Ambient Intelligence

Interactive surfaces form an integral component of intelligent environments. In the paper, we describe HapticArmrest, a simple tactile interface that communicates tactual surface characteristic and form of interactive elements on direct touch surfaces. Spatially separating manual touch input and active tactile output allows for the combination of various types of tactile actuators for versatile haptic feedback. In a preliminary experiment, we indicate that our approach enables a reliable discrimination of virtual elements on touch surfaces solely based on tactile representations. We also assessed the hedonic and pragmatic qualities of the generated tactile stimuli by applying methods from the field of usability research.

Driving a car has become a challenge for many people despite the fact that evermore technology is built into vehicles in order to support the driver. Above all, the increasing number of in-vehicle information systems (IVIS) is a main source of driver distraction. The fragmentation of IVIS elements in the cockpit increases the attention demand and cognitive load of the driver. In this paper, we present an approach to integrate most in-car interaction possibilities into a steering wheel, by combining a multi-button row with a single touch in an intelligent steering wheel. We performed an online study (N=301) to investigate the pre-prototype user acceptance of the three different steering wheel modalities (single touch, multi button, combi touch) as well as a lab-based driving simulator study (N=10) to assess the practicability of the single touch interaction. The results of the online study showed that especially the single touch was highly accepted by the participants. The driving simulator study revealed that touch-based interaction on a steering wheel is feasible for low demand tasks in terms of driver distraction. Especially, the single touch embedded into the steering wheel is a promising approach for ambient information in the automotive context.

Many researchers have proposed the development of table-top interfaces in the last decade. In a table-top system, for user satisfaction, they must be able to operate digital and analog media seamlessly. In this paper, we propose a table-top interface system that allows users to intuitively operate digital media by gesture recognition. The proposed system can capture the image of an object placed on the table by recognizing pressing gestures from fingernail images, and can transfer digital content by recognizing user’s shaking gestures. The evaluation experiments show that users can intuitively operate the proposed system without being aware of the data transmission.

This paper describes new concepts and techniques for an indoor positioning system that uses ultrasonic signals to enhance practicability. This indoor positioning system can be applied to the location detection of a moving object such as a person or a goods trolley over a wide indoor area. The proposed system works by means of ultrasonic signals. This makes it easy to avoid multipath effects because the propagation velocity of ultrasonic signals is much slower than that of radio waves. In addition, ultrasonic signals are not restricted by radio regulations that may differ from country to country. The main feature of our system, developed and presented last year, is that it does not require synchronization between the transmitting and receiving units. This paper describes a system for accommodating multiple moving objects and expanding positioning area. Two techniques, the allocation of a specific ID to each positioning object and the use of a virtual receiving point for ultrasonic signals, were investigated in order to realize the required functions and make the proposed system more practical. The effectiveness of these techniques was confirmed by experiments carried out using ultrasonic sensors installed in the ceiling and model railway trains acting as moving objects on the floor below.

Reaction time (RT) tests are known as simple and sensitive tests for detecting variation in cognitive efficiency. RT tests measure the elapsed time between a stimulus and the individual’s response to it. A drawback of existing RT tests is that they require the full attention of a test person which prohibits the measurement of cognitive efficiency during daily routine tasks. In this contribution we present the design and the evaluation of a wearable RT test user interface which can be operated throughout everyday life. We designed a wearable watch-like device which combines the generation of a haptic stimulus and the recognition of subject’s hand movement response. In order to show to what extent the wearable RT test is convenient to measure reaction times, we designed an experiment in which we measured the reaction times of ten subjects from two different setups. In the first half of the experiment, the participants performed a desktop-based RT test whereas in the second half of the experiment they performed the wearable RT test. In order to measure changes in the duration and variability of reaction times we induced additional cognitive load in both setups. We show that individual changes of reaction times occurred due to the cognitive load manipulation are similar for both desktop-based and wearable RT test. Additionally we investigate the subjective ratings of perceived workload. We conclude that the presented wearable RT test allows to measure changes in reaction times occurred due to additional cognitive load and hence would allow the assessment of changes in cognitive efficiency throughout everyday life.

In Ambient Assisted Living and other environments the problem is to recognize all of user activities. Due to noisy or incomplete information a naïve recognition system may report activities that are logically inconsistent with each other, e.g., the user is sleeping on the couch and at the same time is watching TV. In this work, we develop a rule-based recognition system for hierarchically-organized activities that returns only logically consistent scenarios. This is achieved by explicitly formulating conflicts as Weighted Partial MaxSAT clauses to be satisfied. The system also has the ability to adjust the desired level of detail of the scenarios returned. This is accomplished by assigning preferences to clauses of the SAT problem. The system is implemented and evaluated in a real Ambient Intelligence experimental space. It is shown to be robust to the presence of noise; the level of detail can easily be adjusted by the use of two preference parameters.

The development of ambient social applications brings challenges to aggregate information from heterogeneous sources, like users, physical environments, and available services. We propose a framework for aggregating information from different sources, and utilize a novel representation, Entity Notation (EN), as a starting point of connecting all information to knowledge-based systems, which offers good possibilities to support ambient social intelligence. In this paper, we present the framework, our EN representation, and an implementation of a map reminder service to demonstrate the usability of our framework.

Location is a key element for ambient intelligence services. Due to GPS inaccuracies, inferring high level information (i.e., being at home, at work, in a restaurant) from geographic coordinates in still non trivial. In this paper we use information about activities being performed by the user to improve location recognition accuracy. Unlike traditional methods, relations between locations and activities are not extracted from training data but from an external commonsense knowledge base. Our approach maps location and activity labels to concepts organized within the ConceptNet network. Then, it verifies their commonsense proximity by implementing a bio-inspired greedy algorithm. Experimental results show a sharp increase in localization accuracy.

The automatic recognition of human activities such as cooking, showering and sleeping allows many potential applications in the area of ambient intelligence. In this paper we show that using a hierarchical structure to model the activities from sensor data can be very beneficial for the recognition performance of the model. We present a two-layer hierarchical model in which activities consist of a sequence of actions. During training, sensor data is automatically clustered into clusters of actions that best fit to the data, so that sensor data only has to be labeled with activities, not actions. Our proposed model is evaluated on three real world datasets and compared to two non-hierarchical temporal probabilistic models. The hierarchical model outperforms the non-hierarchical models in all datasets and does so significantly in two of the three datasets.

In this paper we describe a novel methodology for performing real-time analysis of localization data streams produced by sensors embedded in ambient intelligence (AmI) environments. The methodology aims to handle different types of real-time events, detect interesting behavior in sequences of such events, and calculate statistical information using a scalable stream-processing engine (SPE) that executes continuous queries expressed in a stream-oriented query language. Key contributions of our approach are the integration of the Borealis SPE into a large-scale interactive museum exhibit system that tracks visitor positions through a number of cameras; the extension and customization of Borealis to support the types of real-time analysis useful in the context of the museum exhibit as well as in other AmI applications; and the integration with a visualization component responsible for rendering events received by the SPE in a variety of human readable forms.

This work is devoted to the classification and adaptation of current ambient intelligence (AmI) research activities from the viewpoint of the autonomic computing paradigm. Special attention is given to the implementation of AmI’s user-centric focus in autonomic computing.

Automated activity recognition systems that use probabilistic models require labeled data sets in training phase for learning the model parameters. The parameters are different for every person and every environment. Therefore, for every person or environment, training is needed to be performed from scratch. Obtaining labeled data requires much effort therefore poses challenges on the large scale deployment of activity recognition systems. Active learning can be a solution to this problem. It is a machine learning technique that allows the algorithm to choose the most informative data points to be annotated. Because the algorithm selects the most informative data points, the amount of the labeled data needed for training the model is reduced. In this study, we propose using active learning methods for activity recognition. We use three different informativeness measures for selecting the most informative data points and evaluate their performances using three real world data sets recorded in a home setting. We show through experiments that the required number of data points is reduced by 80% in House A, 73% in House B, and 66% in House C with active learning.

This paper is about automatic tagging of urban areas considering its constituent Points of Interest. First, our approach geographically clusters places that offer similar services in the same generic category (e.g. Food & Dining; Entertainment & Arts) in order to identify specialized

zones

in the urban context. Then, these places are analysed and tagged from available information sources on the Web using KUSCO [2,3] and finally the most relevant tags are chosen considering not only the place itself but also its popularity in social networks. We present some experiments in the greater metropolitan area of Boston.

As opposed to conventional applications, smart environments are designed to offer transparent user assistance by decoupling users from devices. Apart from the lack of realised systems there are numerous applications that are strongly interwoven with the users’ workflow and hard to replace, commonly called legacy applications. Instead of creating new applications, our approach is the loose integration of these both, the smart environment and the legacy application. In our work, we propose a generic architecture that is applicable to various kinds of environments and applications. The architecture comprises an intermediate layer that enables a loose coupling between smart environment and legacy application. Furthermore, we introduce a workflow to refine the generic architecture to fit the requirements of specific use cases. For our use case, we apply the vision of a pervasive university. Here, we integrate functionalities of smart lecture rooms into a learning management system that is commonly used in German universities and therefore hard to replace.

We present a distributed systems framework for sharing knowledge and capabilities in ad-hoc networks of devices where network bandwidth, network connectivity and device computing power are severely limited. We develop a distributed registry to store knowledge of device capabilities and their invocation, implement it and show how it can be deployed in a set of network nodes to exemplify its usefulness. The ideas are exemplified with an ambient intelligence scenario known as autonomous road trains.

Liquid Interface is an organic user interface that utilizes ferrofluid as an output display and input button embodiment. Using a matrix of Hall effect sensors, magnetic fields generated by rare-earth magnets worn on the fingertips are measured and are then converted into signals that provide input capability. This input actuates an array of electromagnets. Both Hall effect sensors and electromagnets are contained beneath the surface of the ferrofluid. By matching like polarities between the electromagnets and the rare-earth magnets, haptic force feedback by means of magnetic field repulsion can be achieved.

We propose a mechanism and system for the identification, self-configuration, monitoring and control of non-networked home devices through a shared backplane of networked sensors and actuators. The resulting generic home abstraction layer interfaces to all kinds of physical entities of the home through a software proxy, as if they were state-of-the-art networked devices. The matching of the entities being discovered in the home/building environment to known semi-generic models is performed by iterative approximation. The architecture and OSGi-based implementation of this system is described. Examples are provided for typical home appliances and other subsystems of the home/building that may be dealt with in a similar way.

This paper conducts a preliminary study in which sleeping behavior is predicted using long-term activity data from a wearable sensor. For this purpose, two scenarios are scrutinized: The first predicts sleeping behavior using a day-of-the-week model. In a second scenario typical sleep patterns for either working or weekend days are modeled. In a continuous experiment over 141 days (6 months), sleeping behavior is characterized by four main features: the amount of motion detected by the sensor during sleep, the duration of sleep, and the falling asleep and waking up times. Prediction of these values can be used in behavioral sleep analysis and beyond, as a component in healthcare systems.

Besides saving energy, using it at the right time (i.e. when there is a supply surplus, and the power is produced by sustainable power sources such as hydroelectricity or wind) is an important possibility to achieve positive effects for the environment. To enable the user to align their behavior with the dynamics of the energy generation they need to be informed about the current status of power supply and grid capacity. Furthermore, to be able to plan their behavior and possibly delay or advance consumption activities to more proper moments they also need to have access to high-quality forecasts about the future status of green energy supply. In this paper we present an ambient display design solution based on a common watch that is optimized for providing this information in an unobtrusive, ambient and persuasive way. We present and discuss requirements identified by use of literature analysis, focus groups and end-user questionnaires, outline approaches to calculate basic power generation forecasts based on weather forecast data and present an ambient interface concept designed to meet the identified requirements. We conclude that the developed approach has high potential to support desired behavior changes, and that achieving acceptable accuracy levels for the generation forecast is feasible with relatively little effort.

This paper describes current progress in the implementation of flexible ubiquitous textile display. We use thermochromic inks and miniature peltier semiconductor elements to create a non-emissive textile display. Here we present some of the initial work into the use of custom made miniature peltier elements. We describe some of the early works into the integration of this technology into the fabric to present a flexible non-emissive display.

This paper proposes the design of a voice control module for intelligent environments, primarily oriented to home environments. An intelligent environment is understood to be a ubiquitous space equipped with embedded devices. This solution is based on the main standards in the field of speech technologies (VoiceXML, MRCP, SRGS and SISR), dynamically adaptable to structural changes in the home automation system and scalable to the number of rooms and devices in the home. The final solution has been validated in a real home automation installation, using distant speech recognition and a keyword detection approach (keyword spotting, KWS). KWS works as an input filter for the dialogue system, making it more robust against noise. Test results have shown the technical feasibility of the solution and promising user acceptance.

The Definition of Self is a museum exhibition at 21_21 DESIGN SIGHT in 2010, intended to speculate our attributes in the contemporary world. This paper discusses design and interaction of two exhibits created for The Definition of Self. Pool of Fingerprints presents a new way of looking at fingerprints by using fingerprint matching technology. The visitor feels emotional attachment to his/her fingerprint. The Nominal Divide let the visitor experience how he or she is seen by computer vision.

We present a novel way of interacting with an ambient environment through semantic cut-out images. These images represent resources that appear on a regular image shot by a camera – people, buildings, anything of interest – which are cut out of the original image and pasted into a new image with transparent background. Hence these images can be placed in a different context such as a background that tells more about a resource’s current state. By annotating cut-outs and incorporating them in user interfaces for ambient environments, we show how the interaction experience within such environments can be made more personal, visually appealing and intuitive. To this end, we first transform a series of images and their cut-outs into a visual knowledge base.

This paper presents a proof of concept technology for a novel concept of dynamic markers for Augmented Reality. Here, by dynamic we mean markers that can change on external stimuli. Thus, the paper describes the use of ambient dynamic Augmented Reality Markers as temperature sensors. To achieve this technology we print patterns on an AR marker using thermochromic inks of various actuation temperatures. Thus, as the temperature gradually changes, the marker morphs into new marker for each temperature range. Thus here we present our preliminary results for three temperature ranges and discuss this work can be extended and applied in the future.

In this paper we describe the development of a platform for creating Head Up Games. Nowadays, technology is becoming more and more ubiquitous, but in the field of pervasive gaming it seems that development is mostly centered on smart phones. We argue that for outdoor games for children this might not be the best medium; and we propose the design of our platform that is designed to better support outdoor, active games.

Can ubiquitous technologies intended to change people’s behavior benefit from personalization? This paper addresses the development of an

adaptive persuasive system

intended to increase stair climbing at work: APStairs. Based on their

persuasion profile,

individuals are distinguished by their susceptibility to different social influence strategies. This paper contributes a first application of persuasion profiling in the domain of ambient intelligence; it reports the deployment of the APStairs system in a real life setting for a period of five weeks involving 34 participants. Although a longer deployment period is needed to statistically validate the system, this first deployment of the system has shown the feasibility of adaptive persuasion.

This paper presents the design, implementation and evaluation of a context-aware recommendation system that promotes the adoption of a healthy and active lifestyle. A Smartphone application that provides personalized and contextualized advice based on geo information, weather, user location and agenda was developed and evaluated by a user study. The results show the potential of this mobile application in triggering behavior change by suggesting simple daily activities.

This paper describes the design and preliminary evaluation of Aulura, a system designed for motivating people to increase their physical activity. Aulura is an ambient information display that aims to ‘lure’ users to interact with it, to review their progress and set personal goals. We present the design of ‘ambient cues’ added to a picture frame with the aim to increase user interaction with the device and engagement with a physical activity promotion service. Empirical evaluation in a home simulation laboratory provided positive feedback relating to its potential to further engage participants in an online lifestyle management service.

The goal of this paper is to discover human habits using the received sensors data-streams, in order to improve the energy efficiency. We propose a multi-agent architecture and a formalism to describe scenarios in ubiquitous environments based on a wireless sensors network. We have used sensor data and simulations about a four person family, to validate our prototype.

Personalization of content on public displays is likely to cause the disclosure of user’s private data. In order to protect the user’s privacy, different protection strategies are used, e.g. the private data is hidden, occluded or blurred. Existing systems usually follow a uniform protection strategy, applying it every time a spectator is detected in the display proximity. However, the necessity in privacy protection often depends on the personal relationships between the user and the spectator. This work investigates how the relationship context influences user preferences in adaptation strategies. Additionally, we study how privacy level of data and the presence of a mobile device influence this preference. The obtained results can guide adaptation designers in creation of more flexible privacy protection mechanisms.

In this paper we explore the theoretical concept of trust by putting it in to play empirically. Influences of trust on an Intranet based leader strategy in a big organisation are investigated. We also discuss other significant features that affect success or no success of such approach. The presentation builds on an interview study in one district of Stockholm, Norrmalm, and a survey committed in two districts of this city (Spånga-Tensta and Skärholmen). This paper is conducted in the field of Human Computer Interaction.

This paper introduces free play, a meaning making activity, as a desideratum of social and contemplative ambient intelligence. A contemplative AmI is not focused on easing routine human activities, but through free play and other mechanisms, will encourage humans to engage with each other and the AmI on thinking about and acting on societal issues over long time scales. These ideas are illustrated by the design of an interactive, intelligent art installation about adaptation to climate change. This approach to AmI extends the connotations of AmI along social, spatial, and temporal dimensions.

This paper discusses a line of research targeted to investigate and introduce innovative solutions for efficient learning in smart environments through integrating AmI technology in the learning process. Following a discussion of current approaches to technology integration in the classroom, the overall concept of the Student-Centric “Intelligent” Classroom and the related software are described. Potential future improvements are outlined.

The Florence project develops a robot for elderly that provides multiple Ambient Assisted Living (AAL) and Lifestyle services with a consistent user-interface. The project success is measured by the acceptance of these services by the user group. Enabling such service robotics in (smart) homes requires a robust and flexible platform to collect, enhance and distribute sensory information; and to manipulate the actuators in the environment. A key characteristic of such an environment is that sensors and actuators are not always available, are distributed, and are mobile (due to e.g. the robot and phone mobility). This dynamicity requires a loose coupling between services and sensors/actuators. The paper describes the design principles and high level architecture of the Florence platform that hides the distribution, availability and mobility aspects from the services, and sketches some challenges that lie ahead.

In this paper we introduce a hybrid people tracking system based on the combined use of RFID UWB technology and computer vision techniques. The proposed system takes advantage of the different characteristics of the vision and wireless subsystems to achieve better accuracy and reliability for people tracking. Moreover data gained from the subsystems can be used for a more complex context capture system and can be seen as an enabler of a number of application from video-surveillance to Ambient Intelligence scenarios. Different scenarios have been tested to assess the feasibility and performance of the system. Experimental results demonstrate advantages in people tracking tasks encouraging further researches.

In the Ambient Assisted Living (AAL) domain, specific systems have been developed and applied to enable people with specific needs, such as elderly or disabled people, to live longer independently in their familiar residential environments. In order to support the development of such systems, a range of AAL platforms have been developed in recent years. However, there are considerable differences among these AAL platforms, particularly with respect to the treatment of important non-functional properties. This makes the selection of a suitable platform for a given AAL project very difficult. In order to support developers in this difficult task, we present an evaluation of relevant AAL platforms based on a selection of quality attributes that are important for AAL systems.

Community care is expected to be increasingly important for seniors in need of support towards prolonged independent living and higher quality of life. Whereas people generally indicate they are willing to provide support within their community, several barriers prevent elderly people from asking for support. The present paper describes the design of CommunityNet, a social network service that aims to bring together the local community and to lower the barriers towards asking for help. Based on the findings from user research, ambient awareness displays were developed and placed in the homes of seniors and local community members. The awareness displays showed an overview of the people, their requests for help, and the status of the requests. The concept was evaluated in a field trial (n=4, 10 days). The participants indicated that they preferred using CommunityNet compared to face-to-face contact and telephone when the need for support was not urgent. According to the participants, the barriers towards asking for help were lowered by the system. As a next step, an automated match-maker mechanism will be developed which enables people to extend their care network, and the system will be tested in a range of communities.

The design of awareness displays to support family care has been explored in many recent studies. Whereas user studies indicate that caregivers are interested to know seniors’ subjective experiences regarding activities, events and general attitudes, product developers tend to focus on using sensors to automatically detect the state and context of seniors in time, resulting in systems that are unable to capture the seniors’ experiences. This short paper presents

experience tagging

, a mechanism which enables end-users to enrich sensor data using subjective tags. A research concept of an awareness display for family caregivers is presented to illustrate how the mechanism can be integrated in the design of an awareness display. The preliminary findings from a 4-week field trial with three caregiver/senior couples are presented. As a next step, the use of experience tags could be studied in other settings where people or systems are interested to know the user perspective on sensor data.

Detecting wellness in older adults with just ambient sensors is a challenging and difficult task, one that can only be address with large volumes of detailed annotated data and a diverse participant base. Presented here are early results comparing movement data to baseline depression and mobility data from a purpose built 16 unit ambient assisted living development in Ireland. With the goal of ultimately detecting health changes in an older population with ambient sensors, results here show that whereas there is some correlations between health measures and sensor data as well as some observable patterns, but more work needs to be done.

Self-measurement of blood pressure requires the patient to follow a range of best practice recommendations in order to be considered valid for diagnostic use. We evaluate the feasibility of using a sensor-equipped chair to classify patient position during blood pressure measurement. Results indicate that this is feasible with over 89 % confirmed classification results.

Ambient Assisted Living Technologies are providing sustainable and affordable solutions for the independent living of senior citizens. In this scenario, telemedicine systems enhance distance patient’s health care through interactive audiovisual media at home. Today TV is becoming the main connected device at home. However, Interactive TV applications must be fully adapted, particularly to the available input device: the Remote Control (RC). Despite this adaptation, some tasks are still uncomfortable due to the RC limitations. Therefore, more user-friendly input modalities are strongly desired. Spoken language allows distance hands- and eyes-free operation within the room, providing an intuitive and natural interface. This paper presents some accessibility facilities based on speech technologies for an interactive TV telemedicine service. The specific layout for TV environments, the help of an avatar and the voice navigation will enhance the user access, while the speech-based creation of medical reports reduces dramatically the time physicians need to write reports.

Do elderly people have a preference between performing in-air gestures or pressing screen buttons to interact with an assistive robot? This study attempts to provide answers to this question by measuring the level of acceptance, performance as well as knowledge of both interaction modalities during a scenario where elderly participants interacted with an assistive robot. Two interaction modalities were compared; in-air gestures and touch. A scenario has been chosen in which the elderly people perform exercises in order to improve lifestyle behavior. The seniors in this scenario stand in front of the assistive robot. The robot displays several exercises on the robot screen. After each successfully performed exercise the senior navigates to the next or previous exercise. No significant differences were found between the interaction modalities on the technology acceptance measures on effort, ease, anxiety, performance and attitude. The results on these measures were very high for both interaction modalities, indicating that both modalities were accepted by the elderly people. In a final interview participants reacted more positive on the use of in-air gestures.

In Ambient Assisted Living (AAL), the context-dependent adaption of a system to a person’s needs is of particular interest. In the living area, a fine-grained context may not only contain information about the occupancy of certain furniture, but also the posture of a user on the occupied furniture. This information is useful in the application area of home automation, where, for example, a lying user may effect a different system reaction than a sitting user. In this paper, we present an approach for determining contextual information from furniture, using capacitive proximity sensors. Moreover, we evaluate the performance of Naïve Bayes classifiers, decision trees and radial basis function networks, regarding the classification of user postures. Therefore, we use our generic classification framework to visualize, train and evaluate postures with up to two persons on a couch. Based on a data set collected from multiple users, we show that this approach is robust and suitable for real-time classification.

This paper describes the findings arising from ongoing qualitative usability evaluation studies on mobile companion robotics in smart home environments from two research projects focused on socio-technical innovation to support independent living (

CompanionAble

and

Mobiserv

). Key findings are described, and it is stated that the robotic companion, the smart home environment, and external services need to be seamlessly integrated to create a truly supportive and trusted system. The idea of

robot personas

is introduced, and based on our empirical observations, it is argued that the robot persona, rather than the physical embodiment, is the most important determinant of the degree of users’ acceptance in terms of users’ perceived trustability and responsiveness of the robot and therefore their sense of enhanced usability and satisfaction with such personal assistive systems.

This paper describes a participatory design-oriented study of an ambient assisted living system for monitoring the daily activities of elderly residents. The work presented addresses these questions 1) What daily activities the elderly participants like to be monitored, 2) With whom they would want to share this monitored data and 3) How a monitoring system for the elderly should be designed. For this purpose, this paper discusses the study results and participatory design techniques used to exemplify and understand desired ambient-assisted living scenarios and information sharing needs. Particularly, an interactive dollhouse is presented as a method for including the elderly in the design and requirements gathering process for residential monitoring. The study results indicate the importance of exemplifying ambient-assisted living scenarios to involve the elderly and so to increase acceptance and utility of such systems. The preliminary studies presented show that the participants were willing to have most of their daily activities monitored. However, they mostly wanted to keep control over their own data and share this information with medical specialists and particularly not with their fellow elderly neighbours.

Recent research in Human Computer studies have shown that smart and efficient technology alone is not what people desire for in their homes. The Interactive Carpet project aims to produce a new kind of interaction - Poetic Communication, enabling remote communication through the creation of a sense of sharing, co-presence, and connectedness. This technology connects two carpets in remote locations enhancing communication through more meaningful aesthetic interactions.

We present a method of selective wireless power transferring for paper computing. The novelty of this method lies in the power transmitter can be controlled to selectively activate different receivers in the context of wireless power transferring with multiple receivers. This was achieved by changing the output frequency of the power transmitter and the impedance of the receivers. With this method, users could easily design new types of paper-computing system without worrying about the arrangement of the massive wire connection to power supply. This technology combining with paper computing can become a physical rendering system using paper-crafts, such as paper folding and cutting.

With the continuous advancements in ubiquitous computing and media, the technology has widened to include the multisensory experiences. Although there are quite a lot of systems in auditory, vision, and haptic domains, remarkably few attempts have been made in smell and taste senses in order to facilitate ambient intelligence. We present a novel control system that enables digital stimulations of the sense of taste (gustation) to enhance remote multisensory interactions on human. The system uses two approaches to actuate taste sensations digitally: the electrical and thermal stimulations on tongue. At present, the initial experimental results suggested that sourness and saltiness are the main sensations that could be evoked besides several evidences of sweet and bitter sensations.

There is increasing interest in the development of ambient assisted living services to increase the quality of life of the increasing older population. Little consideration has been given to the specific problem of providing such services and systems at night. We report on the NOCTURNAL project which provides specialised night time support to people at early stages of dementia.

In the domain of assisted living, the majority of the work on awareness systems focuses on communicating information on health and security for functional purposes: to provide better care and peace of mind. When aiming for improved well-being, awareness systems could also be used to stimulate a sense of connectedness. Not much is known on how awareness systems for well-being should be designed. This paper describes several design explorations that illustrate how communication of subtle, low-bandwidth information may be leveraged to support a mutual feeling of social connectedness between people. We discuss the gained insights, which are useful for the design of ambient displays and interactions. The insights presented in this paper are useful for the future design of assisted living services, and for awareness systems in general.

This paper reports on the first international workshop on Aesthetic Intelligence. The focus of the workshop is on the relevance of beauty and aesthetic values for Ambient Intelligence and the meaning of aesthetically pleasing design for usability, technology acceptance, and well-being in technology-enhanced spaces.

LED-based lighting systems have introduced radically new possibilities in the area of artificial lighting. Being physically small the LED can be positioned or embedded into luminaires, materials and even the very fabric of a building or environment. The light switch therefore in many situations will need to be enhanced or fully replaced by intelligent controls and smart environments that are sensitive to the context and responsive to the presence of people. Future lighting systems will become a part of the Ambient Intelligence (AmI). This workshop explores how the vision and principles of the AmI paradigm can be applied to future lighting controls, where lighting is not anymore only a functional on/off system, but a flexible system capable of creating a large range of functional/decoration and ambient light effects.

In the past years, efforts in surveillance and open space analysis have focused on traditional computer vision problems like scene modeling or object detection and tracking. Research on human behavior recognition have tended to work on predefined simple activities such as running, jumping or left luggage, and single-person trajectory analysis. The goal of the workshop is to bring together experts and researchers from different fields to share their experience and expertise about the opportunities on the development of tools for automated social analysis in open and public spaces. Humans exhibit a rich range of behaviors, from their interaction with the environment such as how groups of people occupy the space or how they manipulate or use objects within it, to the way they communicate with each other. Such behaviors can be captured from multiple sensors. Automatically interpreting interactive behavior provides a richer foundation for ambient intelligent environments.

The development of dementia happens to a large part of elderly people. Since the condition is – so far – without a cure, the only means of dealing with it, currently, is personal or institutional care. Basically, as dementia progresses, the affected person tends to forget more about his or her immediate surroundings and regresses into early memories from childhood, for example. The results are disorientation, confusion and the inability to perform many daily life tasks like keeping appointments or even a regular way of life. The high prevalence of the condition in conjunction with the very personnel-consuming means of treatment poses a direct challenge to existing health care systems in the near future.

With Europes aging population and an increasing number of older people living alone or geographically distant from kin, loneliness is turning into a prevalent issue. This might involve deleterious consequences for both the older person and society, such as depression and increased use of healthcare services. Virtual coaches that act as friend in a para-social relationship but also as mentor that helps the elderly end- user to create meaningful relationships in his actual social environment are a powerful method to overcome loneliness and increase the quality of life in the elderly population.The AAL Joint Programme projects A2E2 (AAL-2008-1-071) and V2me (AAL-2009-2-107) are exploring virtual coaches and their application in AAL scenarios, including the use of user avatars, virtual self-representations that allow the user to be represented in communication scenarios. Other European research projects that focus on social integration of the elderly are e.g. ALICE (AAL-2009-2-091) or WeCare (AAL-2009-2-026). Outside the European Union the negative implications of population aging can be observed in Japan, having an even larger proportion of senior citizens, using individual-centred devices, such as robot pets,1 to improve the quality of life of lonely elderly persons.

The user groups involved often are not acquainted with modern ICT systems and therefore it is a challenge to create intuitive, adaptive platforms that cater to the individual needs and allow the user to interact easily.

The digital agenda of the European Commission includes plans for the building of Information and Communication Technology (ICT) based on a new generation of networks, or the Internet of the Future. To this end, the Future Internet Private Public Partnership (FI-PPP) has been established with the help of the European Commission. It will involve the building of a proof of concept FI platform in the coming two years. One of the main challenges of this platform is to be generic while serving the needs of specific application sectors. This workshop will focus on the challenges of integrating Ambient Intelligence (AmI) and Ambient Assisted Living (AAL) platforms with this kind of platform. Participants in the workshop will include members of the AmI/AAL platform community, members of the FI community, and policy makers.

New technologies create opportunities to enrich people’s experience while playing games. In recent years we have seen many examples of technological advances opening up new player experiences, for instance new controllers (e.g. Nintendo’s Wii), new sensor technologies (e.g. GPS), and new forms of play (e.g. multi-player online games and open-ended play), etc. Another novel technology offering ample opportunities to derive new properties for games and play is

ambient intelligence

.

The HBU workshop is organized for the second time, with a focus theme of

inducing behavioral change

. The general aim of the workshop is to bring together researchers developing and using computer analysis tools for learning and modeling human behavior, covering both hardware or software aspects. As such, the topics link areas like pattern recognition, sensor technologies, social signal processing, and interaction design.

This workshop addresses topics of increasing importance in the emerging area of the Internet of Things (IoT): privacy, trust and related interaction concepts. The aim of the workshop is to bring together experts from different areas to cover the complexity of the questions involved and to provide a forum for developing new ideas on how to address the major challenges in the field considering both a scientific and an industrial viewpoint. The workshop targets to identify pressing questions and to develop a research agenda for trusted and privacy-respecting computing in the IoT. Special attention within the workshop is given on whether and how experiences with privacy and trust from related areas can be applied to the IoT, where existing conceptualizations need to be extended or modified and where radically new concepts are required.