Ebook: Ambient Intelligence Perspectives II

As we are approaching the year 2010 Ambient Intelligence is on the verge to reach the milestone set in a quintessential ISTAG report. The concept of ubiquitous, efficient and seamlessly cooperating services with emphasis on user friendliness and unobtrusiveness is to be reviewed. In regard to contemporary reality many of the challenges depicted in the report are still in its infancy. Not only had the technological implementation appeared to be much more intricate. However, in the eyes of a researcher Ambient Intelligence opens new research perspectives that build on existing achievements and intertwine knowledge and experience in different seemingly distant fields. The promising research potential of Ambient Intelligence is evinced by the number of books, journals, conferences and other events. The conferences such as Ambient Intelligence Forum and the new Joint Conference on Ambient Intelligence being on the horizon for the year 2010 with other satellite conferences aiming to join in following years is just a concrete evidence.

This book aims to point to a multifaceted nature of Ambient Intelligence. The book represents a series of rather broadly oriented discussion opportunities for highlighting interdisciplinary, if not transdisciplinary aspects of rapidly evolving area of Ambient Intelligence. In particular the book draws on recent advances, promising research trends in Ambient Intelligence technology and intelligent environments, methods, as well as interesting applications in various areas of the real life.

The book presents Ambient Intelligence in five different perspectives. First perspective focuses on general issues and is discussing the concepts of Ambient Intelligence. Second perspective deals with Ambient Intelligence enablers that facilitate the development of concepts and approaches. Third perspective presents applications of Ambient Intelligence in various fields and activities. Fourth perspective is concerned with Ambient Intelligence as being materialized in intelligent environments integrating devices and knowledge in order to assists and support humans. The last perspective covers the cognitive aspects of Ambient Intelligence.

We acknowledge the support of all the partners who helped this book to become a reality. The book was supported by University of Hradec Králové (Vital mind project 7th EU Framework Programme, project no. 215387), University of Defense (Research proposal Information support of crises management in health care, no. MO0FVZ0000604), Hradec Králové Regional Authority, and Unicorn Systems, a.s. Prague. We are also grateful for selfless support of our colleagues Prof. Peter Mikulecký, Andrea Teichmannová, Vladimír Nodžák, Vojtěch Stehno and Filip Rubáček. Last but not least, we wish to thank to Dr. Juan Carlos Augusto and Maarten Fröhlich for helpful assistance in the process of preparation this book in press, and of course, for publishing the book.

In Hradec Králové, November 30^th, 2009

Editors

This paper presents some ideas related to the concept of large-scale ambient intelligence implementation. The presented concept considers a large network of intelligent devices (ambient artifact) distributed in a number of places in large natural environment (forests, rivers, etc.) ubiquitously communicating each to others, enabling thus monitoring weather conditions, rivers level, rain intensity, and other possible sources of living environment instability unceasingly. The paper is oriented on initial concepts in this area; still it is not possible to present final solutions. However, the approach seems to be usable and promising.

The future of Ambient Intelligence was outlined in two sets of scenarios. However, these scenarios tend to polarize stakeholders' thinking. The paper describes existing scenarios, identifies key stakeholders and depicts related issues such as self-fulfilling prophesy or areas where Ambient Intelligence can be successfully developed.

The paper gives a survey on algebraic tools used in the ambient intelligence to model the basic concepts such as elements of ambient intelligence environment, processes. These techniques proved to be a valid option to formalize the ambient intelligence approaches. Research on relational algebras and universal algebras showed that algebraic tools in general are fully qualified to deal with characteristics of ambient intelligence processes.

Ambient Intelligence (AmI) technology is a step forward to innovation of the whole industrial working environment. The wealth of organizations and enterprises has to be sought in people, their knowledge and skills, internal processes and the company's reputation. Human capital depends on the competence, intellectual ability, and attitudes of the organizations' members. The paper presents a new approach and some practises concerning the education young managers at the Faculty of Economics, Technical University of Košice towards understanding challenges of AmI.

Intelligent Environments provide the infrastructure to deliver Ambient Assisted Living such that elderly people can remain at home and independent for longer. An important part of an Ambient Assisted Living provision is the monitoring, detection and follow up of unsafe situations. One problem these systems have to perform that task is that they only observe the world through incomplete, sometimes unreliable, sensing devices. This naturally leads to uncertain, inconsistent and incomplete perceptions of the world. This paper shows how argumentation, a well established field in computer science, can help to disambiguate some of those confusing (sometimes even inconsistent) situations.

This poster will demonstrate the current state of the semantic technologies usage in the HYDRA project, which aims to develop middleware for networked embedded ambient inteligent devices. Poster provides overview of used ontologies in the project, its structure and description of basic concepts. Ontology maintenance tools and its main functionalities developed within the project are also described.

Nowadays, a rapid progress in information technologies brings the digitalisation into almost every part of our life, with information sources being inter-connected through a variety of online or offline media. The basic idea of the presented paper follows the research report of the British Smith Institute for Industrial Mathematics and System Engineering which states that the design of new products, the delivery of new services, and improvements in operational efficiency in the area of Information Technologies rely in large part on the improvement of collaboration between mathematics and informatics. The problem of the modelling of reality, economical and social processes, is very important in the concept of Information Society. Several methodologies, methods, modelling languages and computer-based tools have been developed. We introduce object-systems as generalizations of graphs as modelling tools in the world of Ambient Intelligence.

Ambient Intelligence (AmI) is a promising notion for improving the performance of managerial decision support function. This research attempts to achieve a considerable progress toward being able to assess the impact of the ambient intelligence tools and technologies on the performance managerial decision support function. This will be accomplished through developing a conceptual model for managerial AmI containing all relevant relationships involving: ICTs and key enabling technologies, key features and notions of ambient intelligence and performance measures of managerial decision support. The developed models will constitute the basis for further objective quantification of the impact of AmI on the performance of the managerial decision support function.

The article deals with a new concept of a crisis health care management system. The concept augments decision making with ambient intelligence approaches integrating information from different components of emergency response system and using simulation and visualization methods to help predict future course of an emergency response.

Ambient Intelligence applications are designed for large numbers of users who share the same physical environment. Agent-based models and simulations allow us to experiment with populations of heterogeneous agents and therefore represent a promising approach applicable in AmI research. In the paper we introduce the principles of agent-based simulations and we explain the process of simulation experimenting in NetLogo programming environment.

CONFIDENCE FP7 project is developing a care system for the elderly based on measurements of locations of radio tags attached to a human body. Posture classification is the basis of reasoning in CONFIDENCE. We first applied a data mining approach to recordings of human behavior in order to develop classifier of posture. However, evaluations with separate training and test set scenario show over fitting. Therefore, we considered enriching classifier by human modification. Posture classifier was developed by human modification of induced decision trees. Besides the 5% improvement in accuracy compared to support vector machines and a significant 11% compared to decision trees, we also expect better robustness of this classifier in real-life tests.

This article describes a state of art for location systems, and presents the INPERLYS (Independent Personal Location System). INPERLYS is an outdoor and indoor location system capable of give the user's position in places where GPS signal fails or is not accurate enough. For that, a dead reckoning method, using sensors like Micro Electrical Mechanical System (MEMS) is used.

In this paper, we propose a persuasive ambient display to promote walking exercise. The display is originally a daily object like a mirror, and provides information about one's exercise level on the periphery of a line of sight. Four strategies for walking encouragement are specified as hypothetical motivational elements: 1) pleasurable interaction with information obtained through daily activity, 2) supporting reflection on each day's walking, 3) avoiding negative feeling while providing negative feedback and 4) facilitating inter-personal encouragement. A case study on information presentation is presented to see the feasibility and effectiveness and to explore further requirements, where a mirror is augmented.

AmIE is an intelligent and innovative system that offers to the elderly people a new way of giving advice on healthy habits and monitoring their health status and daily habits in order to prevent potential problems and diseases, as for example the obstructive sleep apnea, and to help them remain healthy for a longer time. Among the AmIE's innovative aspects there is the use of multimodal interfaces depending on the location of the user, information that will be provided by an indoor location system, and also the profile of the user.

The emergency situations demand for urgent decisions in which much information needs to be gathered and processed and in which many often opposing interests needs to be taken into account. The number of causes, effects, measures, stakeholders and the amount of domain knowledge that is necessary to compile into an optimal solution go beyond human cognitive abilities and draw decision makers for random decisions. This is the situation where the decision makers and/or any authorized personnel can be helpfully and fruitfully supported by intelligent tools that would assist the human decision maker in a proactive and unobtrusive way. The concept of smart office is the label for application of ambient intelligent principles to workplaces where worker often face problem solving and decision making. The paper presents a concept of an assistive environment for decision support in emergency situation. The environment consists of an expert system connected and integrated with simulation engine and the decision support software.

This paper describes a User Centered Design driven development of a system for modern digital home based on the ISO/IEC 24752 standard: Universal Remote Console – URC. The primary target group – elderly users – has problems accepting certain devices and their respective user interfaces. We show that certain user interfaces are acceptable despite the fact that they convey a complex set of functionalities in a modern digital home.

This paper presents proposed solution for analyses of performed actions within a virtual intelligent and interactive environment. Investigated environment provides important functionalities that are based on principles of Ambient intelligence paradigm, i.e. context awareness, personalized and adaptive environment, or access through mobile devices. All activities and changes are monitored and stored into a database to provide one source of data for analytical purposes. The other separate (possibly distributed) databases are various knowledge and content repositories with integrated support services for access by different actors in the environment; and an user database with information about users. Data from these repositories are used for visualization of the whole evolution processes or its selected parts through time-line. The visualization contains information about performed events, relevant objects and actors, interactions between users or between users and environment, all described by semantic metadata. Users will have possibility to create potentially interesting working or critical patterns that will be evaluated through historical data. Results of this evaluation can be seen as new practices, ready for further re-use.

To design socially embedded systems, this paper proposes to learn from human behavior in participatory simulation, where scenario-guided agents and human-controlled avatars coexist in a shared virtual space and jointly perform simulations. To create agent models incrementally, we use machine learning technologies. We characterize agents by using a various combinations of behavior rules instantiated by the user operating his/her avatar. We apply hypothetical reasoning, which offers consistent selection of hypotheses and allows us to start with incompatible behavior rules, for incrementally improving the agent models. Using data obtained during the participatory simulation and the hypotheses including known behavior rules, we can generate an explanation for human behavior.

In this we propose a software architecture to support the Groups in meetings of Ideas Generation in an Ambient Intelligence context. The main issue is how the explicit information, that already exists in the meetings, is represented in order to be easily accessed for future usage. This enables environments in the context of work (Meeting Rooms) to be able to review the past, to be aware of the current context and to be able to propose solutions/ideas for future meetings. The knowledge management is achieve by means of intelligent agents, which must perform tasks such as building knowledge on Domain Ontologies, finding related/equal/opposite issues on indexed knowledge, and delivering the knowledge to the users in appropriate time.