This paper describes an approach for modelling and detecting activities of daily life based on a hierarchy of plans that contain a range of precedence relationships, representations of concurrency and other temporal relationships. Identification of activities of daily life is achieved by episode recovery models supported by using relationships expressed in the plans. The motivation is to allow people with Alzheimerpsilas disease to have additional years of independent living before the Alzheimerpsilas disease reaches the moderate and severe stages.

Keywords

patient care; sensor fusion; Alzheimer´s disease; activity recognition; concurrency representations; daily life activities; episode recovery models; hierarchical framework; precedence relationships; temporal relationships; Alzheimer´s disease; Computer vision; Concurrent computing; Feature extraction; Hidden Markov models; Ontologies; Radiofrequency identification; Sensor phenomena and characterization; Sensor systems; Wearable sensors; Activities of Daily Life; Alzheimer’s Disease; Episode Recovery; Task Identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Pervasive Computing Technologies for Healthcare, 2008. PervasiveHealth 2008. Second International Conference on

Conference_Location

Tampere

Print_ISBN

978-963-9799-15-8

Type

conf

DOI

10.1109/PCTHEALTH.2008.4571018

Filename

4571018