HCI Bibliography Home | HCI Conferences | AmI Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
AmI Tables of Contents: 101112131415

Proceedings of the 2012 International Joint Conference on Ambient Intelligence

Fullname:AmI 2012: Third International Joint Conference on Ambient Intelligence
Editors:Fabio Paternò; Boris de Ruyter; Panos Markopoulos; Carmen Santoro; Evert van Loenen; Kris Luyten
Location:Pisa, Italy
Dates:2012-Nov-13 to 2012-Nov-15
Publisher:Springer Berlin Heidelberg
Series:Lecture Notes in Computer Science 7683
Standard No:DOI: 10.1007/978-3-642-34898-3 hcibib: AmI12; ISBN: 978-3-642-34897-6 (print), 978-3-642-34898-3 (online)
Links:Online Proceedings | Conference Home Page
  1. Long Papers
  2. Short Papers
  3. Landscape Papers
  4. Poster Papers
  5. Demo Papers
  6. Workshops

Long Papers

Context-Based Fall Detection Using Inertial and Location Sensors BIBAKFull-Text 1-16
  Hristijan Gjoreski; Mitja Lustrek; Matjaz Gams
Falls are some of the most common sources of injury among the elderly. A fall is particularly critical when the elderly person is injured and cannot call for help. This problem is addressed by many fall-detection systems, but they often focus on isolated falls under restricted conditions, neglecting complex, real-life situations. In this paper a combination of body-worn inertial and location sensors for fall detection is studied. A novel context-based method that exploits the information from both types of sensors is designed. The evaluation is performed on a real-life scenario, including fast falls, slow falls and fall-like situations that are difficult to distinguish from falls. All the possible combinations of six inertial and four location sensors are tested. The results show that: (i) context-based reasoning significantly improves the performance; (ii) a combination of two types of sensors in a single physical sensor enclosure seems to be the best practical solution.
Keywords: Context-based reasoning; Fall detection; Inertial sensors; Location sensors; Activity recognition
Enhancing Accelerometer-Based Activity Recognition with Capacitive Proximity Sensing BIBAKFull-Text 17-32
  Tobias Alexander Große-Puppendahl; Eugen Berlin; Marko Borazio
Activity recognition with a wearable accelerometer is a common investigated research topic and enables the detection of basic activities like sitting, walking or standing. Recent work in this area adds different sensing modalities to the inertial data to collect more information of the user's environment to boost activity recognition for more challenging activities. This work presents a sensor prototype consisting of an accelerometer and a capacitive proximity sensor that senses the user's activities based on the combined sensor values. We show that our proposed approach of combining both modalities significantly improves the recognition rate for detecting activities of daily living.
Keywords: activity recognition; capacitive proximity sensors; ambient assisted living; user context
Adaptive User Interfaces for Smart Environments with the Support of Model-Based Languages BIBAKFull-Text 33-48
  Sara Bongartz; Yucheng Jin; Fabio Paternò; Jörg Rett; Carmen Santoro; Lucio Davide Spano
This article presents a solution for supporting adaptive user interfaces in work environments. Its architecture is built upon the concept of model-based UI design extended by context aware and adaptive features. Model-based languages provide the software development process with useful support for, building design prototypes and actual implementations for devices with various interaction resources. The proposed architecture is able to adapt to selected aspects of the context during run-time by communicating with a context server and applying the specified adaptation rules. In order to show the possibilities of the proposed solution, we report on its application in the development of an adaptive user interface prototype to be used in a warehouse picking system.
Keywords: Adaptive service front-ends; Context-aware user interfaces; model-based user interface languages; Warehouse picking system
Back of the Steering Wheel Interaction: The Car Braille Keyer BIBAKFull-Text 49-64
  Sebastian Osswald; Alexander Meschtscherjakov; Nicole Mirnig; Karl-Armin Kraessig; David Wilfinger; Martin Murer; Manfred Tscheligi
In this paper, we present a novel text input approach for car drivers: The Car Braille Keyer combines a keyer concept (defined as keyboard without an actual board) and the braille code (i.e. blind writing method) at the back of the steering wheel. This concept allows eyeless text input while driving and simultaneously leaving the hands on the steering wheel. We present a prototype of the Car Braille Keyer along with an expert evaluation and a user study. The prototype consists of two sets of three buttons each, both of which are fixed on the back side of the steering wheel (one on the left, the other on the right side). The six buttons are designed to match a braille character like they can be found in the braille language. This approach allows for entering a character or command with only a single input combination without the need to look at the keys. In our prototype we added visual output in the head up display (HUD) as well as auditive feedback to enhance the interaction. To evaluate the system, we performed a heuristic evaluation with five HCI experts. Based on their feedback, we iterated the design of the prototype and added a learning tool for interaction using the Car Braille Keyer. An initial user study with the iterated prototype and twelve participants showed a good overall usability (SUS score=73.75) as well as a good acceptance rate based on the Technology Acceptance Model (TAM).
Keywords: automotive user interface; steering wheel; braille; keyer; chorded keyboard; acceptance; user studies
PermissionWatcher: Creating User Awareness of Application Permissions in Mobile Systems BIBAKFull-Text 65-80
  Eric Struse; Julian Seifert; Sebastian Üllenbeck; Enrico Rukzio; Christopher Wolf
Permission systems control access of mobile applications to other applications, data, and resources on a smartphone. Both from a technical and a social point of view, they are based on the assumption that users actually understand these permissions and hence they can make an informed decision about which permission to grant to which piece of software. Results of a survey conducted for this article seriously challenges this assumption. For instance, over a third of participating Android users were not able to correctly identify the meaning of the permission Full Internet Access. We developed PermissionWatcher, an Android application which provides users with awareness information about other applications and allows to check on the permission set granted to individual applications. In a field study with 1000+ Android users, we collected data that provides evidence that users are willing to follow security principles if security awareness is created and information is presented in a clear and comprehensive way. Therefore, we argue that it is essential for security policies to take the abilities of the target audience into account.
Keywords: Usable Security; Mobile Phones; Android; Access Rights
Exploring Non-verbal Communication of Presence between Young Children and Their Parents through the Embodied Teddy Bear BIBAKFull-Text 81-96
  Kaisa Väänänen-Vainio-Mattila; Tomi Haustola; Jonna Häkkilä; Minna Karukka; Katja Kytökorpi
Young children are emotionally dependant on their parents. Sometimes they have to be apart from each other, for example, when a parent is travelling. Current communication technologies are not optimal for supporting the feeling of presence. Our goal was to explore the design space for remote communication between young children (4-6 years) and their parents. More specifically, we aimed at gaining user feedback to a variety of non-verbal interaction modalities using augmented everyday objects. We developed the Teddy Bear concept and created an embodied mock-up that enables remote hugging based on vibration, presence indication, and communication of gestures. We conducted a user study with eight children and their parents. Our qualitative findings show that both children and parents appreciated Teddy Bear for its non-verbal communication features, but that some aspects were not easily understood, such as gestures for strong emotions. Based on our findings, we propose design implications for mediated presence between young children and their parents.
Keywords: Child-parent communication; presence; interaction modalities; embodied interaction; augmented everyday objects; concept design; user study
Automatic Behavior Understanding in Crisis Response Control Rooms BIBAKFull-Text 97-112
  Joris IJsselmuiden; Ann-Kristin Grosselfinger; David Münch; Michael Arens; Rainer Stiefelhagen
This paper addresses the problem of automatic behavior understanding in smart environments. Automatic behavior understanding is defined as the generation of semantic event descriptions from machine perception. Outputs from available perception modalities can be fused into a world model with a single spatiotemporal reference frame. The fused world model can then be used as input by a reasoning engine that generates semantic event descriptions. We use a newly developed annotation tool to generate hypothetical machine perception outputs instead. The applied reasoning engine is based on fuzzy metric temporal logic (FMTL) and situation graph trees (SGTs), promising and universally applicable tools for automatic behavior understanding. The presented case study is automatic behavior report generation for staff training purposes in crisis response control rooms. Various group formations and interaction patterns are deduced from person tracks, object information, and information about gestures, body pose, and speech activity.
Keywords: automatic behavior understanding; smart environments; rule-based expert systems; fuzzy metric temporal logic; situation graph trees
Combining Implicit and Explicit Methods for the Evaluation of an Ambient Persuasive Factory Display BIBAKFull-Text 113-128
  Ewald Strasser; Astrid Weiss; Thomas Grill; Sebastian Osswald; Manfred Tscheligi
Research in ambient intelligent systems faces a challenging endeavor, namely the evaluation of user experience of ambient displays. Due to the fact that ambient displays should be unobtrusive, it is hard for users to appraise them on a reflective level (i.e. interviews and questionnaires). In this paper we present a methodological approach that combines an implicit (the Affect Misattribution Procedure (AMP)) and an explicit measurement technique (questionnaire for the persuasive effect (PeQ)) to tackle this problem. We used this approach in a study of an interface (Operator Guide) that provides information to operators in a semiconductor factory. Results show that the implicit technique is better suited to assess fine attitudinal differences on how users experience the display than explicit questionnaires. However, explicit measures are valuable to gain suggestions for improvements and thus it is concluded that this method triangulation adds value for the research on ambient persuasive interfaces.
Keywords: Method triangulation; Methodology; implicit; Affect Misattribution Procedure; AMP; persuasion; ambient; automatic attitude
Context Awareness in Ambient Systems by an Adaptive Multi-Agent Approach BIBAKFull-Text 129-144
  Valérian Guivarch; Valérie Camps; André Péninou
In the field of ambient systems, the dynamic management of user context is needed to allow devices to be proactive in order to adapt to environmental changes and to assist the user in his activities. This proactive approach requires to take into account the dynamics and distribution of devices in the user's environment, and to have learning capabilities in order to adopt a satisfactory behaviour. This paper presents Amadeus, an Adaptive Multi-Agent System (AMAS), whose objective is to learn, for each device of the ambient system, the contexts for which it can anticipate the user's needs by performing an action on his behalf. This paper focuses on the Amadeus architecture and on its learning capabilities. It proposes some promising results obtained through various scenarios, including a comparison with the Multilayer Perceptron (MLP) algorithm.
Keywords: Context; evolution; adaptation; learning; ambient intelligence; self-organization
Towards Fuzzy Transfer Learning for Intelligent Environments BIBAKFull-Text 145-160
  Jethro Shell; Simon Coupland
By their very nature, Intelligent Environments (IE's) are infused with complexity, unreliability and uncertainty due to a combination of sensor noise and the human element. The quantity, type and availability of data to model these applications can be a major issue. Each situation is contextually different and constantly changing. The dynamic nature of the implementations present a challenging problem when attempting to model or learn a model of the environment. Training data to construct the model must be within the same feature space and have the same distribution as the target task data, however this is often highly costly and time consuming. There can even be occurrences were a complete lack of labelled target data occurs. It is within these situations that our study is focussed. In this paper we propose a framework to dynamically model IE's through the use of data sets from differing feature spaces and domains. The framework is constructed using a novel Fuzzy Transfer Learning (FuzzyTL) process.
   The use of a FuzzyTL algorithm allows for a source of labelled data to improve the learning of an alternative context task. We will demonstrate the application of an Fuzzy Inference System (FIS) to produce a model from a source Intelligent Environment (IE) which can provide the knowledge for a differing target context. We will investigate the use of FuzzyTL within differing contextual distributions through the use of temporal and spatial alternative domains.
Keywords: Fuzzy Logic; Transfer Learning; Intelligent Environments; Ambient Intelligence; Context-Aware
Gesture Profile for Web Services: An Event-Driven Architecture to Support Gestural Interfaces for Smart Environments BIBAKFull-Text 161-176
  Radu-Daniel Vatavu; Catalin-Marian Chera; Wei-Tek Tsai
Gestural interfaces have lately become extremely popular due to the introduction on the market of low-cost acquisition devices such as iPhone, Wii, and Kinect. Such devices allow practitioners to design, experiment, and evaluate novel interfaces and interactions for new smart environments. However, gesture recognition algorithms are currently the appanage of machine learning experts which sometimes leaves AmI practitioners dealing with complex pattern recognition techniques instead of focusing on prototyping ambient interactions. To address this problem, we propose GPWS (Gesture Profile for Web Services), a service-oriented architecture (SOA) designed to assist implementation of gestural interfaces. By providing gesture recognition as a web service, we leverage easy and fast adoption of gestural interfaces for various platforms and environments through simple service discovery and composition mechanisms. We discuss two GPWS designs based on SOA 1.0 and SOA 2.0 standards, analyze their performance, and demonstrate GPWS for a gesture-controlled smart home application.
Keywords: Gesture; gesture-based control; service-oriented computing; event-driven architecture; smart home; web services; gesture recognition; SOA; EDA
Using Markov Logic Network for On-Line Activity Recognition from Non-visual Home Automation Sensors BIBAKFull-Text 177-192
  Pedro Chahuara; Anthony Fleury; François Portet; Michel Vacher
This paper presents the application of Markov Logic Networks (MLN) for the recognition of Activities of Daily Living (ADL) in a smart home. We describe a procedure that uses raw data from non visual and non wearable sensors in order to create a classification model leveraging logic formal representation and probabilistic inference. SVM and Naive Bayes methods were used as baselines to compare the performance of our implementation, as they have proved to be highly efficient in classification tasks. The evaluation was carried out on a real smart home where 21 participants performed ADLs. Results show not only the appreciable capacities of MLN as a classifier, but also its potential to be easily integrable into a formal knowledge representation framework.
Keywords: Activity Recognition; Markov Logic Network; Support Vector Machine; Smart Home; Ambient Assisted Living
Multi-Classifier Adaptive Training: Specialising an Activity Recognition Classifier Using Semi-supervised Learning BIBAKFull-Text 193-207
  Bozidara Cvetkovic; Bostjan Kaluza; Mitja Lustrek; Matjaz Gams
When an activity recognition classifier is deployed to be used with a particular user, its performance can often be improved by adapting it to that user. To improve the classifier, we propose a novel semi-supervised Multi-Classifier Adaptive Training algorithm (MCAT) that uses four classifiers. First, the General classifier is trained on the labelled data available before deployment. Second, the Specific classifier is trained on a limited amount of labelled data specific to the new user in the current environment. Third, a domain-independent meta-classifier decides whether to classify a new instance with the General or Specific classifier. Fourth, another meta-classifier decides whether to include the new instance in the training set for the General classifier. The General classifier is periodically retrained, gradually adapting to the new user in the new environment where it is deployed. The results show that our new algorithm outperforms competing approaches and increases the accuracy of the initial activity recognition classifier by 12.66 percentage points on average.
Keywords: semi-supervised learning; adaptation to the user; MCAT; activity recognition
Sound Environment Analysis in Smart Home BIBAKFull-Text 208-223
  Mohamed A. Sehili; Benjamin Lecouteux; Michel Vacher; François Portet; Dan Istrate; Bernadette Dorizzi; Jérôme Boudy
This study aims at providing audio-based interaction technology that lets the users have full control over their home environment, at detecting distress situations and at easing the social inclusion of the elderly and frail population. The paper presents the sound and speech analysis system evaluated thanks to a corpus of data acquired in a real smart home environment. The 4 steps of analysis are signal detection, speech/sound discrimination, sound classification and speech recognition. The results are presented for each step and globally. The very first experiments show promising results be it for the modules evaluated independently or for the whole system.
Keywords: Smart Home; Sound Analysis; Sound Detection; Sound Recognition; Speech Distant Recognition
Contextual Wizard of Oz -- A Framework Combining Contextual Rapid Prototyping and the Wizard of Oz Method BIBAFull-Text 224-239
  Doris Zachhuber; Thomas Grill; Ondrej Polácek; Manfred Tscheligi
Exploring user interaction in specific contexts is often based on simulated environments and semi-functional prototypes of interactive systems. In this paper, we address a combination of context simulation with the Wizard of Oz (WOz) technique, where a hidden human "wizard" simulates missing functionalities and system intelligence. The goal of our work is to provide a software framework for fast prototyping and concurrent evaluation through user studies during iterative interaction design processes. Contextual interaction research is particularly challenging in high-dynamic interaction contexts like ambient environments and includes the simulation of various context parameters to elaborate interaction designs in the target context. For this purpose, we have developed a prototyping framework that allows the setup and handling of different contextual situations during user studies. The framework and the proposed WOz protocol, which is used for integrating the WOz technique, are highly flexible, modular and adjustable at runtime. This allows their application in a big variety of study contexts in in-situ and in-vitro settings. A detailed description of the framework's requirements and architecture as well as a user study, where we successfully applied our framework, are presented. First results have been collected through interviews with evaluators and developers who used the framework to develop the particular study setups. The identified improvements and potentials experienced during the usage of the framework have been analyzed and provide valuable findings for further iterations.
Recognizing the User Social Attitude in Multimodal Interaction in Smart Environments BIBAFull-Text 240-255
  Berardina De Carolis; Stefano Ferilli; Nicole Novielli
Ambient Intelligence aims at promoting an effective, natural and personalized interaction with the environment services. In order to provide the most appropriate answer to the user requests, an Ambient Intelligence system should model the user by considering not only the cognitive ingredients of his mental state, but also extra-rational factors such as affect, engagement, attitude, and so on. This paper describes a study aimed at building a multimodal framework for recognizing the social response of users during interaction with embodied agents in the context of ambient intelligence. In particular, we describe how we extended a model for recognizing the social attitude in text-based dialogs by adding two additional knowledge sources: speech and gestures. Results of the study show that these additional knowledge sources may help in improving the recognition of the users' attitude during interaction.
Evolutionary Feature Extraction to Infer Behavioral Patterns in Ambient Intelligence BIBAKFull-Text 256-271
  Leila Shila Shafti; Pablo A. Haya; Manuel García-Herranz; Eduardo Pérez
Machine learning methods have been applied to infer activities of users. However, the small number of training samples and their primitive representation often complicates the learning task. In order to correctly infer inhabitant's behavior a long time of observation and data collection is needed. This article suggests the use of MFE3/GADR, an evolutionary constructive induction method. Constructive induction has been used to improve learning accuracy through transforming the primitive representation of data into a new one where regularities are more apparent. The use of MFE3/GADR is expected to improve the representation of data and behavior learning process in an intelligent environment. The results of the research show that by applying MFE3/GADR a standard learner needs considerably less data to correctly infer user's behavior.
Keywords: Intelligent Environments; Behavioral Inference; Machine Learning; Genetic Algorithms; Constructive Induction; Feature Construction
Personalization of Content on Public Displays Driven by the Recognition of Group Context BIBAKFull-Text 272-287
  Ekaterina Kurdyukova; Stephan Hammer; Elisabeth André
Personalization of content on public displays relies on the knowledge of spectator interests and real-time recognition of social context. In busy public places, with numerous individuals circulating daily, the knowledge of individual interests becomes unrealistic. This paper presents an approach for automatic personalization which, instead of individual profiles, relies on group context. The system recognizes the constellation of spectators in front of a public display, based on their disposition and gender. Thus, the approach provides an important prerequisite for a completely automated personalization, requiring no input from the spectator side, neither for training, nor for real-time content adaptation. The experiment conducted in a public area showed that the presented approach can successfully identify the differences in the content observation of various groups. Moreover, the approach provides an insight into the diversity of circulating groups, and gives a hint about spectators' emotional and conversational response to the content.
Keywords: Public displays; Adaptation; Social Context

Short Papers

Towards the Generation of Assistive User Interfaces for Smart Meeting Rooms Based on Activity Patterns BIBAKFull-Text 288-295
  Michael Zaki; Peter Forbrig
The main purpose of a given smart meeting room is to increase the efficiency of the meetings taking place in this room by assisting the resident actors performing their tasks and thus offering them the opportunity to focus on the exchange of information among each other. However, a proper assistance should be based on a clear understanding of the nature of tasks the users are performing in the environment. Therefore, in this paper we present an attempt to base the design of the assistive system to be operated in smart meeting rooms on activity patterns collected in the analysis stage and resulting from the perception of the human behavior in those environments. The end goal is to tailor individualized user interfaces for each actor depending on his/her current role and user profile.
Keywords: smart meeting room; task model; team model; task pattern; precondition; post-condition; assistive user interface
Reducing Dementia Related Wandering Behaviour with an Interactive Wall BIBAKFull-Text 296-303
  Saskia Robben; Kyra Bergman; Sven Haitjema; Yannick de Lange; Ben J. A. Kröse
People suffering from dementia often have problems with way finding and feel restless. In this paper we present an interactive wall developed for decreasing the amount of wandering behaviour of people suffering from dementia. The installation aims at making these people feel more at home in the nursing homes by guiding them with a motion triggered audio path. This leads them to a wall with large windows displaying images and short movie tracks from their hometown. The results of an observation study show that the interactive wall succeeds in attracting people and thus reducing the wandering behaviour. Remarks of the elderly as well as their family and caretakers support this conclusion.
Keywords: Dementia; Wandering; Elderly People; Alzheimer; Interactive Wall
Gesture Based Semantic Service Invocation for Human Environment Interaction BIBAKFull-Text 304-311
  Carsten Stocklöw; Reiner Wichert
The assistance of users in their activities of daily life by a smart environment is the main goal of Ambient Assisted Living (AAL). In this case, interaction is of particular interest since some users are very familiar with modern technology and for some users this technology is very challenging so that poorly designed interaction metaphors will lead to a low acceptance. Additionally, AAL has to cope with the challenges of open systems in which at any time new devices and functionalities can appear. This paper presents a gesture based approach to control devices and their functionalities in a smart environment at a semantic level to issue a command or to set a level. Redundant functionalities are filtered out before presenting the list of functions to the user. This concept is validated by a demonstrator that uses the semantic AAL platform universAAL.
Keywords: Gesture based Interaction; Semantic Services; Ambient Assisted Living; Human Environment Interaction
Understanding Complex Environments with the Feedforward Torch BIBAKFull-Text 312-319
  Jo Vermeulen; Kris Luyten; Karin Coninx
In contrast with design flaws that occur in user interfaces, design flaws in physical spaces have a much higher cost and impact. Software is in fact fairly easy to change and update in contrast with legacy physical constructions where updating their physical appearance is often not an option. We present the Feedforward Torch, a mobile projection system that targets the augmentation of legacy hardware with feedforward information. Feedforward explains users what the results of their action will be, and can thus be seen as the opposite of feedback. A first user study suggests that providing feedforward in these environments could improve their usability.
Keywords: feedforward; intelligibility; mobile projection; legacy systems
Open Objects for Ambient Intelligence BIBAKFull-Text 320-327
  Paulo Ricca; Kostas Stathis
We present the Open Object, a framework for distributing capabilities over a system of inter-connected physical objects. We focus on allowing lightweight objects to not only share their capabilities with other objects but also to outsource capabilities when needed, in order to fulfil a user's goal. We exemplify our approach with a smart home scenario and a service-oriented implementation.
Keywords: Ubiquitous Computing; End-User Development; Events; Behaviours; Capabilities; Workflows; Service-Oriented Architecture

Landscape Papers

Towards Accessibility in Ambient Intelligence Environments BIBAKFull-Text 328-337
  George Margetis; Margherita Antona; Stavroula Ntoa; Constantine Stephanidis
This paper aims to set a landscape and elaborate a roadmap for accessible user interaction in AmI environments, including and beyond personal computational devices (PCs, mobiles, etc.), by identifying and addressing the new needs that emerge in the above context. This line of work is currently being pursued in the context of the AmI Research Programme of ICS-FORTH, and will be implemented in the new AmI Research Facility, which provides an ideal environment for developing the proposed solutions and a test-bed for validating them in a realistic simulation environment.
Keywords: ambient intelligence; accessibility; universal access; assistive technologies; personalized interaction; user model
INCOME -- Multi-scale Context Management for the Internet of Things BIBAFull-Text 338-347
  Jean-Paul Arcangeli; Amel Bouzeghoub; Valérie Camps; C. Marie-Françoise Canut; Sophie Chabridon; Denis Conan; Thierry Desprats; Romain Laborde; Emmanuel Lavinal; Sébastien Leriche; Hervé Maurel; André Péninou; Chantal Taconet; Pascale Zaraté
Nowadays, context management solutions in ambient networks are well-known. However, with the IoT paradigm, ambient information is not anymore the only source of context. Context management solutions able to address multiple network scales ranging from ambient networks to the Internet of Things (IoT) are required. We present the INCOME project whose goal is to provide generic software and middleware components to ease the design and development of mass market context-aware applications built above the Internet of Things. By revisiting ambient intelligence (AmI) context management solutions for extending them to the IoT, INCOME allows to bridge the gap between these two very active research domains. In this landscape paper, we identify how INCOME plans to advance the state of the art and we briefly describe its scientific program which consists of three main tasks: (i) multi-scale context management, (ii) management of extrafunctional concerns (quality of context and privacy), and (iii) autonomous deployment of context management entities.
New Forms of Work Assistance by Ambient Intelligence -- Overview of the Focal Research Topic of BAuA BIBAKFull-Text 348-355
  Armin Windel; Matthias Hartwig
Research and development in the area of AmI are currently migrating from basic technologies to application-readiness. In the consumer domain a field of research has now become established bearing the description Ambient Assisted Living. In contrast, for the area of work, practice-oriented and work science-relevant questions in the field of AmI are only considered in isolated cases and unsystematically. To capture the intersection of the world of work and the concept of AmI, the term adaptive work assistance systems (AWAS) is coined in this paper. Furthermore, the different research project bundles at BAuA are described briefly, each focusing on opportunities and risks of new I&C technologies in the working environment and their impact on work systems. Most of the projects are handled as BAuA's own research and supported by external research contracted extramurally.
Keywords: Ambient Intelligence; application in working life; adaptive work assistance systems; AWAS; work science; research programme
Living Labs as Educational Tool for Ambient Intelligence BIBAKFull-Text 356-363
  Ben J. A. Kröse; Mettina Veenstra; Saskia Robben; Marije Kanis
The way that innovation is currently done requires a new research methodology that enables co-creation and frequent, iterative evaluation in real-world settings. This paper describes the employment of the living lab methodology that corresponds to this need. Particularly, this paper presents the way that the Amsterdam University of Applies Sciences (HvA) incorporates living labs in its educational program with a particular focus on ambient intelligence. A number of examples are given to illustrate its place in the university's curriculum. Drawing on from this, problems and solutions are highlighted in a 'lessons learned' section.
Keywords: Ambient Intelligence; Living Labs; Education; participatory design
Intel Collaborative Research Institute -- Sustainable Connected Cities BIBAFull-Text 364-372
  Johannes Schöning; Yvonne Rogers; Jon Bird; Licia Capra; Julie A. McCann; David Prendergast; Charles Sheridan
Cities are places where people, meet, exchange, work, live and interact. They bring people with different interests, experiences and knowledge close together. They are the centres of culture, economic development and social change. They offer many opportunities to innovate with technologies, from the infrastructures that underlie the sewers to computing in the cloud. One of the overarching goals of Intel's Collaborative Research Institute on Sustainable Connected Cities is to integrate the technological, economic and social needs of cities in ways that are sustainable and human-centred. Our objective is to inform, develop and evaluate services that enhance the quality of living in the city.

Poster Papers

IE Sim -- A Flexible Tool for the Simulation of Data Generated within Intelligent Environments BIBAKFull-Text 373-378
  Jonathan Synnott; Liming Chen; Chris D. Nugent; George Moore
Availability of datasets generated by Intelligent Environments for the testing of new approaches may be limited due to constraints including time, space, and money. The use of simulated Intelligent Environments offers a method of creating datasets with maximum control and minimal costs and constraints. Such datasets facilitate the testing of novel approaches to areas such as activity recognition and ambient assisted living. IE Sim is a flexible feature-rich approach that supports graphical interactive construction and simulation of virtual Intelligent Environments This paper discusses the key features of IE Sim and discusses the results of a software evaluation performed by 21 international researchers with an interest in such datasets. Results from the evaluation rated IE Sim highly in terms of ease of use and usefulness in research and identified key requirements for future developments.
Keywords: Data Simulation; Virtual Environment Creation; Virtual Sensors; Intelligent Environments; Environment Prototyping
Intention Recognition with Clustering BIBAKFull-Text 379-384
  Fariba Sadri; Weikun Wang; Afroditi Xafi
Intention recognition has significant applications in ambient intelligence, assisted living and care of the elderly, amongst others. In this paper we explore an approach to intention recognition based on clustering. To this end we show how to map the intention recognition problem into a clustering problem. To our knowledge the use of clustering techniques for intention recognition is novel, and this paper suggests it is promising.
Keywords: Intention recognition; clustering; Fuzzy C-means
Behavior Modeling and Recognition Methods to Facilitate Transitions between Application-Specific Personalized Assistance Systems BIBAKFull-Text 385-390
  Arun Ramakrishnan; Zubair Bhatti; Davy Preuveneers; Yolande Berbers; Aliaksei Andrushevich; Rolf Kistler; Alexander Klapproth
Activity recognition mandates complex sensor fusion processing. Many contributions in the literature focus on improving the recognition accuracy of a limited set of activities or the efficiency of the algorithms. However, there is little work on how to dynamically adapt the activity recognition techniques when evolving from one situation to the next. We present tool support to model transitions between activities, and a modular distributed framework of human activity recognition components with support for analyzing resource and recognition trade-offs for different deployments and configurations.
Keywords: Behavior and activity recognition; smart home and health
LumaFluid: A Responsive Environment to Stimulate Social Interaction in Public Spaces BIBAFull-Text 391-396
  Gianluca Monaci; Tommaso Gritti; Martine van Beers; Ad Vermeulen; Bram Nab; Inge Thomassen; Marigo Heijboer; Sandra Suijkerbuijk; Wouter Walmink; Maarten Hendriks
LumaFluid is an interactive environment that explores new ways to stimulate emotional and social engagement through light. A vision system localizes people present in the LumaFluid square. Colored spotlights highlight each person and connections are drawn between neighboring visitors to underline and stimulate interpersonal communication. Two versions of the concept where deployed during the 2011 STRP Festival. In this paper we describe the conception and realization of the installation, and we discuss the insights collected during the event.
A Cost-Based Model for Service Discovery in Smart Environments BIBAKFull-Text 397-402
  Michele Girolami; Francesco Furfari; Stefano Chessa
This paper describes the CoDA algorithm for the service discovery in the Smart Environments. CoDA is based on the energy distance metric that allows the clients to select the service providers whose access cost is the lowest in terms of the energy requirements.
Keywords: service discovery; Smart Environments; energy efficiency
On the Use of Video Prototyping in Designing Ambient User Experiences BIBAFull-Text 403-408
  Nikolaos Batalas; Hester Bruikman; Annemiek van Drunen; He Huang; Dominika Turzynska; Vanessa Vakili; Natalia Voynarovskaya; Panos Markopoulos
We discuss a case study where this technique was used in the design of an ambient intelligence system, highlighting how it impacted the design process both in positive and negative ways. This contextualized account complements related comparative studies that have been conducted outside the context of a design project, and have focused on methodological aspects of video prototyping. We conclude that designers need to be aware of how video as a persuasive medium obfuscates implementation and usability issues, and video prototype production should communicate explicitly the scope of the design issues that it addresses and those it does not.
Automatic Power-Off for Binaural Hearing Instruments BIBAKFull-Text 409-414
  Bernd Tessendorf; Peter Derleth; Manuela Feilner; Daniel Roggen; Thomas Stiefmeier; Gerhard Tröster
Users of state-of-the-art hearing instruments (HIs) switch their devices on and off by closing and opening the battery compartment. Switching the HIs off is important for the users to maintain the battery lives of their HIs. However, users currently need to switch off their devices manually, which is easy to forget or which can be difficult, e.g. for elderly with reduced dexterity. In this work, we propose an approach to avoid the need to manually switch off HIs. We assume, that whenever the user's HIs are not moved the same way, they cannot be at the user's ear and are, thus, not in use. We exploit the binaural communication between the user's HIs available in the latest generation of HIs together with the concept of multimodal HIs, which integrates sensors such as accelerometers. On a data set of one hour comprising acceleration data of two HIs worn by three male participants (age 26-31) we achieve a precision of 100% and a recall of 93% in detecting power-off events.
Keywords: hearing instruments; human computer interaction (HCI); multimodal sensing
Proposal and Demonstration of Equipment Operated by Blinking BIBAKFull-Text 415-420
  Masaki Kato; Tatsuya Kobori; Takayuki Suzuki; Shigenori Ioroi; Hiroshi Tanaka
This paper describes a new input method that makes use of eyelid blinking. We found that the electromyographic (EMG) signal generated by blinking can be detected using a commercially available brain sensor. Since it is impossible to distinguish between voluntary and involuntary blinks, we propose setting a specific time duration between eyelid closing and opening. This duration can be used as a trigger for signal generation and at the same time for selection of a particular operation. The blink pattern is interpreted as a signal pattern for operation and corresponding commands are assigned for the operation selected. We built a demonstration system to evaluate the proposed method. The validity of the method and the effectiveness of the system were confirmed by the experiment using the system.
Keywords: Blink; EMG signal; Brain sensor; Signal generation; Equipment operation
CASi -- A Generic Context Awareness Simulator for Ambient Systems BIBAKFull-Text 421-426
  Jörg Cassens; Felix Schmitt; Tobias Mende; Michael Herczeg
In this paper, we present CASi (Context Awareness Simulator), a software system for the simulation of context-aware computer systems and environments. CASi provides an abstract framework of components for simulating smart world applications like a smart office or house with ambient sensors and actuators. Agents moving through these application worlds are tracked by sensors and their actions are influenced by actuators, both of which can be programmed to resemble the actual peripherals of the tested system. CASi allows testing ambient, context aware computer systems even in early stages of development without the need for expensive prototyping or real world deployment.
Keywords: Ubiquitous computing; ambient intelligence; context; simulation
A Conceptual Framework for Supporting Adaptive Personalized Help-on-Demand Services BIBAKFull-Text 427-432
  William Burns; Liming Chen; Chris D. Nugent; Mark P. Donnelly; Kerry-Louise Skillen; Ivar Solheim
Mobile applications that encompass personalization and context-aware components are increasingly becoming more prevalent. The ability to offer personalized content and User Interfaces to the users of these applications, however, has still not been fully addressed. In this paper we describe a conceptual framework that establishes a User Profile and aims to monitor the usage patterns of users of a mobile application and, based on these patterns, provide both personalized, context aware content and user interfaces. The framework consists of four components that together contribute towards an overall Help on Demand service that is targeted at older age Smartphone users. A usage scenario is presented to describe the typical usage of the help on demand service.
Keywords: context-aware services; adaptive personalization; smartphone applications

Demo Papers

Developing Touchless Interfaces with GestIT BIBAKFull-Text 433-438
  Lucio Davide Spano
In this paper, we report on the development of touchless interfaces for supporting long lasting tasks, which need an interleaving between the interaction with the system and the focus on other activities. As an example, we considered a dish cooking task, which enables selecting and browsing the information about different recipes while cooking through gestural and vocal interaction. The application demonstrates the advantages offered by the GestIT library, which allows a declarative and compositional definition of reusable gestures.
Keywords: Touchless interfaces; Input and Interaction Technologies; Gestural Interaction; Ambient Intelligence
Tool Support for Probabilistic Intention Recognition Using Plan Synthesis BIBAFull-Text 439-444
  Frank Krüger; Kristina Yordanova; Thomas Kirste
To provide assistance in intelligent environments it is necessary to accurately infer the users needs and wishes. In this demonstration we present a probabilistic plan recognition system that is able to track the user and to compare different hypotheses about the users behavior and her goal(s) based on observations of the current activity. Furthermore, the tool provides a probability distribution over the possible goals and selects the most probable hypothesis as the user intention.


Aesthetic Intelligence: The Role of Design in Ambient Intelligence BIBAKFull-Text 445-446
  Carsten Röcker; Kai Kasugai; Daniela Alina Plewe; Takashi Kiriyama; Artur Lugmayr
This paper illustrates the rationale behind the second international workshop on Aesthetic Intelligence. The workshop addresses the multiple facets of aesthetics in the design process of Ambient Intelligence technologies, especially in the fields of architecture, industrial and interface design as well as human-computer interaction.
Keywords: Ambient Intelligence; Ubiquitous Computing; Smart Spaces; Aesthetics; Design; Architecture; Urban Informatics
Workshop on Ambient Intelligence Infrastructures (WAmIi) BIBAKFull-Text 447-448
  Alina Weffers; Johan Lukkien; Tanir Ozcelebi
The last two decades have seen a significant amount of results and insights that promote the Ambient Intelligence vision, in particular via the architecture and design of Ambient Intelligence infrastructures supporting interconnected, context aware, personalized devices and services to act as an interactive and intelligent environment. We propose a workshop that would facilitate a systematic overview of the results achieved and work currently done in the context of European projects on the topic. The goal is to identify the white spaces in the domain, and thereby prepare the ground for further work, to be built on thorough understanding of the state-of-the-art.
Keywords: Ambient Intelligence infrastructures; middleware
Sixth International Workshop on Human Aspects in Ambient Intelligence (HAI 2012) BIBAFull-Text 449-450
  Juan Carlos Augusto; Tibor Bosse; Cristiano Castelfranchi; Diane J. Cook; Mark A. Neerincx; Fariba Sadri
Recent developments within Ambient Intelligence (AmI) provide new possibilities to contribute to personal care. For example, our car may monitor us and warn us when we are falling asleep while driving or take measures when we are too drunk to drive. As another example, an elderly person may wear a device that monitors his or her wellbeing and offers support when a dangerous situation is noticed. Such applications can be realised partly because of advances in acquiring sensor information about humans and their functioning. However, their full realisation depends crucially on the availability of adequate knowledge for analysis of such information about human functioning. If such knowledge about human functioning is computationally available within devices in the environment, these systems can show more human-like understanding and contribute to personal care based on this understanding [1].
Context-Aware Adaptation of Service Front-Ends BIBAFull-Text 451-452
  Francisco Javier Caminero Gil; Fabio Paternò; Jean Vanderdonckt
Ambient Intelligence implies the need for context-aware adaptation of user interfaces. This adaptation with respect to the context of use is applicable to a wide spectrum of interactive applications ranging from front ends of web services, information systems to multimedia and multimodal applications. Although the ultimate goal of this adaptation is always for the ultimate benefit of the end user, many approaches and techniques have been used to various degrees of experience and maturity that effectively and efficiently support context-aware adaptation. This workshop is intended to review the state of the art in this domain, while looking at a broad range of applications, to discuss positive and negative experiences of context-aware adaptation, and to come up with criteria and requirements for driving such adaptation.
2nd International Workshop on Ambient Gaming BIBAKFull-Text 453-454
  Janienke Sturm; Pepijn Rijnbout; Ben A. M. Schouten
Ambient games are games and playful activities that offer context-aware and personalized features. Because ambient play and games can be incorporated in everyday objects and routines, they allow players to play throughout the day. Ambient gaming offers promising opportunities for creating novel and unique player experiences. However, there are still many unanswered questions related to this new field of research, for instance related to gamification, personalisation and adaptation, aspects and issues of control and privacy. In this 2nd workshop on Ambient Gaming we intend to further discuss the opportunities and challenges in the field of ambient gaming and play with people from different disciplines (designers, researchers, and developers) who are active in this field.
Keywords: Ambient Gaming; Playful Interactions; Design; Ambient Technology
Designing Persuasive Interactive Environments BIBAKFull-Text 455-456
  Marco M. C. Rozendaal; Aadjan van der Helm; Walter A. Aprile; Arnold P. O. S. Vermeeren; Tilde Bekker; Marije Kanis; Wouter Middendorf
Ambient Intelligent environments are interactive environments that can sense human behaviour and can respond intelligently. This workshop explores how interactive environments can be designed with persuasive quality, hereby influencing human experience and behaviour. The workshop follows a research-through-design approach in which practise-relevant insights are gained while designing. The focus will be on intuitive and rational decision-making, the role of aesthetics in persuasion, social and spatial influences as well as technological influences on persuasion, evaluation methods for persuasion, and the ethics of designing for persuasion.
Keywords: Ambient intelligence; persuasion; aesthetics; decision-making research-through-design; interactive prototyping
Applying AmI Technologies to Crisis Management -- Workshop at AmI2012 BIBAKFull-Text 457-458
  Monica Divitini; Babak A. Farshchian; Jacqueline Floch; Ragnhild Halvorsrud; Simone Mora; Michael Stiso
The workshop aims to bring together researchers and practitioners working on the application of AmI to crisis and disaster management. Because of their pervasiveness and ease of use, AmI technologies hold a great potential to support crisis management in an efficient and effective way. Focus will be on better understanding (1) the strengths of the AmI paradigm, (2) challenges to its application, and (3) its potential in the development of innovative solutions. The workshop is open to papers from different standpoints, including platform and user interaction issues, methodological approaches, and specific applications.
Keywords: Ambient Intelligence; Crisis Management; innovative AmI solutions