Constructing Ambient Intelligence

We are pleased to present the workshop proceedings of the workshop Artificial Intelligence Methods for Ambient Intelligence, which took place as part of the European Conference on Ambient Intelligence on November 7, 2008 in Darmstadt, Germany. Ambient Intelligence (AmI) is the vision of our future environment. In this future environment we will be surrounded by various kinds of interfaces supported by computing and networking technology which will provide an intelligent, seamless and non-obtrusive assistance to humans. The ambient environment will be aware of the presence and identity of the humans, it will be able to communicate in multi-modal form and to anticipate the humans’ goals and needs in order to provide best possible assistance to them. This broad vision addresses all areas of human life, such as home, work, health care, travel and leisure activities. A large amount of interdisciplinary research will be required in order to achieve this vision. Here, Artificial Intelligence (AI) provides a rich set of methods for implementing the “intelligence bit” of the AmI vision. Speech recognition, image interpretation, learning (from user interaction), reasoning (about users’ goals and intensions) and planning (appropriate user interaction) are core features of AmI to which AI can contribute significantly. The goal of this workshop is to make a step forward towards a common understanding of how AI can contribute to the AmI vision and how to align AI research with it.

Ubiquitous computing aims for the realisation of environments that assist users autonomously and proactively in a non-distractive manner. Therefore smart environment infrastructures need to be able to identify users needs (

intention recognition

) and to plan an appropriate assisting strategy (

strategy generation

) without explicit user interaction. In our two-stage approach we address inferring the intention of a team of users during a meeting within a smart multiple display environment and the system decision process – what information to present on which display – on the strategy generation level.

A key issue in the study of Ambient Intelligence is reasoning about context. The aim of context reasoning is to deduce new knowledge, based on the available context data. The endmost goal is to make the ambient services more ”

intelligent

”; closer to the specific needs of their users. The main challenges of this effort derive from the imperfect context information, and the dynamic and heterogeneous nature of the ambient environments. In this paper, we focus on semantics-based approaches for reasoning about context. We describe how each approach addresses the requirements of ambient environments, identify their limitations, and propose possible future research directions.

In ambient environments, there coexist many different entities that collect, process, and change the available context information. Although they all share the same context, they face it from different viewpoints based on their perceptive capabilities, experiences and goals. Moreover, they are expected to use distinct vocabularies; they may even have different levels of sociality. This diversity raises additional research challenges in the study of Distributed Artificial Intelligence. In this paper, we present an algorithm for reasoning with distributed rule theories in an ambient setting. The algorithm models the participating agents as nodes in a peer-to-peer system, and considers the potential conflicts that may arise during the integration of the distributed theories taking into account some special characteristics of context knowledge and ambient agents.

Ambient agents react on humans on the basis of partial information obtained by sensoring. Appropriate types of reactions depend on in how far an ambient agent is able to interpret the available information (which is often incomplete, and hence multi-interpretable) in order to create a more complete internal image of the environment, including humans. This interpretation process, which often has multiple possible outcomes, can make use of an explicitly represented model of causal and dynamic relations. Given such a model representation, the agent needs a reasoning method to interpret the partial information available by sensoring, by generating one or more possible interpretations. This paper presents a generic model-based default reasoning method that can be exploited to this end. The method allows the use of software tools to determine the different default extensions that form the possible interpretations.

In this paper we describe a network for distributing personalised information with the usage of artificial intelligence methods. Reception of this information should be possible with everyday mobile equipment. Intelligent filtering and spam protection aim at integrating this technology into our environment. Information on the system architecture and usage of the installation are also presented.

Anticipation is a key property of human-human communication, and it is highly desirable for ambient environments to have the means of anticipating events to create a feeling of responsiveness and intelligence in the user. In a home or work environment, a great number of low-cost sensors can be deployed to detect simple events: the passing of a person, the usage of an object, the opening of a door. The methods that try to discover re-usable and interpretable patterns in temporal event data have several shortcomings. Using a testbed that we have developed for this purpose, we first contrast current approaches to the problem. We then extend the best of these approaches, the T-Pattern algorithm, with Gaussian Mixture Models, to obtain a fast and robust algorithm to find patterns in temporal data. Our algorithm can be used to anticipate future events, as well as to detect unexpected events as they occur.

Evaluating ubiquitous systems with users can be a challenge, and the goal of this workshop was to take stock of current issues and novel approaches to address this challenge. In this paper, we report on the discussions we had during several plenary and small-group sessions. We first briefly review those evaluation methods that we identified as being used in ubiquitous computing, and then discuss several issues and research questions that emerged during the discussion. These issues include: data sources used for evaluation, comparing ubiquitous systems, interdisciplinary evaluation, multi-method evaluation, factoring in context and disengaged users.

The implementation of AmI applications is a task of tremendous complexity requiring the seamless integration of heterogeneous systems in an open and flexible way while providing the means for adaptivity and context-awareness. Ubiquitous devices have to cooperate to realize smart environments, multimodal user interfaces have to adapt to the available modalities for interaction and context information has to be taken into account. Therefore, new engineering approaches are needed in order to facilitate efficient design, development and deployment of AmI applications.

This position paper attempts to address the need of including persons, users, as a part of software conception and design. The proposal encourages a keen understanding of the context of use. How and why will the users “use” the product? When? What are their personal goals for using it? Model Driven Engineering has proven its capacity to create software products from (UML) models, but -in our understanding-, it is not enough for specifying products that persons use and love. In order to create human-aware products, traditional analysts of functionality results incomplete. In order to complete the specification of a system a so-called user analysis is considered, complementing the traditional OO functionality and structure analysis. This paper should encourage research in such a line, extending modeling languages to include the new requirements and creating methods to incorporate them in the engineering process.

We propose an approach how to develop and integrate usability metrics in (multimodal) dialog systems and user interfaces with Model Driven Software Development (MDSD). It enables the developer to start early with simple metrics and allows him to refine them during the ongoing work. Additionally, we show how the resulting metrics can be used to estimate the usability in advance, so that the developer may care about critical parts of the application before testing it.

A reusable agent-based generic model is presented for a specific class of Ambient Intelligence applications: those cases addressing human wellbeing and functioning from a human-like understanding. The model incorporates ontologies, knowledge and dynamic models from human-directed sciences such as psychology, social science, neuroscience and biomedical sciences. The model has been formally specified, and it is shown how for specific applications it can be instantiated by application-specific elements, thus providing an executable specification that can be used for prototyping. Moreover, it is shown how dynamic properties can be formally specified and verified against generated traces.

This paper aims at demonstrating that the Model-Driven Architecture (MDA) approach to transformation is suitable to cope with the abstraction gap between the specification of application rules for context-aware applications and the implementation of these rules using rule engines. This paper reports on the transformation of Event-Condition-Action (ECA) rules onto rules that can be executed by the Jess rules engine. We have applied the MDA approach to define this transformation, by specifying it in terms of mappings between elements of the ECA Domain-specific Language (ECA-DL), which is the language we developed to represent ECA rules, and the Jess metamodel. The transformation was fully specified, implemented using the Atlas Transformation Language (ATL) and tested with a simple example.

The ongoing utilization of computer technologies in all areas of life leads to the development of smart environments comprising numerous networked devices and resources. Interacting in and with such environments requires new interaction paradigms, abstracting from single interaction devices to utilize the environment as interaction space. Using a networked set of interaction resources allows supporting multiple modalities and new interaction techniques, but also requires the consideration of the set of devices and the adaptation to this set at runtime. While the generation of user interfaces based on UI models, although still challenging, has been widely researched, the runtime processing and delivery of the derivable user interfaces has gained less attention. Delivering distributed user interfaces while maintaining their interdependencies and keeping them synchronized is not a trivial problem. In this paper we present an approach to realize a runtime environment, capable of distributing user interfaces to a varying set of devices to support multimodal interaction based on a user interface model and the management of interaction resources.

Before developing an Ambient Intelligence (AmI) application, it is often required to examine how its user interface will be distributed across the various interaction surfaces of its physical environment and which types of services these user interfaces will provide to end-users. For this purpose, a virtual reality rendering engine has been developed that renders a user interface model in a physical environment expressed by an environment model and a service model which enables designers to prototype the definition and the distribution of such user interfaces. After the modeling phase, the user interface is rendered in a virtual reality scene that may be subject to prototyping thanks to the model rendering engine. Any suggestion for modification applied on the underlying models (i.e., user interface, environment, and service) is propagated in the virtual reality scene. Depending on the interaction surface where a particular user interface is rendered, some adaptation rules may be performed expressed in terms of model-to-model transformations.

Task models are able to specify the behavior of actors in ambient environments in a compact and readable form. Their original notations have to be extended to meet the requirements in this context. The corresponding tool support has to be flexible in terms of integrating domain concepts rapidly. We propose a model-based approach for tool support of task model editors. By doing so, new modeling concepts can be introduced easily. Thus task models can be extended and provide a basis for analysis and high level design for a wide spread of domains. We fortify our approach by an example in the domain of AmI.

Smart environments offer interconnected sensors, devices, and appliances that can be considered for interaction to substantially extend the potentially available modality mix. This promises a more natural and situation aware human computer interaction. Technical challenges and differences in interaction principles for distinct modalities restrict multimodal systems to specialized systems that support specific situations only. To overcome these limitations enabling an easier integration of new modalities to enhance interaction in smart environments, we propose a task-based notation that can be interpreted at runtime. The notation supports evolutionary prototyping of new interaction styles for already existing interactive systems. We eliminate the gap between design- and runtime, since support for additional modalities can be prototyped at runtime to an already existing interactive system.

Context-awareness, personalization and adaptation are among salient features of Ambient Intelligent (AmI) Systems. The User Interfaces (UI) in AmI environments should therefore also be dynamic at runtime. Developing such UIs is challenging since many aspects have to be considered. Most existing approaches follow Model-driven Engineering (MDE) as a solution. However, they only address design time issues. We successfully applied MDE for runtime generation of UI in the BelAmI project but encountered challenges that we presented in this paper. Possible solutions have also been discussed.

The first edition of AmI-Blocks’07 workshop took place on 7

th

of November 2007 in Darmstadt, in conjunction with the European Conference on Ambient Intelligence (AmI-07). The focus of the workshop was to bring together experts of diverse areas such as Ubiquitous Computing, Product Engineering, Cognitive Science, Human Computer Interaction, Economics, and Artificial Intelligence, with the specific goal of helping shape a vision of creating living and working environments out of Smart Products. The topic chosen to focus the workshop’s discussions was:

“Smart Products: Building Blocks of Ambient Intelligence”

. This focus reflects a growing trend of research that understands the creation of future technology-assisted living and working spaces, as the result of the collaborations between devices and services gradually being deployed, one product at a time.

Sophisticated commercial products and product assemblies can greatly benefit from novel IT-based approaches to the conditioning of these products and of ‘product knowledge’, leading to what we call Smart Products. The paper motivates the need for such novel approaches, introduces important relevant challenges and research domains, and provides an early definition of Smart Products.

Ambient intelligence technologies rapidly change product capabilities but also the way how users interact with physical products. This product-centered stance requires an

instance-centered Product Life Cycle

(iPLC) view which perceives products as autonomous actors performing in physical situations which leads to the concept of smart products. Smart products adapt to situations on the basis of internal representations. We present a generic extensible data model, called

Smart Product Description Objects

(SPDO), whose semantics are described by formal and machine-readable ontologies. SPDO instantiations are computational counterparts of physical product instances. We exemplify the use of SPDO by inferring similarity sets of products within a fashion domain.

In inter-organizational supply chains, sharing of distributed, item-related information gathered using RFID can enable novel applications. Access control (AC) is needed to selectively disclose information to authorized participants. Given the large amount of data and the number of participants, common AC approaches would require extensive manual efforts. These efforts can be reduced significantly by the ability to prove physical possession of items to other companies. We examine how such Proofs of Possession can be designed. Based on two promising approaches, we introduce the concept of a Possession Service that may become a key factor in addressing the AC challenges in future supply chains.

U-TOPIA, introduced in this paper, is an advanced ubiquitous computing environment mainly focusing on a university campus. Research in U-TOPIA spans various components each of which is essential to realize U-TOPIA: from user device hardware/software, user interface, communication technology, indoor/outdoor testbed, middleware to practical applications and security infrastructure. We designed and implemented a wearable platform from the scratch and make use of it as a main user device inside U-TOPIA. In addition to this, as a new user interface, we developed a wireless gesture recognition device, called i-Throw to communicate with U-TOPIA in an intuitive manner. For data communication and location tracking in U-TOPIA, campus-wide indoor and outdoor testbed was deployed. To keep up with secure and dynamic U-TOPIA environment, a new security infrastructure,called pKASSO, and extensible middleware,

μ

-ware, was developed. Finally, as a practical application for U-TOPIA, we implemented a ubiquitous testbed room where multiple users interact with various ubiquitous devices or other users securely in a user-friendly manner. Integrating these components all together, we show that U-TOPIA can be a realistic role model to improve current paradigm of ubiquitous computing environment one step forward within a few years.

The joint workshop on Ambient Assisted Living Systems was held in Darmstadt on 10th November 2007. It consisted of a plenary talk by Gregory Abowd from the Georgia Institute of Technology, a keynote by Hartmut Strese from VDI/VDE-IT, a track on the progress in the EU project MonAMI, and a scientific track presenting eight peer reviewed papers on various topics in ambient assisted living (AAL). The workshop was concluded by a joint discussion about the future of AAL. Here, we report on the outcome of this discussion. The views and ideas put forth in the following summary are the joint contributions of all the participants in that discussion whom we hereby want to express our thanks.

In this paper, the most important results of the social research within the Project “Assisted Living” at the Technical University of Kaiserslautern, are discussed: First we present impressions of elderly people who tested a newly developed user interface for touch screen Computers. Second, experiences of elderly people who use assistive devices in their everyday life are illustrated. Third, results of a standardised survey on acceptance of home automation technology are presented: The overall willingness to use new technical devices among the elderly is higher than often expected. Still, Ambient Assisted Living (AAL) for elderly people still faces some challenges: Costs and installation efforts are still very high, the most urgent needs and wants of elderly people should be emphasized more strongly for AAL to evolve into successful products on the market.

A formally specified multi-agent-based model for medicine usage management is presented and formally analysed. The model incorporates an intelligent ambient agent model that has an explicit representation of a dynamic system model to estimate the medicine level in the patient’s body by simulation, and is able to analyse whether the patient intends to take the medicine too early or too late.

An ambient assisted living (AAL) approach based on standard home automation devices is presented. The aim of this AAL project is to enable senior citizens to live independently as long as possible. Two basic principles have been observed during the development of the AAL environment: first, in order to make the project a success it is crucial to consider both the needs and the wants of seniors. Second, health monitoring issues are important but the project will only be successful if it comes as a package with additional benefits (comfort, entertainment, safety, and communication). To provide these extra functionalities, the tablet PC-based PAUL – the Personal Assistant Unit for Living – has been developed. The HCI has been specifically designed for high ease of use and intuitive interaction. Moreover, PAUL also monitors the activities of daily living (ADL) and can generate alarms. The algorithms and automata used for this purpose are described in this paper.

The objective is to detect activities taking place in a home for the purpose of creating models of behavior for the occupant. An array of sensors captures the status of appliances used in the home. Models for the occupant’s activities are built from the captured data using unsupervised learning techniques. Predictive models can be used in a number of ways: to enhance user experience, to maximize resource usage efficiency, for safety and for security. This work focuses on supporting independent living and enhancing quality of life for older persons. The goal is for the system to distinguish between normal and anomalous behavior. In this paper, we present the results of unsupervised classification techniques applied to the problem of modeling activity.

The paper presents the BERNIE prototype that realizes health assistance within super markets based on RFID technology. By storing the list of ingredients of each individual good, BERNIE is able to support shoppers in an unobtrusive and anonymous fashion. The paper ends with the description of the quantitative results of a 7-days field trial that was conducted at the CeBIT 2007 exhibition.

Rural areas cover 90% of the EU’s territory and half of the Europeans live in these areas. It is of high priority to ensure the full participation right of these people in the information society, which means considering them during the newest developments (such as AAL) as well. In this paper, we envision a PDA-centered medical sensor system setup that is suitable for the AAL homecare scenario and identify a problem that can easily arise in rural areas. Additionally, we intruduce a pilot application that can act as the seed of the envisioned system and gives an answer to the identified problems.

The steady increase in life expectancy in our modern industrialized societies will not only lead to a significant change in demographics, but also in epidemiologic factors. This paper reviews current predictions for epidemiologic indicators and derives implications for the development of future health-enabling technologies. Methods: A literature search in PubMed/MEDLINE was conducted and several statistical data bases were used to obtain up-to-date prediction data on health in the elderly population. Results: Prevalence rates for the leading diseases such as cardiovascular diseases, diabetes mellitus and cancers will remain almost constant in the next decades, but incidence rates will rise markedly because of the increase in the elderly population. For neuropsychiatric diseases such as dementias and depression an increased impact is expected. Conclusion: One focus for the development of health-enabling technologies is and will remain on monitoring, especially cardiovascular parameters. More research needs to be conducted to tap the full technological potential of preventive measures, e.g. for the prevention of social isolation and the promotion of a healthy lifestyle.

The workshop on Human Aspects in Ambient Intelligence addresses multidisciplinary aspects of Ambient Intelligence with human-directed disciplines such as psychology, social science, neuroscience and biomedical sciences. The aim is to get modellers and researchers together, working in these disciplines, or on cross connections of Ambient Intelligence with such a discipline. The focus is on the use of knowledge from these disciplines in Ambient Intelligence applications, in order to take care of and support in a knowledgeable manner humans in their daily living in medical, psychological and social respects.

This paper briefly outlines the scientific area that addresses Ambient Intelligence applications in which not only sensor data, but also knowledge from the human-directed sciences such as biomedical science, neuroscience, and psychological and social sciences is incorporated. This knowledge enables the environment to perform more in-depth, human-like analyses of the functioning of the observed humans, and to come up with better informed actions. It is discussed which ingredients are important to realise this view, and how frameworks can be developed to combine them to obtain the intended type of systems: reflective coupled human-environment systems. Finally, further perspectives are discussed for Ambient Intelligence applications based on these reflective coupled human-environment systems.

This paper is aimed to introduce IDIAP Brain Computer Interface (IBCI) research that successfully applied Ambience Intelligence (AmI) principles in designing intelligent brain-machine interactions. We proceed through IBCI applications describing how machines can decode and react to the human mental commands, cognitive and emotive states. We show how effective human-machine interaction for brain computer interfacing (BCI) can be achieved through, 1) asynchronous and spontaneous BCI, 2) shared control between the human and machine, 3) online learning and 4) the use of cognitive state recognition. Identifying common principles in BCI research and ambiance intelligence (AmI) research, we discuss IBCI applications. With the current studies on recognition of human cognitive states, we argue for the possibility of designing empathic environments or devices that have a better human like understanding directly from brain signals.

This paper addresses the development of an adaptive cooperative agent in a domain that suffers from human error in the allocation of attention. The design is discussed of a component of this adaptive agent, called Human Attention-Based Task Allocator (HABTA), capable of managing agent and human attention. The HABTA-component reallocates the human’s and agent’s focus of attention to tasks or objects based on an estimation of the current human allocation of attention and by comparison of this estimation with certain normative rules. The main contribution of the present paper is the description of the combined approach of design and validation for the development of such components. Two complementary experiments of validation of HABTA are described. The first experiment validates the model of human attention that is incorporated in HABTA, comparing estimations of the model with those of humans. The second experiment validates the HABTA-component itself, measuring its effect in terms of human-agent team performance, trust, and reliance. Finally, some intermediary results of the first experiment are shown, using human data in the domain of naval warfare.

The need to include customer’s affective needs in product design presents a new direction beyond tradtional human factors and ergonomics. While the human-product interactions have been extensively studied, the interactions of these elements with the ambience have been largely ignored. This gives rise to a nascent research perspective called affective human factors design, which aims at addressing human’s emotional responses and aspirations and to achieve aesthetic appreciation and pleasurable experience through human-product-ambience interactions. This paper presents a framework of affective human factors design with ambient intelligence to achieve the extensive interactions among these elements. Ambient intelligence establishes a multidisciplinary technology core that incorporates affective design, human factors and ergonomics, product development, and specific application sectors. A few application scenarios reveal the most important characteristics and emerging trends in this research area.

The “implementation” and use of smart home technology to lengthen independent living of non-instutionalized elderly have not always been flawless. The purpose of this study is to show that problems with smart home technology can be partially ascribed to differences in perception of the stakeholders involved. The perceptual worlds of caregivers, care receivers, and designers vary due to differences in background and experiences. To decrease the perceptual differences between the stakeholders, we propose an analysis of the expected and experienced effects of smart home technology for each group. For designers the effects will involve effective goals, caregivers are mainly interested in effects on workload and quality of care, while care receivers are influenced by usability effects. Making each stakeholder aware of the experienced and expected effects of the other stakeholders may broaden their perspectives and may lead to more successful implementations of smart home technology, and technology in general.

Ambient systems that explain their actions promote the user’s understanding as they give the user more insight in the effects of their behavior on the environment. In order to provide individualized intelligent explanations, we need not only to evaluate a user’s observable behavior, but we also need to make sense of the underlying beliefs, intentions and strategies. In this paper we argue for the need of intelligent explanations, identify the requirements of such explanations, propose a method to achieve generation of intelligent explanations, and report on a prototype in the training of naval situation assessment and decision making. We discuss the implications of intelligent explanations in training and set the agenda for future research.

The recent NFC technology is not only valid for payment and ticketing, a new interaction form is also available. With the only action being to put a mobile phone close to another NFC device (reader, tag or mobile phone) it is possible to get a contactless communication supported by a server or not. Some services such as open doors, location, access, presence, and so on, can be performed with a simple touch. In this work we analyze the interaction through the adaptability of two technologies: RFID and NFC. Challenges in models have been considered. In addition, we are trying to put in practice the idea of tagging context and the awareness only with a single interaction by touch. For that, we consider the benefits to adapting NFC technology as a good approach to model contexts.

Ambient agents react on humans on the basis of their information obtained by sensoring and their knowledge about human functioning. Appropriate types of reactions depend on in how far an ambient agent understands the human. On the one hand, such an understanding requires that the agent has knowledge to a certain depth about the human’s physiological and mental processes in the form of an explicitly represented model of the causal and dynamic relations describing these processes. On the other hand, given such a model representation, the agent needs reasoning methods to derive conclusions from the model and the information available by sensoring. This paper presents a number of such model-based reasoning methods. They have been formally specified in an executable temporal format, which allows for simulation of reasoning traces and automated verification in a dedicated software environment. A number of such simulation experiments and their formal analysis are described.

The Amigo architecture follows the paradigm of Service orientation, which allows developing software as services delivered and consumed on demand. The benefit of this approach lies in the looser coupling of the software components making up an application. Discovery mechanisms can be used for finding and selecting the functionality that a client is looking for. Many protocols already exist in the area of Service orientation; the Amigo project has chosen to support a number of the important protocols for discovery and communication in an interoperable way, which allows programmers to select the protocol of their choice while they can still access functionality of services using different methods. This paper gives an introductory overview of the Amigo middleware and shows how this Amigo architecture can provide easy and effective integration of services in today’s home through middleware that dynamically integrates heterogeneous systems and through intelligent user services that improve the usability and attractiveness of the system.

The user’s environment is increasingly enriched with computing devices that offer services that aid users in their daily activities. Current use of these services is either public (i.e. unrestricted), or requires explicit registration. In the first case, user control and security are sacrificed whilst in the second ease of use and flexibility is limited. In this paper, we extend the perspective of user-centric computing in offering guests a simple and transparent way to access their home services from a visited intelligent environment. We provide the users with a Personal Access Device (PAD) that facilitates creation of trust between the user’s own home and a visited intelligent environment. This enables seamless access to home services from the visited environment.

We offer a comprehensive approach to semantic service description, discovery, composition, adaptation and execution in the Amigo home, collectively called SD-SDCAE, which enables integration of heterogeneous services of the networked home environment into complex user tasks based on their abstract specification. We demonstrate SD-SDCAE with an application scenario that dynamically composes home services and devices.

Ambient communication adapts interpersonal remote communication to the activities of users and supports interactions that come as close as possible to face to face communication. Elements of both user, physical environment and system context are taken into account to support adaptation of the communication setup and to offer implicit and intuitive interaction with the system. User presence and availability are two of the key elements of context information used by ambient communication systems. In this paper, we discuss our approach to context-aware user presence management, and describe an implementation of a presence management service. This software leverages middleware and services developed by the Amigo project to estimate user presence and availability with respect to communication applications. We also show an example of a visual communication application using interfaces distributed in the user’s environment to support spatial interaction functionalities.

The Amigo Context Management Service (CMS) provides an open infrastructure for the exchange of contextual information between context sources and context clients. Whereas context sources supply context information, retrieved from sensors or services within the networked home environment, context clients utilize those information to become context-aware.

An ambient communication scenario realizing follow-me elements is used to showcase how applications benefit from the combination of acoustics-based context sources and positioning sensors.

Perceived privacy, i.e., how end-users perceive that the system affects their privacy, is one of the key aspects for the acceptance by users of ambient intelligent systems and one of the most complex to handle. Exploratory, field and conceptual design studies were conducted to generate user requirements as input and constraints for the development of mechanisms for the enforcement of privacy preferences. Based on these field studies, a model was created and a prototype was implemented in which the context, the content, and the presence of people was discovered, and shared under various privacy-sensitive conditions.

The ontology-based semantic approaches are gradually gaining momentum in ambient intelligent environments such as smart homes, smart cars, intelligent offices, etc. In spite of the significant research work carried out in the ontology design and application field, several issues remain unresolved. The ontologies mainly focus on specific context information features. The capabilities of services from different functional domains are rarely addressed and are not aligned with context ontologies. No attempt has been made to integrate the existing ontologies, facilitating their future extension with emerging new technologies for networks, devices, software architectures and platforms. Moreover, the application developer support facilitating better understanding of semantic technologies is still in its infancy. The research work presented in this paper tackles the aforementioned issues.

The Amigo Interoperability Framework provides middleware-layer mechanisms that enable integrating heterogeneous networked devices and services. It includes a service discovery and interaction interoperability architecture and a domotic architecture, which have been tested in combination in a proof-of-concept prototype.

This article presents an overview of the integrated project WASP that deals with the research and development of Wirelessly Accessible Sensor Populations. WASP is a European project of the Embedded Systems Strategic Objective in Framework Programme 6 of the European Union. WASP is covering the complete technology chain from sensor node hardware to the implementation of applications. The article illustrates the integrated approach of WASP by subsuming the variety of research and development issues that are addressed to reach the ambitious project goal: the provision of a complete system view for building large populations of collaborating objects.

This paper presents some intermediate results of the EU-IST project WASP that aims to develop an integrated model for implementing applications using wireless sensor networks. In this paper we present our approach to programming sensor networks. The main contribution concerns the separation of three abstraction levels leaving more room for standardization than with current practices. In addition, we propose to program the network from an overall perspective rather than programming individual nodes. For doing this we present two programming models that complement one another. The proposed programming model is event-based, corresponding closely to the nature of wireless sensors. The paper shows our approaches by giving several examples and ends with a description of wireless sensor networks related services and gives an outlook on future work.

Being both EU-IST integrated projects in the field of AAL, PERSONA and SOPRANO organized a conjoint workshop on the occasion of the AmI-07 conference in order for the researchers of the projects to exchange insights of the approaches to the key field challenges, the achievements so far in each of the projects, and possible synergies in the future. Here, we summarize the exchanged info and the workshop results. The paper gives a good overview of the two projects and their status by the end of October 2007.

In order to explore how the next generation of information intensive, distributed and ubiquitous systems will look like, we need to establish a common ground for relevant research that has been carried out by several interrelated communities, e.g. ubiquitous Data Mining/Machine Learning, Semantic Web, Ubiquitous Computing and Embedded Systems.