Creating an Ambient-Intelligence Environment Using Embedded Agents

Abstract

A mbient intelligence is an exciting new information technology paradigm in which people are empowered through a digital environment that is aware of their presence and context and is sensitive, adaptive, and responsive to their needs. 1 Ambient-intelligence environments are characterized by their ubiquity, transparency, and intelligence. In these environments, a multitude of interconnected, invisible embedded systems, seamlessly integrated into the background, surround the user. The system recognizes the people that live in it and programs itself to meet their needs by learning from their behavior. 1 To realize the ambient-intelligence vision, people must be able to seamlessly and unobtrusively use and configure the computer-based artifacts and systems in their ubiquitous-computing environments without being cognitively overloaded. 1 The user shouldn't have to program each device or connect them together to achieve the required functionality. The complexity associated with the number, varieties, and uses of computer-based artifacts requires that we design a system that lets intelligence disappear into the infrastructure of active spaces (such as buildings, shopping malls, theaters, and homes), 2 automatically learning to carry out everyday tasks based on the users' habitual behavior.Our work focuses on developing learning and adaptation techniques for embedded agents. We seek to provide online, lifelong, personalized learning of anticipatory adaptive control to realize the ambientintelligence vision in ubiquitous-computing environments. We developed the Essex intelligent dormitory, or iDorm, as a test bed for this work and an exemplar of this approach.

Ambient intelligence: Technologies, applications, and opportunities

“…The iDorm project of Hagras, et al [66] is another of these notable projects that has realized a fully-implemented automated living environment. In this case, the setting is a campus dorm environment.…”

“…A common interface to the iDorm and its devices is implemented through Universal Plug and Play (UPnP), and any networked computer running a standard Java process can access and control the iDorm directly [66]. Fuzzy rules are learned from observing resident activities [67] and are used to control select devices in the dorm room.…”

A review of smart homes in healthcare

“…In [46], the authors used a fuzzy rule-based controller where the output of the rules is not a class but a function in order to monitor a smart environment, called "iDorm", based on preferences of the occupants. The data was generated over two months by recording two student activities in a dormitory flat which is equipped with 11 sensors: internal light level, external light level, internal temperature, external temperature, chair pressure, bed pressure, occupancy and time etc.…”

“…The study demonstrated how fuzzy rules can be continuously generated online to meet the requirements of a dynamic environment. The author used the iDorm data [46]. The data was split into two subsets: the training set contains 75% samples for the first month, and The testing set contains 25% of the first month and all samples of the second month.…”

Algorithms for Smart Spaces

“…In contrast, the approach taken by the iDorm project [19] is to use a fuzzy expert system to learn rules that replicate inhabitant interactions with devices, but will not find an alternative control strategy that improves on manual control for considerations such as energy expenditure.…”