Moving from Internet Appliances to Internet Intelligent Environments: Challenges and DirectionsAbstract1 introduction2 Characteristics of Intelligent Environments2.1 Related Research3 Intelligent Environment System3.1 Physical Network3.2 Communication Protocols3.3 Network Environment3.4 Intelligent Devices and Internet Appliances3.5 Learning Framework3.6 Training Element3.7 Maintenance element4 Internet Intelligent Environments4.1 Scenarios4.1.1 Device Adaptation4.1.2 Usage of Internet and Telecommunication Networks4.1.3 Temporal and Contextual Behavior4.2 Major Challenges4.2.1 Inherent Difficulties4.2.2 Specialization4.2.3 Heterogeneity and Intrusiveness4.2.4 Temporal (Contextual) Sensitivity5 Recommendations5.1 Adapting to Dynamic Collections of Devices5.2 Automating the usage of simple devices5.3 Learning occupant behavior5.4 Allowing user intervention5.5 Learning temporal patterns6 Conclusions7 ReferencesMoving from Internet Appliances to Internet IntelligentEnvironments: Challenges and DirectionsEdwin O Heierman, III, Diane J. Cook, Sajal K. Das, and Lawrence B. HolderDepartment of Computer Science and EngineeringThe University of Texas at ArlingtonArlington, Texas 76019-0015{heierman, cook, das, holder}@cse.uta.eduABSTRACTAlthough various research efforts have reported some success in solving difficultproblems related to intelligent environments, very little progress has been made inimplementing a truly intelligent system in reality. This paper looks at intelligentenvironments from a networking and connectivity point of view in order to gain a freshperspective. First, we review intelligent environment qualities and projects so that wemay ascertain the current state of intelligent environment research. Next, we present aclassification of the essential components of an intelligent environment, and observe thata connectivity infrastructure does exist in the form of a network of Internet Appliances.We also note, however, that the intelligence components necessary for an intelligentenvironment are lacking. Therefore, we discuss challenges and provide directions forfuture research so that we can move from a network of Internet Appliances to InternetIntelligent Environments.1 INTRODUCTIONSince the beginning of the computer age, extraordinary predictions have been madeabout computers revolutionizing our lives. Early predictions were based on theperception that computers could eventually perform the same tasks as humans, andpossibly even exceed human intelligence. Although computer performance hassignificantly increased over the years, many of these predications have failed tomaterialize due to the difficulty of learning even simplistic human tasks. For example,consider the prediction of intelligent home automation. Widespread automated homes donot exist to date. For most of us, perhaps a VCR that could program itself would be asignificant step towards an intelligent home. - 1 -Two observations clarify the difficulties with intelligent environment systems. First, anintelligent environment needs to be an intelligent being [Dilger, 1998]. The environmentmust possess a degree of autonomy, adapt itself to changing conditions, andcommunicate with humans in a natural way. Second, adaptive software will benecessary for environment automation to become commonplace [Mozer, 1998]. It isunreasonable to assume the inhabitants will want to program the environment in order tocustomize the behavior, especially if the term "programming" implies traditional computerprogramming. Traditional approaches to user interfaces and software applications arenot appropriate for intelligent environments. This paper looks at intelligent environments from a networking and connectivity point ofview in order to gain a fresh perspective. First, we define the qualities of an intelligentenvironment and present related research. Next, we provide a classification of the majorcomponents of an intelligent environment system. Then, we discuss Intelligent InternetEnvironments, and we describe several scenarios and associated challenges. Finally,we conclude with recommendations to guide future intelligent environment research.2 CHARACTERISTICS OF INTELLIGENT ENVIRONMENTSWe begin by discussing common characteristics found in intelligent environments, suchas environment automation, natural interfaces, multimodal inputs, ubiquitous computing,aware computing and adaptable computing. These qualities differentiate an intelligentenvironment from traditional environments, and are discussed below.- The goal of any intelligent environment is to automate the usage of the deviceswithin the environment. The system automatically turns devices on and off, directsinformation to the appropriate devices, and simplifies the coordination of multipledevices. Environment automation allows an inhabitant to concentrate on the task athand, rather than on the devices necessary to perform the task. It is important not toconfuse centralized device control with environment automation. We do not consideran environment that only provides device control to be an intelligent environment.Automation is the key characteristic of an intelligent environment.- In general, computers do a poor job of supporting our daily activities, because theycommunicate with users via devices that are suitable to the computer. Unfortunately,the commonly used WIMP (windows, icons, menus, pointer) interface is exactly what- 2 -limits the usefulness of a computer. The paradigm is not an acceptable form ofhuman-computer interaction for future computing environments [Turk, 2000]. In anintelligent environment, Human-Computer Interfaces (HCI) should be naturalinterfaces designed for the human inhabitants and not for the computational system.Spoken language and human behavior should be used to communicate with thesystem, rather than pointing and clicking. A computational system should performtasks in support of the human occupants naturally and non-intrusively. The goal ofcurrent HCI research is to remove the barriers of traditional computer interfaces. Todate, almost all computer interface effort has concentrated on graphical userinterfaces (GUIs). Work on the next generation of interfaces, namely Perceptual UserInterfaces