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

Proceedings of the 2010 International Joint Conference on Ambient Intelligence

Fullname:AmI 2010: First International Joint Conference on Ambient Intelligence
Editors:Boris de Ruyter; Reiner Wichert; David V. Keyson; Panos Markopoulos; Norbert Streitz; Monica Divitini; Nikolaos Georgantas; Antonio Mana Gomez
Location:Malaga, Spain
Dates:2010-Nov-10 to 2010-Nov-12
Publisher:Springer Berlin Heidelberg
Series:Lecture Notes in Computer Science 6439
Standard No:DOI: 10.1007/978-3-642-16917-5 hcibib: AmI10; ISBN: 978-3-642-16916-8 (print), 978-3-642-16917-5 (online)
Papers:47
Pages:354
Links:Online Proceedings | Conference Home Page
Automating Routine Tasks in AmI Systems by Using Models at Runtime BIBAKFull-Text 1-10
  Estefanía Serral; Pedro Valderas; Vicente Pelechano
One of the most important challenges to be confronted in Ambient Intelligent (AmI) systems is to automate routine tasks on behalf of users. In this work, we confront this challenge presenting a novel approach based on models at runtime. This approach proposes a context-adaptive task model that allows routine tasks to be specified in an understandable way for users, facilitating their participation in the specification. These tasks are described according to context, which is specified in an ontology-based context model. Both the context model and the task model are also used at runtime. The approach provides a software infrastructure capable of automating the routine tasks as they were specified in these models by interpreting them at runtime.
Keywords: task modelling; routine task automation; models at runtime; OSGi
Service Obtrusiveness Adaptation BIBAKFull-Text 11-20
  Miriam Gil; Pau Giner; Vicente Pelechano
Increasingly, mobile devices play a key role in the communication between users and the services embedded in their environment. All these services compete for the attentional resources of the user. Thus, it is essential to consider the degree in which each service intrudes the user mind (i.e., the obtrusiveness level) when services are designed. In this work we introduce a method for the development of mobile services that can be adapted in terms of obtrusiveness. That is, services can be developed to provide their functionality at different obtrusiveness levels by minimizing the duplication of efforts. In order to define the obtrusiveness level adaptation in a declarative manner we make use of Feature Modeling techniques. An experiment was conducted in order to put in practice the proposal and evaluate the user acceptance for the way in which services are presented.
Keywords: Obtrusiveness adaptation; feature modeling; interaction adaptation
A Dynamic Time Warping Approach to Real-Time Activity Recognition for Food Preparation BIBAFull-Text 21-30
  Cuong Pham; Thomas Plötz; Patrick Olivier
We present a dynamic time warping based activity recognition system for the analysis of low-level food preparation activities. Accelerometers embedded into kitchen utensils provide continuous sensor data streams while people are using them for cooking. The recognition framework analyzes frames of contiguous sensor readings in real-time with low latency. It thereby adapts to the idiosyncrasies of utensil use by automatically maintaining a template database. We demonstrate the effectiveness of the classification approach by a number of real-world practical experiments on a publically available dataset. The adaptive system shows superior performance compared to a static recognizer. Furthermore, we demonstrate the generalization capabilities of the system by gradually reducing the amount of training samples. The system achieves excellent classification results even if only a small number of training samples is available, which is especially relevant for real-world scenarios.
Refining Interaction Designs through Simplicity BIBAKFull-Text 31-40
  Pablo Muñoz; Pau Giner; Vicente Pelechano
With more and more devices in our surroundings, users increasingly-consume applications and digital services which compete for their attention. Therefore, users appreciate simplicity when they interact with them because a less intrusive interaction allows users focus on the task at hand. This work relates an approach based on the concept of simplicity. We propose an iterative interaction design process in which we include a new role. This role is only in charge of providing simplified solutions from original designs. Moreover, we put on practice our proposal in a case study in which we design an application to support mobile workflows. We relate our experience and how new ideas were produced towards the definition of refactored interactions by means of the key of Simplicity.
Keywords: interaction; simplicity; mobile devices; user-centered design
Semantic Visualization of Wireless Sensor Networks for Elderly Monitoring BIBAKFull-Text 41-50
  Carsten Stocklöw; Felix Kamieth
In the area of Ambient Intelligence, Wireless Sensor Networks are commonly used for user monitoring purposes like health monitoring and user localization. Existing work on visualization of wireless sensor networks focuses mainly on displaying individual nodes and logical, graph-based topologies. This way, the relation to the real-world deployment is lost. This paper presents a novel approach for visualization of wireless sensor networks and interaction with complex services on the nodes. The environment is realized as a 3D model, and multiple nodes, that are worn by a single individual, are grouped together to allow an intuitive interface for end users. We describe application examples and show that our approach allows easier access to network information and functionality by comparing it with existing solutions.
Keywords: Wireless Sensor Network; Semantic Visualization; Elderly Care
Privacy Management and Control in ATRACO BIBAKFull-Text 51-60
  Bastian Könings; Björn Wiedersheim; Michael Weber
Privacy is a critical factor for the acceptance and success of next generation ambient intelligent environments. Those environments often act autonomously to support a user's activity based on context information gathered from ubiquitous sensors. The autonomous nature and their accessibility to large amount of personal information raises several privacy issues for participants in such environments. Those issues need to be addressed by adequate privacy mechanisms. In this paper we present an overview of the ATRACO approach to provide privacy management and control in an ambient intelligent environment.
Keywords: privacy; ambient intelligence; ubiquitous computing
Place in Perspective: Extracting Online Information about Points of Interest BIBAFull-Text 61-72
  Ana O. Alves; Francisco C. Pereira; Filipe Rodrigues; João Oliveirinha
During the last few years, the amount of online descriptive information about places has reached reasonable dimensions for many cities in the world. Being such information mostly in Natural Language text, Information Extraction techniques are needed for obtaining the meaning of places that underlies these massive amounts of commonsense and user made sources. In this article, we show how we automatically label places using Information Extraction techniques applied to online resources such as Wikipedia, Yellow Pages and Yahoo!.
AmbiSec: Securing Smart Spaces Using Entropy Harvesting BIBAFull-Text 73-85
  Paolo Barsocchi; Stefano Chessa; Ivan Martinovic; Gabriele Oligeri
Following the vision of Ambient Intelligence (AmI), this paper introduces and evaluates a novel security scheme that takes the advantage of the unpredictable and erratic behavior of wireless communication to generate secret keys. The main advantage is that the secret key generation is applicable to every wireless device, independently of their hardware characteristics as it only requires a wireless interface and a human movement, which inherently affects the signal propagation within the physical environment. To analyze the applicability of this scheme, we implement and systematically evaluate the key generation using a wireless sensor network deployed in a real-world scenario. The analysis clarifies how different factors influence the amount of randomness collected from the physical environment, and it also shows that guessing attacks from an eavesdropper are negligible even if it is able to eavesdrop the complete wireless communication.
Taxi-Aware Map: Identifying and Predicting Vacant Taxis in the City BIBAFull-Text 86-95
  Santi Phithakkitnukoon; Marco Veloso; Carlos Bento; Assaf Biderman; Carlo Ratti
Knowing where vacant taxis are and will be at a given time and location helps the users in daily planning and scheduling, as well as the taxi service providers in dispatching. In this paper, we present a predictive model for the number of vacant taxis in a given area based on time of the day, day of the week, and weather condition. The history is used to build the prior probability distributions for our inference engine, which is based on the naïve Bayesian classifier with developed error-based learning algorithm and method for detecting adequacy of historical data using mutual information. Based on 150 taxis in Lisbon, Portugal, we are able to predict for each hour with the overall error rate of 0.8 taxis per 1x1 km2 area.
Dynamic Privacy Management in Pervasive Sensor Networks BIBAKFull-Text 96-106
  Nan-Wei Gong; Mathew Laibowitz; Joseph A. Paradiso
This paper describes the design and implementation of a dynamic privacy management system aimed at enabling tangible privacy control and feedback in a pervasive sensor network. Our work began with the development of a potentially invasive sensor network (with high resolution video, audio, and motion tracking capabilities) featuring different interactive applications that created incentive for accepting this network as an extension of people's daily social space. A user study was then conducted to evaluate several privacy management approaches -- an active badge system for both online and on-site control, on/off power switches for physically disabling the hardware, and touch screen input control. Results from a user study indicated that an active badge for on-site privacy control is the most preferable method among all provided options. We present a set of results that yield insight into the privacy/benefit tradeoff from various sensing capabilities in pervasive sensor networks and how privacy settings and user behavior relate in these environments.
Keywords: dynamic privacy management; ubiquitous computing; active badge system; pervasive sensor networks
Geo-Social Interaction: Context-Aware Help in Large Scale Public Spaces BIBAKFull-Text 107-116
  Nasim Mahmud; Petr Aksenov; Ansar-Ul-Haque Yasar; Davy Preuveneers; Kris Luyten; Karin Coninx; Yolande Berbers
We present an approach to exploit social and spatio-temporal context in order to improve information dissemination in dynamic large-scale public spaces. We illustrate it by applying a proposed measure of geo-social relevance of each individual in a simulated vehicular network and by comparing the performance of different network message passing techniques in an inter-vehicle 'help-me-best-and-do-it-fast' communication scenario. We conclude that the use of social networking capabilities of an individual combined with knowledge about their spatio-temporal context information significantly improves purposeful interaction between individuals in terms of both the efficiency of the network data dissemination and the quality of the delivered information.
Keywords: Social network; FOAF; Context awareness; Location awareness; Information dissemination
The Operator Guide: An Ambient Persuasive Interface in the Factory BIBAKFull-Text 117-126
  Alexander Meschtscherjakov; Wolfgang Reitberger; Florian Pöhr; Manfred Tscheligi
In this paper we introduce the context of a semiconductor factory as a promising area for the application of innovative interaction approaches. In order to increase efficiency ambient persuasive interfaces, which influence the operators' behaviour to perform in an optimized way, could constitute a potential strategy. We present insights gained from qualitative studies conducted in a specific semiconductor factory and provide a description of typical work processes and already deployed interfaces in this context. These findings informed the design of a prototype of an ambient persuasive interface within this realm -- the "Operator Guide". Its overall aim is to improve work efficiency, while still maintaining a minimal error rate. We provide a detailed description of the Operator Guide along with an outlook of the next steps within a user-centered design approach.
Keywords: factory; ethnography; UCD; ambient persuasion
Reduction of Driver Stress Using AmI Technology while Driving in Motorway Merging Sections BIBAKFull-Text 127-137
  Kashif Zia; Andreas Riener; Alois Ferscha
High average intensity of traffic and problems like traffic congestions, road safety, etc. are challenging problems striking highway operators in these days. With the broad application of intelligent transport systems (ITS), particularly for the most dense street sections, some of these problems can be minimized or even solved; supplementary great potential is attributed to applications based on state-of-the art technology like car-to-x communication, for instance by extending an individuals "field of vision" by observations taken from all the vehicles in front. In this work we present a simulation based approach for improving driving experience and increasing road safety in merging sections by redirecting vehicles in advance according to a negotiation of requirements and desires of the flowing traffic on the main road and cars merging from the entrance lane. The simulation experiments performed in a cellular automaton based environment were data driven and on real scale, using traffic flow data on a minute-by-minute basis from a large urban motorway in a main city of the European Union. Our results have shown that the application of AmI technology has potential to influence driver's behavior (seamlessly invoking for a lane change well before an abrupt merging point) resulting in a reduction of panic, particularly for sections with limited range of view.
Keywords: Data driven simulation; Driver assistance; Motorway merging; Field of view extension; Vibro-tactile seat; Safety belt interface
Subjective Difficulty Estimation for Interactive Learning by Sensing Vibration Sound on Desk Panel BIBAKFull-Text 138-147
  Nana Hamaguchi; Keiko Yamamoto; Daisuke Iwai; Kosuke Sato
In this paper, we propose a method which estimates the student's subjective difficulty with a vibration sound on a desk obtained by a microphone on the back of the desk panel. First, it classifies the student's behavior into writing and non-writing by analyzing the obtained sound data. Next, the subjective difficulty is estimated based on an assumption that the duration of non-writing behavior becomes long if the student feels difficult because he (or she) would not have progress on answer sheet. As a result, the accuracy of the proposed so simple behavior classification reaches around 80%, and that of the subjective difficulty estimation is 60%.
Keywords: subjective difficulty estimation; behavior classification
Ontology Driven Piecemeal Development of Smart Spaces BIBAKFull-Text 148-156
  Eila Ovaska
Software development is facing new challenges due to transformation from product based software engineering towards integration and collaboration based software engineering that embodies high degree of dynamism both at design time and run time. Short time-to-markets require cost reduction by maximizing software reuse; openness for new innovations presumes a flexible innovation platform and agile software development; and user satisfaction assumes high quality in a situation based manner. How to deal with these contradictory requirements in software engineering? The main contribution of this paper is a novel approach that is influenced by business innovation, human centered design, model driven development and ontology oriented design. The approach is called Ontology driven Piecemeal Software Engineering (OPSE). OPSE facilitates incremental software development based on software pieces that follow the design principles defined by means of ontologies. Its key elements are abstraction, aggregation and adaptivity. The approach is intended for and applied to the development of smart spaces.
Keywords: smart space; ontology; context awareness; interoperability; MDD
Exploiting Acoustic Source Localization for Context Classification in Smart Environments BIBAKFull-Text 157-166
  Christian Kleine-Cosack; Marius H. Hennecke; Szilárd Vajda; Gernot A. Fink
Smart environments rely on context classification in order to be able to support users in their daily lives. Therefore, measurements provided by sensors distributed throughout the environment are analyzed. A main drawback of the solutions proposed so far is that the type of sensors and their placement often needs to be specifically adjusted to the problem addressed. Instead, we propose to perform context classification based on the analysis of acoustic events, which can be observed using arrays of microphones. Consequently, the sensor setup can be kept rather general and a wide range of contexts can be discriminated. In an experimental evaluation within a smart conference room we demonstrate the advantages of our new approach.
Keywords: Context classification; audio localization; smart rooms
Real-Time Gaze Tracking for Public Displays BIBAFull-Text 167-176
  Andreas Sippl; Clemens Holzmann; Doris Zachhuber; Alois Ferscha
In this paper, we explore the real-time tracking of human gazes in front of large public displays. The aim of our work is to estimate at which area of a display one ore more people are looking at a time, independently from the distance and angle to the display as well as the height of the tracked people. Gaze tracking is relevant for a variety of purposes, including the automatic recognition of the user's focus of attention, or the control of interactive applications with gaze gestures. The scope of the present paper is on the former, and we show how gaze tracking can be used for implicit interaction in the pervasive advertising domain. We have developed a prototype for this purpose, which (i) uses an overhead mounted camera to distinguish four gaze areas on a large display, (ii) works for a wide range of positions in front of the display, and (iii) provides an estimation of the currently gazed quarters in real time. A detailed description of the prototype as well as the results of a user study with 12 participants, which show the recognition accuracy for different positions in front of the display, are presented.
An Agent-Based Approach to Care in Independent Living BIBAKFull-Text 177-186
  Bostjan Kaluza; Violeta Mirchevska; Erik Dovgan; Mitja Lustrek; Matjaz Gams
This paper presents a multi-agent system for the care of elderly people living at home on their own, with the aim to prolong their independence. The system is composed of seven groups of agents providing a reliable, robust and flexible monitoring by sensing the user in the environment, reconstructing the position and posture to create the physical awareness of the user in the environment, reacting to critical situations, calling for help in the case of an emergency, and issuing warnings if unusual behavior is detected. The system has been tested during several on-line demonstrations.
Keywords: Multi-agent system; fall detection; disability detection; independent living; remote care
Making AAL Platforms a Reality BIBAKFull-Text 187-196
  Antonio Kung; Bruno Jean-Bart
This paper takes the position that the advent of Ambient Assisted Living (AAL) depends on the availability of an ecosystem based on widely accepted mainstream platforms supporting AAL domain specific interfaces. It describes the features which such platforms must meet, based on the experience of the MonAMI project. It identifies challenges concerning the standardisation of application specific interfaces, and their support by platforms. It finally suggests two measures that will help make such platforms a reality: first, the launching of a research and industry initiative for an open source platform; secondly, the launching of a EC policy supported long-term process for the adoption of AAL standards.
Keywords: AmI; AAL; Platform; Applications; Policies; Standards
A Unified Architecture for Supporting Direct Tag-Based and Indirect Network-Based Resource Discovery BIBAFull-Text 197-206
  Simone Mora; Babak A. Farshchian
Discovering and integrating ambient computational resources is a central topic in AmI. There are two major existing approaches: indirect network-based resource selection and direct tag-based resource identification. We motivate the need to integrate the two approaches through a scenario. We then present an architecture for a pluggable discovery system called UbiDisco. We demonstrate how UbiDisco implements a seamless integration of the two approaches at user interaction level through a framework for implementing discovery actions.
Multilevel and Hybrid Architecture for Device Abstraction and Context Information Management in Smart Home Environments BIBAKFull-Text 207-216
  Víctor Peláez; Roberto González; Luis Ángel San Martín; Antonio M. Campos; Vanesa Lobato
Hardware device management, and context information acquisition and abstraction are key factors to develop the ambient intelligent paradigm in smart homes. This work presents an architecture that addresses these two problems and provides a usable framework to develop applications easily. In contrast to other proposals, this work addresses performance issues specifically. Results show that the execution performance of the developed prototype is suitable for deployment in a real environment. In addition, the modular design of the system allows the user to develop applications using different techniques and different levels of abstraction.
Keywords: smart home; middleware; frameworks
A Distributed Many-Camera System for Multi-person Tracking BIBAFull-Text 217-226
  Claus Lenz; Thorsten Röder; Martin Eggers; Sikandar Amin; Thomas Kisler; Bernd Radig; Giorgio Panin; Alois Knoll
This article presents a modular, distributed and scalable many-camera system designed towards tracking multiple people simultaneously in a natural human-robot interaction scenario set in an apartment mock-up. The described system employs 40 high-resolution cameras networked to 15 computers, redundantly covering an area of approximately 100 square meters. The unique scale and set-up of the system require novel approaches for vision-based tracking, especially with respect to the transfer of targets between the different tracking processes while preserving the target identities. We propose an integrated approach to cope with these challenges, and focus on the system architecture, the target information management, the calibration of the cameras and the applied tracking methodologies themselves.
An Open Distributed Framework for Adaptive User Interaction in Ambient Intelligence BIBAFull-Text 227-238
  Mohammad-Reza Tazari
Challenges of handling user interaction in Ambient Intelligence environments are manifold. The systems installed in these environments are highly distributed with dynamic configurations in terms of integrated devices and installed applications. Context-awareness, personalization, and multimodality are critical for supporting more natural interaction and optimizing the interaction in an adaptive way. Research activities have dealt with different specific problems in the field and now it is high time for moving towards an open framework with a more comprehensive solution. This paper introduces results of such work with a high level of freedom in developing and deploying applications without needing to care about the available I/O infrastructure. The other way around, the latter can be changed without worrying about the application side. The independence of applications from the available I/O infrastructure helps to share mechanisms and manage such a complex scene more adequately. The key idea behind this framework is the natural distribution of tasks according to the real scene using a middleware solution supporting seamless connectivity and goal-based interoperability.
A Vision-Based System for Object Identification and Information Retrieval in a Smart Home BIBAKFull-Text 239-247
  Raphael Grech; Dorothy Ndedi Monekosso; Deon de Jager; Paolo Remagnino
This paper describes a hand held device developed to assist people to locate and retrieve information about objects in a home. The system developed is a standalone device to assist persons with memory impairments such as people suffering from Alzheimer's disease. A second application is object detection and localization for a mobile robot operating in an ambient assisted living environment. The device relies on computer vision techniques to locate a tagged object situated in the environment. The tag is a 2D color printed pattern with a detection range and a field of view such that the user may point from a distance of over 1 meter.
Keywords: Smart home; object detection and recognition
SeSaMoNet 2.0: Improving a Navigation System for Visually Impaired People BIBAKFull-Text 248-253
  Ugo Biader Ceipidor; Carlo Maria Medaglia; Eliseo Sciarretta
The authors present the improvements obtained during the work done for the last installation of SeSaMoNet, a navigation system for blind people. First the mobility issues of visually impaired people are shown together with strategies to solve them. Then an overview of the system and of its main elements is given. Afterward, the reasons which brought to a re-design are explained and finally the main features of the last system revision for the application are presented and compared to the previous one.
Keywords: accessibility; navigation; RFId; blind; visually impaired; mobility
Plugin Driven Architecture for Intelligent Management of Building BIBAKFull-Text 254-258
  Alessandro Olivi; Roberto Borsini; Alessandro Bastari
In the present work an innovative solution based on a middleware framework is introduced which simplifies the modeling of a software for intelligent management of buildings and allows a multistandard and multiprotocol integration of sensors and actuators. The adopted programming methodology has never been used in the implementation of a BA system and makes it possible to overcome some limitations of traditional approaches, such as the hard integration of new interfaces and protocols. The results of the framework application in a residential building proves the validity of the proposed solution.
Keywords: Model Driven Architecture; Building Automation
Enhancing the Expressiveness of Fingers: Multi-touch Ring Menus for Everyday Applications BIBAKFull-Text 259-264
  Dietrich Kammer; Frank Lamack; Rainer Groh
In the future, environments equipped with interaction surfaces sensitive to touch input will be a key factor to enable ambient intelligence. The user's fingers become input devices, allowing simple and intuitive interaction, like the manipulation of digital objects. However, people are used to everyday applications offering a wide variety of menu choices. We evaluate ring menus to enhance the expressiveness of finger interaction on multi-touch devices. Applicability and limits of ring menus are discussed with regard to our implementation by means of a preliminary user study.
Keywords: Multi-touch; ring menus; pie menus; user interface design
Privacy Policy Enforcement for Ambient Ubiquitous Services BIBAKFull-Text 265-269
  Were Oyomno; Pekka Jäppinen; Esa Kerttula
Ubiquitous service providers leverage miniaturised computing terminals equipped with wireless capabilities to avail new service models. These models are pivoted on personal and inexpensive terminals to customise services to individual preferences. Portability, small sizes and compact keyboards are few features popularising mobile terminals. Features enable storing and carrying of ever increasing proportions of personal data and ability to use them in service adaptations. Ubiquitous services automate deeper soliciting of personal data transparently without the need for user interactions. Transparent solicitations, acquisitions and handling of personal data legitimises privacy concerns regarding disclosures, retention and re-use of the data. This study presents a policy enforcement for ubiquitous services that safeguards handling of users personal data and monitors adherence to stipulated privacy policies. Enforcement structures towards usability and scalability are presented.
Keywords: Context-aware; privacy policy; ubiquitous service; privacy
A Concept for a First Communication Initiation for Ambient Intelligent Industrial Environments BIBAKFull-Text 270-274
  Florian Floerchinger; Marc Seissler
This paper presents a concept for an intuitive way of establishing physical communication connections between industrial field devices and an universal control device that supports several communication standards. It aims to stimulate the discussion about how a first communication initiation in ad-hoc linked environments has to look like. Key of the presented concept is a reference model that specifies all communication relevant information of a field device, attaching this information to the device, using an inexpensive passive data carrier. Furthermore, this reference model references data like multi-user behavior and user-rights, enabling a flexible user-centered device interaction which satisfies the needs of an industrial environment. With such a reference model most AMI technologies will be much more easy to use in ad-hoc linked environments. The concept presented in this paper is being tested and evaluated in the SmartFactoryKL, the intelligent factory of the future.
Keywords: Universal Interaction Device; SmartFactoryKL; context model; industrial communication; user-centered interaction; useML
A Bluetooth-Based Device Management Platform for Smart Sensor Environment BIBAKFull-Text 275-279
  Ivan Boon-Kiat Lim; Kin Choong Yow
In this paper, we propose the use of Bluetooth as the device management platform for the various embedded sensors and actuators in an ambient intelligent environment. We demonstrate the ease of adding Bluetooth capability to common sensor circuits (e.g. motion sensor circuit based on a pyroelectric infrared (PIR) sensor). A central logic application is proposed which controls the operation of controller devices, based on values returned by sensors via Bluetooth. The operation of devices depends on rules that are learnt from user behavior using an Elman recurrent neural network. Overall, Bluetooth has shown its potential in being used as a device management platform in an ambient intelligent environment, which allows sensors and controllers to be deployed even in locations where power sources are not readily available, by using battery power.
Keywords: Ambient Intelligence; Smart Sensor Environment; Bluetooth
Investigation and Demonstration of Local Positioning System Using Ultrasonic Sensors for Wide Indoor Areas BIBAKFull-Text 280-284
  Takashi Hada; Hikaru Sunaga; Masaki Akiyama; Shigenori Ioroi; Hiroshi Tanaka
This paper proposes an indoor positioning system for detecting the location of a moving object such as a person or a goods trolley in a wide indoor area. Conventional system requires synchronization between transmission and receiving unit. As a result, they include not only an ultrasonic part but also a radio part to maintain synchronization. We have developed a system that uses only ultrasonic waves, that is, an asynchronous system. The system configuration and sequence of operation are explained and the verification system which includes H8, PIC microprocessors and a PC for positioning calculation is described. It was confirmed that the proposed method is valid and the positioning error is within 100mm.
Keywords: Positioning System; Ultrasonic Waves; Asynchronous System; Positioning Error; Navigation
Automatic Pedestrian Detection and Counting Applied to Urban Planning BIBAKFull-Text 285-289
  Thomas Michelat; Nicolas Hueber; Pierre Raymond; Alexander Pichler; Pascal Schaal; Bernard Dugaret
The statistical knowledge of human flows in the streets is mandatory for urban planning. Today many cities use the expensive method of manual pedestrian counting, since there is no reliable automatic counting device. This project aims at achieving the first efficient, real-time, embedded and autonomous system that provides high-level data. Our first work focused on the development of a reliable counting method under Matlab™. On the basis of video sequences recorded in the city of Mulhouse we have validated the robustness of our approach.
Keywords: Pedestrian counting; Pedestrian detection; Background subtraction; Smart sensor; Global sensing; Embedded computing
This Is Me: Using Ambient Voice Patterns for In-Car Positioning BIBAKFull-Text 290-294
  Michael Feld; Tim Schwartz; Christian A. Müller
With the range of services that can be accessed inside a car constantly increasing, so are the opportunities for personalizing the experience for both driver and other passengers. A main challenge however is to find out who is sitting where without asking explicitly. The solution presented in this paper combines two sources of information in a novel way: Ambient speech and mobile personal devices. The approach offers improved privacy by putting the user in control, and it does not require specialized positioning technologies such as RFID. In a data-driven evaluation, we confirm that the accuracy is sufficient to support a ten-speaker scenario in practice.
Keywords: Positioning; Speaker Recognition; Automotive HMI; User Modeling; Personalization
Selective Delivery of Points of Interest BIBAFull-Text 295-299
  Nuno Gil Fonseca; Luís Rente; Carlos Bento
In our daily life, we are increasingly surrounded by devices that expose us to quantities of information well behind our cognitive capabilities. To overcome this problem various authors propose mechanisms capable of selecting only the most relevant pieces of information.
   In this paper, we propose an approach for information selection based on the concepts of relevance, selective attention and diversity. The idea is to select the most promising items in terms of surprise and usefulness and dismiss those that are less promising.
   We illustrate our approach with an example of an application for restaurant selection and show the first results from an initial evaluation of this system.
Ambient Intelligence Research Landscapes: Introduction and Overview BIBAKFull-Text 300-303
  Norbert Streitz
This paper starts out by introducing the "Landscapes" category at the Joint International Conference on Ambient Intelligence (AmI-2010) and provides an overview over the two sessions. The main part of the paper presents a framework for the role of Ambient Intelligence in the development of the cities of the future. This includes the integration of real and virtual worlds resulting in Hybrid Cities and their transformation into Smart Cities. In the context, it is argued that the technological development has to be monitored by guidelines and goals for maintaining and improving the quality of life leading to what is called Humane Cities, addressing, e.g., social awareness and privacy, trust and identity. The paper closes with proposals for a future research agenda.
Keywords: landscapes; ambient intelligence; smart environments; smart city; hybrid city; ubiquitous city; humane city; research agenda
Challenges and Limitations of Intelligent Ambient Assisted Living Environments BIBAKFull-Text 304-309
  Reiner Wichert
As a result of changing demographics, residing and being cared for in one's own familiar environment versus in an institutionalised inpatient setting is becoming the more attractive alternative for an ever increasing portion of the population. Despite its tremendous market potential, the AAL (Ambient Assisted Living) branch is still on the cusp of a mainstream breakthrough. A lack of viable business models is considered almost unanimously to be the greatest market obstacle to a broad implementation of innovative AAL systems. This paper highlights possible explanations for this deficit and shows why the AAL community has yet to arrive at joint solutions based on a unified AAL reference platform. Furthermore, this paper describes the enormous potential of AmI and AAL, as the first real opportunity for their success is provided through universAAL and AALOA.
Keywords: Ambient Assisted Living; Ambient Intelligence; market potential of AAL; business model; self-organisation; software infrastructures; AAL reference platform; standardisation; Smart Home; Fraunhofer AAL Alliance
The DFKI Competence Center for Ambient Assisted Living BIBAKFull-Text 310-314
  Jochen Frey; Christoph Stahl; Thomas Röfer; Bernd Krieg-Brückner; Jan Alexandersson
The DFKI Competence Center for Ambient Assisted Living (CCAAL) is a cross-project and cross-department virtual organization within the German Research Center for Artificial Intelligence coordinating and conducting research and development in the area of Ambient Assisted Living (AAL). Our demonstrators range from multimodal speech dialog systems to fully instrumented environments allowing the development of intelligent assistant systems, for instance an autonomous wheelchair, or the recognition and processing of everyday activities in a smart home. These innovative technologies are then tested, evaluated and demonstrated in DFKI's living labs.
Keywords: intelligent environments; ambient assisted living; living labs
Intersecting the Architecture of the Internet of Things with the Future Retail Industry BIBAFull-Text 315-319
  Carsten Magerkurth; Stephan Haller; Pascal Hagedorn
This paper discusses the approach of SAP Research in Switzerland to investigate, develop and evaluate future Internet of Things architectures and prototypes with their unique combination of three scientific pillars: SAP Research combines an environment of co-located academic education at leading universities ("Campus-Based Engineering Centers") with the concept of living laboratories in which real-world prototypes and systems are rigorously tested. SAP Research Switzerland hosts the "Future Retail Center" (FRC) in order to validate innovations in the retail industry. As an orthogonal element, we also structure our research activities in technological dimensions as opposed to the industry-specific living labs. The "Smart Items Research Program" bundles and focuses all research topics that are related to Ambient Intelligence (AmI), Internet of Things, and Pervasive Computing. With the researchers from the engineering centers, the industry focus in the living labs, and the different research projects and research programs, a holistic research perspective is created that ensures a highly effective and focused execution of research, unifying technical Internet of Things architectures with the corresponding business needs and forming a unique landscape of innovation.
On the Role of ExperienceLab in Professional Domain Ambient Intelligence Research BIBAKFull-Text 320-324
  Evert van Loenen; Richard van de Sluis; Boris E. R. de Ruyter; Emile H. L. Aarts
Concept development for professional domain AmI solutions involves different stakeholders than those for consumer products, and puts different requirements on experience test methods and facilities. Philips ExperienceLab facility for experience research is described, as well as trends and lessons learned from its use in the two domains.
Keywords: User-centered Research; Ambient Intelligence; Experience Research; Healing Environments
The Christian Doppler Laboratory on Contextual Interfaces BIBAKFull-Text 325-332
  Thomas Grill; Wolfgang Reitberger; Marianna Obrist; Alexander Meschtscherjakov; Manfred Tscheligi
Contextual interfaces gain more and more importance within the last years. Numerous research programs that address the term context have been established, each focusing on context from their own point of view. The Christian Doppler Laboratory on Contextual Interfaces has been founded with different goals in mind. The first goal is to elaborate on the definitions and foundations of the term context to achieve a common understanding on how to use context and the terms related to context. Further we elaborate on the relation between context and user experience to tackle the complexity of the interrelations between both areas. The second goal is to apply the findings of the basic context research with two different context laboratories, each addressing a different application area. This allows to build a robust research basis that is applied to application oriented research.
Keywords: ambient interfaces; human computer interaction; context; usability
Workshop on Interaction Techniques in Real and Simulated Assistive Smart Environments BIBAKFull-Text 333-336
  Felix Kamieth; Johannes Schäfer; Juan-Carlos Naranjo; Antonella Arca; Jacopo Aleotti
To further the development of AmI solutions, the simulation of solutions in virtual reality can help saving both development costs and time. The simulation of AAL environments, however, adds additional requirements to the interaction modalities used for making the simulated environment suitable for AAL target groups like elderly and handicapped people. This workshop aims at the development of a systematic approach to the creation of such simulation environments for reducing the additional gap between the virtual reality simulation of an environment and its real counterpart in terms of end-user interaction. This paper provides an analysis of the core problems of this issue an overview of current technological approaches to solve them.
Keywords: Ambient Intelligence; Virtual Reality; Simulation; Interaction
Workshop on Pervasive Computing and Cooperative Environments in a Global Context BIBAFull-Text 337-338
  Kirusnapillai Selvarajah; Neil A. Speirs
The increasing number of devices that are invisibly embedded into our surrounding environment as well as the proliferation of wireless communication and sensing technologies are the basis for visions like ambient intelligence, ubiquitous and pervasive computing. In this context, the objective of PECES EU project is the creation of a comprehensive software layer to enable the seamless cooperation of embedded devices across various smart spaces on a global scale in a context-dependent, secure and trustworthy manner.
'Designing Ambient Interactions -- Pervasive Ergonomic Interfaces for Ageing Well' (DAI'10) BIBAKFull-Text 339-341
  Arjan Geven; Sebastian Prost; Manfred Tscheligi; John Soldatos; Mari Feli González
The workshop will focus on novel computer based interaction mechanisms and interfaces, which boost natural interactivity and obviate the need for conventional tedious interfaces. Such interfaces are increasingly used in ambient intelligence environments and related applications, including application boosting elderly cognitive support, cognitive rehabilitation and Ambient Assisted Living (AAL). The aim of the workshop is to provide insights on the technological underpinnings of such interfaces, along with tools and techniques for their design and evaluation.
Keywords: AAL; Elderly; User centred design; context-awareness; pervasive computing; ergonomics
3rd Workshop on Semantic Ambient Media Experience (SAME) -- In Conjunction with AmI-2010 BIBAKFull-Text 342-345
  Artur Lugmayr; Björn Stockleben; Juha Kaario; Bogdan Pogorelc; Thomas Risse
The SAME workshop takes place for the 3rd time in 2010, and it's theme in this year was creating the business value-creation, vision, media theories and technology for ambient media. SAME differs from other workshops due to its interactive and creative touch and going beyond simple powerpoint presentations. Several results will be published by AMEA -- the AMbient Media Association (www.AmbientMediaAssociation.org).
Keywords: ambient intelligence; ubiquitous computation; pervasive computation; pervasive e-commerce; media studies; ambient health
Workshop AccessibleTV "Accessible User Interfaces for Future TV Applications" BIBAKFull-Text 346-348
  Volker Hahn; Pascal Hamisu; Christopher Jung; Gregor Heinrich; Carlos Duarte; Patrick Langdon
Approximately half of the elderly people over 55 suffer from some type of typically mild visual, auditory, motor or cognitive impairment. For them interaction, especially with PCs and other complex devices is sometimes challenging, although accessible ICT applications could make much of a difference for their living quality. Basically they have the potential to enable or simplify participation and inclusion in their surrounding private and professional communities. However, the availability of accessible user interfaces being capable to adapt to the specific needs and requirements of users with individual impairments is very limited. Although there are a number of APIs [1, 2, 3, 4] available for various platforms that allow developers to provide accessibility features within their applications, today none of them provides features for the automatic adaptation of multimodal interfaces being capable to automatically fit the individual requirements of users with different kinds of impairments. Moreover, the provision of accessible user interfaces is still expensive and risky for application developers, as they need special experience and effort for user tests. Today many implementations simply neglect the needs of elderly people, thus locking out a large portion of their potential users. The workshop is organized as part of the dissemination activity for the European-funded project GUIDE "Gentle user interfaces for elderly people", which aims to address this situation with a comprehensive approach for the realization of multimodal user interfaces being capable to adapt to the needs of users with different kinds of mild impairments. As application platform, GUIDE will mainly target TVs and Set-Top Boxes, such as the emerging Connected-TV or WebTV platforms, as they have the potential to address the needs of the elderly users with applications such as for home automation, communication or continuing education.
Keywords: AccessibleTV; accessibility; multimodal interfaces; set-top boxes; open platforms; connected-TV; WebTV platforms
First Workshop on Radically Innovative AAL Services BIBAKFull-Text 349-350
  Juan-Pablo Lázaro; Sergio Guillén
The following document describes the call for papers for a workshop based on identifying the key aspects that are implicit in any innovative application or service in the field of Ambient Assisted Living. Expected results will be focused in identifying the success factors that are under successful implementations and deployments of AAL Services in real conditions.
Keywords: Ambient Assisted Living; AAL Services; innovation; best practices; barriers in AAL adoption; exploitation
First Workshop on Convergence and Consolidation towards Standard AAL Platform Services BIBAKFull-Text 351-352
  Juan-Pablo Lázaro; Sergio Guillén; Babak A. Farshchian; Marius Mikalsen
The following document describes the call for papers for a workshop based on identifying which are the potential commonalities that are important for an AAL system, so they can be discussed and proposed for opening an standardization process. Groups of components like context-management, user interaction management or semantic description of services are frequent components and technologies that are part of an AAL system.
Keywords: Ambient Assisted Living; standardization; ontologies; platforms