作者: Stewart Massie , Glenn Forbes , Susan Craw , Lucy Fraser , Graeme Hamilton
DOI:
关键词:
摘要: We consider use of an ambient sensor network, installed in Smart Homes, to identify low level events taking place which can then be analysed generate a resident's profile activities daily living (ADLs). These ADL profiles are compared both the typical and known 'risky' support evidence-based interventions. Human activity recognition ADLs from data is key challenge, windowbased representation on four existing datasets. find that windowing works well, giving consistent performance. also introduce FITsense, building Home environment specifically increased risk falls allow interventions before occurs.