6533b85bfe1ef96bd12bbabe

RESEARCH PRODUCT

An Autonomic System for Estimating Human Presence through Bayesian Networks

A AdelfioGiuseppe Lo ReM. OrtolaniAlessandra De PaolaSalvatore Gaglio

subject

Ambient Intelligence Bayesian Network Autonomic Computing

description

In the Ambient Intelligence (AmI) context, a relevant research topic is represented by the methods for determining users' presence in order to design context-aware systems capable of monitoring the environment in which they operate, and of timely reacting to changes. This work describes an autonomic software agent comprising a double-level reasoning. At the lower level, a Bayesian network merges the available sensory information related to the users' presence, whereas the upper level performs a meta-reasoning on the system performance and configuration in order to enable the system self-assessment. Experimental results show the validity of the proposed method on a sample scenario.

http://hdl.handle.net/10447/59590