Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben

2013 | Buch

An Implementation, Execution and Simulation Platform for Processes in Heterogeneous Smart Environments Kapitel lesen Erstes Kapitel lesen

Ambient Intelligence

4th International Joint Conference, AmI 2013, Dublin, Ireland, December 3-5, 2013. Proceedings

herausgegeben von: Juan Carlos Augusto, Reiner Wichert, Rem Collier, David Keyson, Albert Ali Salah, Ah-Hwee Tan

Verlag: Springer International Publishing

Buchreihe : Lecture Notes in Computer Science

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

This book constitutes the refereed proceedings of the 4th International Joint Conference an Ambient Intelligence, AmI 2013, held in Dublin, Ireland, in December 2013. The 15 revised full papers, 4 papers from the landscape track, 3 papers from the doctoral colloquium and 6 demo and poster papers were carefully reviewed and selected from numerous submissions and are presented with 6 workshop descriptions. The papers cover a variety of multi-disciplinary topics in computer science, human computer interaction, electrical engineering, industrial design, behavioral sciences, distributed devices, ubiquitous and communication technologies, pervasive computing, intelligent user interfaces and artificial intelligence.

Inhaltsverzeichnis

Frontmatter

Full Papers Track

Frontmatter
An Implementation, Execution and Simulation Platform for Processes in Heterogeneous Smart Environments
Abstract
Developing ambient intelligence for a smart home is a complex task. We present how to define intelligent system behavior through processes on an adequate level of abstraction with the SHIP-tool. Based on the representation of the environment in a formal logical description, communication with the environment is realized via updates of the logical description. Processes are built from basic actions to update the current logical descriptions and include means to monitor the evolution of the environment in a temporal logic formalism. The SHIP-tool implements the process language and serves both for simulation and execution. The paper describes two examples of assisting services in a real smart home living lab, one for light and door control in emergency situations, and one for the scheduling of two parallel wheelchair transports.
Serge Autexier, Dieter Hutter, Christoph Stahl
Generating Explanations for Pro-active Assistance from Formal Action Descriptions
Abstract
In this paper we show how to generate explanations for an automatic assistance system for smart environments. In particular, we address dynamically changing environments in which devices and services can enter and leave at any time. All components employ the same simple action definitions. They are used to analyse the underlying intention, to synthesise a supporting strategy and to generate explanations that provide insights into the internals of the system. As tool of communication, we employ automatically generated question and corresponding answers. We furthermore detect sub-optimal behaviour and provide explanations that help to improve the usage of the system. All explanations are generated in natural language by utilising an intermediate representation as discourse representation structure and the SimpleNLG natural language generation framework.
Sebastian Bader
The Screen Is Yours—Comparing Handheld Pairing Techniques for Public Displays
Abstract
Whereas mobile devices have been heavily investigated as remote controls for distant displays, research on the fundamental first step, the pairing with the display, is scarce. In a comparative user study with 31 participants we evaluated five potential pairing techniques concerning their performance and acceptance for connecting to a public display and gained insights into the general requirements for pairing techniques in this special usage context. Besides four established mobile interaction techniques (touching an NFC tag, capturing a QR code, scanning, and manual input), our study considered a recent appropriate pairing technique called display pointing, which allows passers-by to connect to available displays just by pointing their smartphone at the installation, for the first time. Our results show that display pointing is superior to traditional alternatives to a large extent. Yet, its quick response times can result in a perceived lack of control if not handled appropriately. Further, we learnt that long distance techniques are generally preferred while the type of device gesture as well as security concerns are of less relevance.
Matthias Baldauf, Markus Salo, Stefan Suette, Peter Fröhlich
Customized Situation Verification in Ambient Assisted Living Environments
Abstract
The demographic change in the European society leads to an increased demand for assistance and support systems for elderly people. To cope with the upcoming superannuation of the population a variety of projects for developing Ambient Assisted Living (AAL) solutions were funded. The usage of multiple sensor sources can increase the accuracy and fault tolerance of an ambient system, but increases the effort and complexity for decision making as well. In ambient assisted environments, where the decision making process has to consider different user specific behavior, complexity becomes an issue. Therefore, we propose the usage of a semantic layer, which encapsulates user specific information and enriches sensed user interactions with semantics. Within this paper we present an approach, which (i) allows to verify sensor events in a user specific context during decision making and (ii) ensures that actions are triggered corresponding to the user’s needs. To demonstrate the feasibility of our approach we implemented the use case of detecting and handling a critical household event by using a simulation environment to evaluate different scenario set ups.
Mario Buchmayr, Werner Kurschl, Josef Küng
Inferring Model Structures from Inertial Sensor Data in Distributed Activity Recognition
Abstract
Activity-Event-Detector (AED) digraphs can describe relations between human activities, activity-representing pattern events from sensors, and distributed detector nodes. AED graphs have been successfully used to perform network adaptations, including reconfiguring networks to reduce recognition complexity and network energy needs. In this paper, we present an approach to infer AED graph configurations from distributed sensor data. We utilise a non-parametric clustering procedure and derive all relevant information about the AED graph structure, including the detector-specific activity grouping and activity-detector relations from measured data. We analysed our approach using a previously published dataset and compared our inferred AED graph with those designed by an expert. The system based on the inferred AED graph yielded a performance boost of 15% in the final classification accuracy and reduced computational complexity of detectors. These results indicate that our approach is viable to automate the configuration of distributed activity recognition sensor-detector networks.
Pierluigi Casale, Oliver Amft
Making Context Aware Decision from Uncertain Information in a Smart Home: A Markov Logic Network Approach
Abstract
This research addresses the issue of building home automation systems reactive to voice for improved comfort and autonomy at home. The focus of this paper is on the context-aware decision process which uses a dedicated Markov Logic Network approach to benefit from the formal logical representation of domain knowledge as well as the ability to handle uncertain facts inferred from real sensor data. The approach has been experiemented in a real smart home with naive and users with special needs.
Pedro Chahuara, François Portet, Michel Vacher
Towards Human Energy Expenditure Estimation Using Smart Phone Inertial Sensors
Abstract
This paper is focused on a machine-learning approach for estimating human energy expenditure during sport and normal daily activities. The paper presents technical feasibility assessment that analyses requirements and applicability of smart phone sensors to human energy expenditure. The paper compares and evaluates three different sensor configuration sets: (i) a heart rate monitor and two standard inertial sensors attached to the users thigh and chest; (ii) a heart rate monitor with an embedded inertial sensor and a smart phone carried in the pocket; and (iii) only a smart phone carried in the pocket. The accuracy of the models is validated against indirect calorimetry using the Cosmed system and compared to a commercial device for energy expenditure SenseWear armband. The results show that models trained using relevant features can perform comparable or even better than available commercial device.
Božidara Cvetković, Boštjan Kaluža, Radoje Milić, Mitja Luštrek
Designing Personal Informatics for Self-reflection and Self-awareness: The Case of Children with Attention Deficit Hyperactivity Disorder
Abstract
A main challenge in designing for children with Attention Deficit Hyperactivity Disorder (ADHD) is to support the learning process of supressing undesired behaviour on daily routines by means of positive feedback and rewards. Personal Informatics (PI) is a model that supports capturing and integration of personal data to facilitate reflection and action that is used as a design platform to support behavioral learning. This paper presents a design-driven research study that illustrates the potential of PI to support self-awareness and self-reflection of ADHD children. Two design approaches are described which aim to support self-behavioral inhibition learning: (a) KITA, a Kinesiofeedback Toy for ADHD, being a Tangible User Interface that measures and assesses children’s activity and provides them with feedback as to whether or not behavior is within appropriate limits; and (b) WRISTWIT, a Wearable device presenting information on attention and time for ADHD to increase on-task behavior. KITA and WRISTWIT were tested in the field with children as design means to implement PI to positively modify children behavior during daily school routines.
Juan Jimenez Garcia, Hilde de Bruyckere, David V. Keyson, Natalia Romero
A Robotic Fitness Coach for the Elderly
Abstract
The ultimate goal of ambient assisted living is to help elderly people live a healthy life in the convenience of their homes by making more intelligent technology bring them a set of required assistive tools. In this paper we describe a robotic fitness coach that learns a set of physical exercises from a professional trainer, and assists elderly subjects in performing these gestures. The gestures were selected from an actual training programme at an elderly care home. When demonstrating gestures, the robot performs the learned gestures to the best of its abilities, and while monitoring the elderly subject with an RGB-D camera, provides verbal guidance to complement the visual display, correcting gestures on the fly. We provide a detailed description of the training programme, the gesture acquisition, replication and evaluation algorithms, our solution to the robot stability problem, and a set of preliminary user tests to validate our approach.
Binnur Görer, Albert Ali Salah, H. Levent Akın
Digital Receipts: Fostering Mobile Payment Adoption
Abstract
Mobile payment adoption remains low. This paper presents a user-study that evaluates whether providing digital receipts in-store to customers could drive mobile payment adoption. Our results reveal that although our smart phone based payment and digital receipt processes took up to 60% longer than getting paper receipts and paying with cash, users perceived the digital receipt approach as fun, useful, and even time-saving. These insights may help drive adoption of mobile payment systems.
Edward Ho, Silviu Apostu, Florian Michahelles, Alexander Ilic
Exploring Persuasion in the Home: Results of a Long-Term Study on Energy Consumption Behavior
Abstract
This paper presents a seven-months field study on a persuasive ambient display in private households. The FORE-Watch aims at adjusting the consumption behavior of energy users in 24 multi-person households and persuading them to change their timing of consumption activities; half of them were shown a forecast of the occupancy rate of the local energy grid (i.e., grid status), and the other half were shown how much energy will be delivered by green sources such as windmills (i.e., green energy). Our qualitative and quantitative survey and the energy consumption data revealed that the grid status group showed a more constant behavior than the green energy, indicating that the more dynamic forecast presentation did not lead to the same type of behavior change as the static forecast presentation. Overall, the FORE-Watch aroused awareness, attention and interest through permanent presence, clear and simple information, and changed the energy consumption behavior of our participants.
Patricia M. Kluckner, Astrid Weiss, Johann Schrammel, Manfred Tscheligi
Low-Power Ambient Sensing in Smartphones for Continuous Semantic Localization
Abstract
Extracting semantic meaning of locations enables a large range of applications including automatic daily activity logging, assisted living for elderly, as well as the adaptation of phone user profiles according to user needs. Traditional location recognition approaches often rely on power-hungry sensor modalities such as GPS, network localization or audio to identify semantic locations, e.g., at home, or in a shop. To enable a continuous observation with minimal impact on power consumption, we propose to use low-power ambient sensors – pressure, temperature, humidity and light – integrated in phones. Ambient fingerprints allow the recognition of routinely visited places without requiring traditional localization sensing modalities. We show the feasibility of our approach on 250 hours of data collected in realistic settings by five users during their daily transition patterns, in the course of 49 days. To this end, we employ a prototype smartphone with integrated humidity and temperature sensor. We achieve up to 80% accuracy for recognition of five location categories in a user-specific setting, while saving up to 85% of the battery power consumed by traditional sensing modalities.
Sînziana Mazilu, Ulf Blanke, Alberto Calatroni, Gerhard Tröster
Fast Adaptive Object Detection towards a Smart Environment by a Mobile Robot
Abstract
This paper proposes a novel method to detect objects by a mobile robot which adapts to an environment. Such a robot would help human designers of a smart environment to recognize objects in the environment with their attributes, which significantly facilitates his/her design. We first introduce Lifting Complex Wavelet Transform (LCWT) which plays an important role in this work. Since the LCWT has a set of controllable free parameters, we can design the LCWTs with various properties by tuning their parameters. In this paper we construct a set of LCWTs so that they can extract local features from an image by multi-scale. The extracted local features must be robust against several kinds of changes of the image such as shift, scale and rotation. Our method can design these LCWTs by selecting their parameters so that the mobile robot adapts to the environment. Applying the new set of LCWTs to the images captured by the mobile robot in the environment, a local feature database can be constructed. By using this database, we implement an object detection system based on LCWTs on the mobile robot. Effectiveness of our method is demonstrated by several test results using the mobile robot.
Shigeru Takano, Ilya Loshchilov, David Meunier, Michèle Sebag, Einoshin Suzuki
On the Edge of a Virtual World – Investigating Users’ Preferences and Different Visualization Techniques
Abstract
This paper investigates how the edges of a limited size 3D virtual world model can be visualized. We compared five alternative visualization techniques by conducting downloading, post-processing and rendering measurements and evaluating the designs with a user study. Recommendations for UI designers working especially in the mobile computing domain are presented.
Jarkko Vatjus-Anttila, Leena Ventä-Olkkonen, Jonna Häkkilä
Semantics-Driven Multi-user Concurrent Activity Recognition
Abstract
This paper presents a novel knowledge-driven approach to recognising multi-user concurrent activities in smart home environments. Capturing these concurrent activity patterns is challenging in that it usually requires detailed application-/user-specific specifications, or needs a large amount of data to build sophisticated models. The proposed approach is founded upon the use of a generic ontology model to represent domain knowledge, which is independent of particular sensor deployment and activities of interest. It leverages the hierarchical structure of domain concept ontologies and applies well-established hierarchy-based techniques to enable automatic segmentation of real-time sensor traces and supports matching finely grained sensor data to coarsely constrained activities. We empirically evaluate our approach using a large-scale real-world dataset, achieving an average accuracy of 86%.
Juan Ye, Graeme Stevenson

Landscape Track

Frontmatter
Personalized Smart Environments to Increase Inclusion of People with Down’s Syndrome
Abstract
Most people with Downs Syndrome (DS) experience low integration with society. Recent research and new opportunities for their integration in mainstream education and work provided numerous cases where levels of achievement exceeded the (limiting) expectations. This paper describes a project, POSEIDON, aiming at developing a technological infrastructure which can foster a growing number of services developed to support people with DS. People with DS have their own strengths, preferences and needs so POSEIDON will focus on using their strengths to provide support for their needs whilst allowing each individual to personalize the solution based on their preferences. This project is user-centred from its inception and will give all main stakeholders ample opportunities to shape the output of the project, which will ensure a final outcome which is of practical usefulness and interest to the intended users.
Juan Carlos Augusto, Terje Grimstad, Reiner Wichert, Eva Schulze, Andreas Braun, Gro Marit Rødevand, Vanda Ridley
Living Lab and Research on Sustainability: Practical Approaches on Sustainable Interaction Design
Abstract
Living labs can be understood as the ability to bring user, technology and business into an open innovative development process that establishes real life environments. In this paper we describe our ongoing works on sustainable interaction design on energy saving and trading in which local residents are involved. The SusLabNWE (Sustainable Living Lab North-West Europe) project aims to resolve territorial challenges related to industrial competitiveness and sustainability in North West Europe. We present two projects in which local residents in the Netherlands were engaged in sustainable innovation in the context of the SusLabNWE project.
David V. Keyson, Abdullah Al Mahmud, Natalia Romero
Intelligent Decision-Making in the Physical Environment
Abstract
The issue of situating intelligent agents within an environment, either virtual or physical, is an important research question in the area of Multi Agent Systems. In addition, the deployment of agents within Wireless Sensor Networks has received some focus also.
This paper proposes an architecture to augment the reasoning capabilities of agents with an abstraction of a physical sensing environment over which it has control. This architecture combines the SIXTH sensor middleware platform with the ASTRA agent programming language, using CArtAgO as the intermediary abstraction.
David Lillis, Sean Russell, Dominic Carr, Rem W. Collier, Gregory M. P. O’Hare
An Intelligent Hotel Room
Abstract
This paper presents an innovative application of ambient technology in the domain of tourism and leisure that aims to improve the quality of services offered by the hospitality industry. The main objective is to formulate an ambient ecosystem that observes its surroundings using non-invasive technology and adapts its behavior, in real-time, to deliver “intelligent” and personalized services to the occupants of a guest room. Towards that direction, the proposed system aims to leverage the disadvantages of being away from home and offer a unique user experience.
Asterios Leonidis, Maria Korozi, George Margetis, Dimitris Grammenos, Constantine Stephanidis

Doctoral Colloquium

Frontmatter
Harnessing Mathematics for Improved Ontology Alignment
Abstract
Given a domain of interest, an ontology provides a formal specification of the concepts and relationships in this domain. An alignment identifies a semantic connection between the concepts and relationships of ontologies purporting to describe the same knowledge. The majority of approaches to ontology alignment take a general view and rely on terminological and structural techniques to handle the widest possible class of ontologies. Due to the fuzzy nature of concepts and the variations in their representations, this matching process is often complicated. One area that should provide a more solid foundation for comparison is mathematical concepts. Mathematical concepts are covered by numerous ontologies, making them a potentially important basis for comparison. One part of this doctoral work is to investigate the potential of using mathematical concepts to improve ontology alignment.
Chau Do, Eric J. Pauwels
On Combining a Context Recognition System and a Configuration Planner for Personalised Ambient Assisted Living
Abstract
This abstract describes how a context recognition system and a configuration planner can interact to enable personalised activity monitoring in apartments with different features. The two systems are developed to supporting independent living of senior citizens (primary users) by monitoring their daily interaction with the environment. For this purpose, networked non-intrusive sensors that senses motion, power usage, and pressure are used, in addition relevant physiological parameters such as heart rate and blood pressure are measured on demand.
Lia Susana d. C. Silva-López, Jonas Ullberg, Lars Karlsson
Towards Automatic Detection of Missing Referred Documents during Meetings
Abstract
Business meetings are often informed by and make reference to documents, however not every document that a meeting wishes to consult will already be present. We propose the concept of a smart meeting room capable of detecting when the meeting talks about a document and determining whether that document is already present. We report a preliminary interview-based study into the experience of attending meetings where documents are missing. A subsequent study investigated how observers of meetings are able to judge whether a document being talked about is currently present. This indicates the specific capabilities required by an intelligent assistant system able to detect references to missing documents. We describe an experimental investigation into one such capability involving visually tracking hands and printed documents in a video recording of a meeting.
Hugo Lopez-Tovar, John Dowell

Demos and Posters Track

Frontmatter
SHIP-Tool Live: Orchestrating the Activities in the Bremen Ambient Assisted Living Lab
(Demo)
Abstract
Developing ambient intelligence for a smart home living lab is a complex task. We present the SHIP-tool to define ambient intelligence processes on an adequate level of abstraction. Based on the representation of the environment in a formal logical description, communication from and to the environment is via updates of the logical description. Processes are built from basic actions to update the current logical descriptions and include means to monitor the evolution of the environment in a temporal logic formalism. The SHIP-tool implements the process language and serves both for simulation and execution of sample ambient intelligent services in a real smart home living labs also presented in the paper. Two showcases have been realized: a night surveillance service and a transportation assistance. The demonstration consisted of showing both showcases both simulated in a desktop VR environment and remotely controlling the real smart home living lab.
Serge Autexier, Dieter Hutter, Christian Mandel, Christoph Stahl
CAKE – Distributed Environments for Context-Aware Systems
Abstract
In this paper, we introduce the distributed Context Awareness and Knowledge Environment CAKE. The design objectives for CAKE were to develop a system that is flexible enough to be used in different application domains, that supports re-use of components with the help of a well-defined plugin-system and application programming interface and that caters for privacy concerns by giving users access to personal context aware environments that share information selectively with other users’ context aware environments. We describe related work on context middleware and the niche CAKE is targeting. We also argue for taking privacy concerns into account and outline how our framework addresses such issues. The concepts behind CAKE are introduced, and we describe how reasoning engines based on different paradigms can be put to work together in our framework. A first take on end-user programming is outlined and a prototypical implementation of the system presented.
Jörg Cassens, Felix Schmitt, Michael Herczeg
Energy Expenditure Estimation DEMO Application
Abstract
The paper presents two prototypes for the estimation of human energy expenditure during normal daily activities and exercise. The first prototype employs two dedicated inertial sensors attached to the user’s chest and thigh and a heart rate monitor. The second prototype uses only the accelerometer embedded in a smart phone carried in the user’s pocket. Both systems use machine learning for the energy expenditure estimation. The focus of the demo is the convenience of using a smart phone application to provide the user with real-time insight into his/hers current status of the expended energy and also for on-the-spot encouragement based on the status. The evaluation and validation of both systems were done against the Cosmed indirect calorimeter, a gold standard for energy expenditure estimation and against the SenseWear, a dedicated commercial product for energy expenditure estimation.
Božidara Cvetković, Simon Kozina, Boštjan Kaluža, Mitja Luštrek
Enabling a Mobile, Dynamic and Heterogeneous Discovery Service in a Sensor Web by Using AndroSIXTH
Abstract
Achieving the vision of Ambient Intelligence, a world where devices adapt and anticipation our needs without intervention, requires a device to connect to multiple sensors to achieve this goal. One solution to this goal is to create a sensor web between sensors. This proves to be challenging due to the range of devices, different application requirements and is compounded by the fact that devices with their corresponding sensors can be mobile. Therefore a sensor web also requires the ability of heterogenous sensors to be discovered dynamically. This paper seeks to address the challenge of discovery by demonstrating how this can be achieved using a lightweight discovery service developed for this paper. AndroSIXTH aims to improve network middleware SIXTH with discovery services and extend its abilities to mobile networks. To illustrate the functionality of AndroSIXTH discovery service and its importance to the creation of Ambient Intelligent applications, a case study will be examined that demonstrates how through a seamless discovery service, an Augmented Reality environment can be created and used for maintenance and deployment of sensors for an Ambient Intelligent environment.
Levent Görgü, Barnard Kroon, Abraham G. Campbell, Gregory M. P. O’Hare
A Modular and Distributed Bayesian Framework for Activity Recognition in Dynamic Smart Environments
Abstract
Conditional dependencies between the human activities and different contexts (such as location and time) in which they emerge, are well known and have been utilized in the modern Ambient Intelligence (AmI) applications. But the rigid topology of the inference models in most of the existing systems adversely affects their flexibility and ability to handle inherent sensor ambiguities. Hence, we propose a framework for activity recognition suitable for a distributed and evolving smart environment. On the one hand, the framework exhibits flexibility to dynamically add and remove contexts through autonomic learning of individual contexts capitalizing the spatially distributed AmI infrastructures. On the other hand, it shows resilience to missing data by boot-strapping and fusing multiple heterogeneous context information.
Arun Kishore Ramakrishnan, Davy Preuveneers, Yolande Berbers
Towards an Integrated Methodology to Design Sustainable Living Practices
Abstract
Sustainable Living Labs (SLL) provide an experimental and interactive infrastructure to enable open innovation processes in the context of real (realistic) home settings. In SLL, home occupants play a role in communicating and discussing their values and lifestyles; they can experience innovations and reflect on the impact of their practices in daily life by means of situated experiments. The Concept House (CH), a SLL built in Rotterdam, the Netherlands, offers such facilities. In this paper, we discuss the development of the Experience Intervention Method (EIM) to obtain a holistic understanding of living practices. We demonstrate the method with a case study on home energy management developed in CH to clarify the role of qualitative and quantitative in-situ methods to get insights, co-design and validate sustainable innovations.
Natalia Romero, Abdullah Al Mahmud, Satish Beella, David V. Keyson
Backmatter
Metadaten
Titel
Ambient Intelligence
herausgegeben von
Juan Carlos Augusto
Reiner Wichert
Rem Collier
David Keyson
Albert Ali Salah
Ah-Hwee Tan
Copyright-Jahr
2013
Verlag
Springer International Publishing
Electronic ISBN
978-3-319-03647-2
Print ISBN
978-3-319-03646-5
DOI
https://doi.org/10.1007/978-3-319-03647-2

Premium Partner

    Bildnachweise