Mobile computing and the IoT offer the potential to provide new applications to support our ageing population. However, there has been little research into the implications for system design of supporting this specific user demographic. In this paper we consider these implications, focusing in particular on an architectural design that offers the potential for complex cross-device analytics while meeting the privacy and usability concerns of older adults.

Intelligent environment research has resulted in many useful tools such as activity recognition, prediction, and automation. However, most of these techniques have been applied in the context of a single resident. A current looming issue for intelligent environment systems is performing these same techniques when multiple residents are present in the environment. In this paper we investigate the problem of attributing sensor events to individuals in a multi-resident intelligent environment. Specifically, we use a naive Bayesian classifier to identify the resident responsible for a unique sensor event. We present results of experimental validation in a real intelligent workplace testbed and discuss the unique issues that arise in addressing this challenging problem. (8 pages)

The concept of ambient intelligence requires software architectures enabling machine intelligence in unstructured dynamic environments. Research in mobile robotics tries to address this field since many years and has successfully created several architectural concepts for behavior-based reactive systems. We describe the architectural and communication-oriented capabilities of the modular controller architecture (MCA) and how ambient intelligence systems may benefit from these. Especially the shared memory approach of MCA offers a great possibility to facilitate distributed dynamic applications. MCA has been developed for mobile robotics research, initially at the FZI in Karlsruhe (K.U. Scholl et al., 2001) and is under continuous development. MCA addresses primitive and object-related communication, re-usability, component-based development, hardware access and application distribution. We want to take a closer look on the MCA framework and how it is already in use within an assisted living environment, established during several projects at Fraunhofer IESE (J. Nehmer et al., 2006) (M. Becker et al., 2007). Several sensors and a mobile service unit were provided by the Robotics Research Lab and the MCA framework was used for service interconnection. An intelligent refrigerator, two human localisation technologies and the mobile service robot ARTOS have MCA running as described in section 3. We present our experiences with the modular controller architecture regarding the parameters identified by the ubiquitous community (M. Weiser, 1991). The outline of this paper is as follows: first the architectural approaches in other projects are mentioned. The modular controller architecture is described in detail, with focus on the requirements of ambient intelligence. We continue by describing our assisted living demonstrator and the services and applications relevant to this work. With reference to our example implementation we conclude the features of MCA that comply to the requirements. Furthermore it is described which future work shall lead to addons and concepts to overcome certain weaknesses in the current system architecture.

This paper discusses the potential of using computer vision systems to determine the usage of architectural spaces with the assistant of cameras. It describes a motion analysis system and explores how this functionality can be used by intelligent spaces to interact with the users in short-term, long-term or periodically, or to assess their usability. (8 pages)

This paper is a very brief summary of a research project which explores, through design and precedent survey, the potential of kinetic architecture to augment our kinesthetic experience of space. The term 'kinetic' here, refers to mechanical and actual motion of the structure which results to changes and modifications of the shape, form and position of the architecture. This research project regards kinetic architecture to be part of the wider context of interactive architecture and discusses issues of spatial experience through the design of an interactively kinetic room. (6 pages)

This paper introduces a novel way to enable users to create temporal smart surroundings easily at open-air events. The final goal of this research was to support social activities in public spaces, such as festivals, camps, and outdoor-ceremonies with ubiquitous computing technologies. We designed and developed universal modular units called "I/O-CRATEs", which are box-shaped units embedded with microcomputers, sensors, actuators, and batteries. We demonstrated the possibilities of our units with a one-night special event. Through this practical experience, we found "I/O-CRATEs" could easily be used to create smart and enjoyable surroundings in many places. (9 pages)

One of the human strengths is to utilize past experiences to solve problems. This process can be technically supported by collecting and exploiting the history of a user's interactions with an intelligent environment. However, most of today's applications cannot or do not take on the additional burden of providing the user with sophisticated memory functionality. In this paper we present the concept of an open personal memory, which allows arbitrary applications to contribute knowledge to the memory with minimal extra effort. We describe a proof-of-concept implementation and show how users can exploit such memories. (10 pages)

The following paper concentrates on examining the built fabric under extreme events. The definition of the extreme within the built environment is analyzed and models for the relief of the phenomenon are considered. The aim is to examine the fluctuations created by the event and to create models of appeasement and design typologies which intent on the imminent relief of the crisis. Theories, such as complexity, self organization, emergence, swarm intelligence, catastrophe theory, bifurcations, networks and systems theories are applied in order to find optimum ways of designing. Generative and evolutionary design, parametric design, is explored. The methodology followed is by simulating (pedestrian movement) the facts and finding optimum design solution. (6 pages)

This paper concerns the personalization of intelligent buildings, where intelligence of a building is considered in a broad sense, not confined to the computational aspects. Personalization is desired in order to give the individual greater representation in the building and for energy consumption/well-being balance in the context of measuring building intelligent quotient. The paper examines problems of programming in pervasive space, and current systems for personalization. It discusses design issues relating to human representation in the building, active and passive human participation, the nature of the personal agent, ownership and location, transparency, and norm-based agency. A design based upon active involvement of the occupant is presented. (7 pages)

The aim of the paper is to introduce a natural language processor enabling mobile multimodal interfaces to receive user driven free speech in order to enable more natural voice interaction with mobile applications and services to control devices in smart environments. Free speech of users is continuously analysed and matched against semantically defined device service commands. The concept and requirements of the language processor and the semantic description for application commands will be explained. Further the paper elaborates on how this concept was fitted into the general concept of a mobile multimodal interface and elaborates on implementation aspects of the language processor. The feasibility of the approach has been shown in a prototypical implementation. The work has been carried out as part of the research on mobile multimodal interfaces within the IST-FP6 MobiLife project. First order or main headings should commence at the left hand margin of each column, and should be in capitals and can be in bold. Except at the top of a new column the first order heading should be preceded by two lines of space and followed by two lines of space. (9 pages)

Security monitoring systems are popular in home automation, and Zigbee is a new industrial standard wireless sensor networks. This paper introduces an experimental home security monitoring and alarming system based on Zigbee technology, it is capable of monitoring door & window magnetic contact, smoke, gas leak, water flooding, providing simple controls such as turning off the valves, and sending the alarms to the residential area security network etc. The security alarming system is based on Zigbee chip MC13192 and low power consumption micro-controller MSP430F135. A description of the system architecture, circuit principle and the firmware flowchart is presented. The system uses a control key fob for activating and de-activating the alarm easily, supports Web interface so that user can access the system remotely to control, search or review the history record, and offers a LCD panel for simple configuration. The experimental system has been designed and its wireless communication test result shows that the Zigbee wireless network can improve the home security with low power and easy to implement solution. (4 pages)

A wide range of disconnected communication networks is emerging in the home. Each has different functions and implementation architectures. The user experience as well as the overall functionality would be vastly enhanced if these networks could collaborate in a seamless fashion. Collaboration is challenging because it requires disparate devices and components to interoperate in a user friendly, scalable and upgradeable fashion. We conjecture that such cooperation might be most efficiently assured using a supporting infrastructure. The universal contents router (UCR) is introduced as an infrastructural component. The UCR moves the burden of connectivity away from the end devices to the system core. The paper spells out ZUMA, or functions that a UCR should support, discusses UCR architecture and presents a first-order prototype. (10 pages)

In this keynote, the author presents selected visions of ambient intelligence and the disappearing computer and comment on the resulting challenges for designing interaction in future smart environments. Our approach is based on exploiting the affordances of real objects by augmenting their physical properties with the potential of computer-based support. Combining the best of both worlds requires an integration of real and virtual worlds resulting in hybrid worlds. In this approach, the computer "disappears" and is almost "invisible" but its functionality is ubiquitously available and provides new forms of interacting with information. The general comments are illustrated with examples taken from developing roomware components for cooperative buildings, project work in the EU-funded "Disappearing Computer" initiative, especially ambient displays and mobile devices in the "Ambient Agoras" project, and more recent developments for smart home environments. (6 pages)

The purpose of this paper is to present the potential of tactile sensing technology in creating intelligent objects. These objects constitute active components of an intelligent environment. The creation of intelligent environments requires the use of sensing technologies that can record the interaction of objects with other objects or with human beings. These sensing technologies provide the data upon which the intelligent environment acts. Tactile sensing can be used to detect the physical interaction of human beings with objects. The application concepts presented in this paper can show how diverse objects such as a keyboard, a door mat, a refrigerator, a driver's seat, a table and a chair can create intelligent environment experiences. (5 pages)

This paper addresses learning and recognition of individual roles from video data in a smart home environment. The proposed approach is part of a framework for acquiring a high-level contextual model for human behaviour in an intelligent environment. The proposed methods for role learning and recognition are based on Bayesian models. The input is the targets and their properties generated and tracked by a robust video tracking system in the environment. The output is the roles "walking", "standing", "sitting", "interacting with table", "sleeping" for each target. A Bayesian classifier produced good results for a framewise classification of these roles, while a hidden Markov model had even better performance taking into account a priori probabilities of roles and role transitions. A support vector machine produced best classification results. The classifiers had, however, problems to distinguish ambiguous roles like "walking" and "standing" in the environment. The obtained results permit to pass to the next step in future work: learning and recognizing relations and situation. (9 pages)

The current multimedia, processing and communication capabilities of mobile devices make them most suitable to act as our intermediaries with the surrounding environment. They are capable of sensing, processing, storing and communicating with the artefacts augmented with computing services (i.e. smart objects) deployed in a smart space. This paper describes a device-type, user-location and communication-means agnostic platform, namely EMI²lets, which fulfils a two-fold purpose: a) it transforms our mobile devices into universal remote controllers of smart objects and b) it helps us constructing smart object ecosystems, i.e. smart spaces. (10 pages)

We present a novel software infrastructure for the seamless integration of heterogeneous output devices into intelligent environments. It dynamically coordinates the output devices to enable adaptive, multimedia presentations by taking the availability of resources and the context of the presentation into account. In this paper we focus on three topics. We present our connecting middleware which supports ad-hoc spontaneous interactions between heterogeneous devices connected by different types of networks. We focus on the multimedia output (MMO) channel which is situated atop this middleware and which is responsible for coordinating output devices according to their self-descriptions. Then we give details about the AI planner which is used by the MMO channel to compute a solution to the presentation problem given by the presentation context. Finally, we outline our implementations for an intelligent living room scenario and point out related work. (10 pages)

The number of smart home appliances that can be connected to the Internet grows every day. In this paper, we explore the potential of combining two emerging head-mounted interaction devices for intuitive control of these devices. Smart glasses are used to detect the object the user wants to control, and an EEG/EMG headset is used for triggering commands to the object of interest. We discuss the research and implementation challenges of identifying devices having the users visual attention and of mapping EEG/EMG headset output to device instructions. By exploiting the user context, we improve the responsiveness and precision of the user intent detection. Despite the enthusiastic reactions of the participants in a small user study, we have learned that the consumer-grade headsets available today present many shortcomings.