A Fuzzy Based Architecture for Learning Relevant Embedded Agents Associations in Ambient Intelligent Environments

Abstract

This paper presents a novel fuzzy-based intelligent architecture that aims to find relevant associations between services provided by devices and embedded agents residing in Ambient Intelligent Environments (AlEs). The embedded agents perform two processes where the first process monitors the inhabitants of the AIE and learns their behaviors in an online, non-intrusive and life-long fashion. The second process then evaluates the relevance and significance of the associations to various services and eliminates the redundant associations in order to minimize the agent computational latency within the AIE. We will present real world experiments that were conducted in the Essex intelligent Dormitory (iDorm) to evaluate and validate the significance of the proposed architecture.

A multi-society-based intelligent association discovery and selection for ambient intelligence environments

“…Although an agent is capable of acting on its own to execute tasks, the agents perform more useful and complex behaviors if they collaborate together towards a common objective, thus forming an embedded agent society [Duman et al 2007a[Duman et al , 2007b. Grouping agents into societies aims to reduce the complexity of associating and managing large numbers of embedded agents within AIE, where the IAS will deal with a manageable number of agents within each society.…”

“…The iDorm is ubiquitous because the user is surrounded by a multitude of interconnected embedded systems and transparent since the artifacts are seamlessly integrated into the environment [Duman et al 2007b]. The agents will provide the intelligent "presence" as they are able to recognize the users and can autonomously program themselves to the users' needs and preferences by learning from their behavior to control the environment on their behalf [Duman et al 2007b]. …”

“…Step III: Assign γ X j to the following equation which forms a sigmoid function with a normalized constant value for each F-IAS agent as can be seen in Figure 5 [ Duman et al 2007b]). -Step IV: The previous equation generates normalized association weights so that an equal and fair judgment on the importance of association between the agents and the F-IAS can be performed.…”

“…The F-IAS agent perceives the environment through the information provided by the associated agents subscribed to topic T and it affects the AIE through its actuator based on its learnt fuzzy logic controller that approximates the particularized preferences of the user [Duman et al 2007b]. The F-IAS agent is comprised of two stages: (1) offline monitoring and learning and (2) online adaptation and actuation.…”