Ambient Intelligence - Software and Applications

Frontmatter

Content-Based Design and Implementation of Ambient Intelligence Applications

Abstract

Optimal support of professionals in complex ambient task environments requires a system that delivers the Right Message at the Right Moment in the Right Modality: (RM)³. This paper describes a content-based design methodology and an agent-based architecture to enable real time decisions of information presentation according to (RM)³. We will describe the full development cycle of design, development, and evaluation. Ontologies are regarded as key enablers as they define the classes and attributes to allow (RM)³ delivery. As a case study, we describe an ambient computing application for human-robot interaction in the Urban Search and Rescue domain.

Jurriaan van Diggelen, Marc Grootjen, Emiel M. Ubink, Maarten van Zomeren, Nanja J. J. M. Smets

Tracking People and Equipment Simulation inside Healthcare Units

Abstract

Simulating the trajectory of a patient, health professional or medical equipment can have diverse advantages in a healthcare environment. Many hospitals choose and to rely on RFID tracking systems to avoid the theft or loss of equipment, reduce the time spent looking for equipment, finding missing patients or staff, and issuing warnings about personnel access to unauthorized areas. The ability to successfully simulate the trajectory of an entity is very important to replicate what happens in RFID embedded systems. Testing and optimizing in a simulated environment, which replicates actual conditions, prevent accidents that may occur in a real environment. Trajectory prediction is a software approach which provides, in real time, the set of sensors that can be deactivated to reduce power consumption and thereby increase the system’s lifetime. Hence, the system proposed here aims to integrate the aforementioned strategies - simulation and prediction. It constitutes an intelligent tracking simulation system able to simulate and predict an entity’s trajectory in an area fitted with RFID sensors. The system uses a Data Mining algorithm, designated SK-Means, to discover object movement patterns through historical trajectory data.

Cátia Salgado, Luciana Cardoso, Pedro Gonçalves, António Abelha, José Machado

Requirements Systematization through Pattern Application in Ubiquitous Systems

Abstract

Application of patterns to address Non-Functional Requirements (NFRs) is a field that has not been widely explored, and that is still uncovered in the scope of Ubiquitous Computing. The unique features of this paradigm, such as context-awareness or technological unobtrusiveness, present a challenge to appropriately treat the specific NFRs related to this field. In this paper, recurring situations in ubiquitous systems have been identified and captured as patterns, which can be used to satisfy NFRs in different domains.

Tomás Ruiz-López, Manuel Noguera, María José Rodríguez Fórtiz, José Luis Garrido

Indoor Tracking Persons Using Bluetooth: A Real Experiment with Different Fingerprinting-Based Algorithms

Abstract

In outdoor localization, global positioning systems (GPS) has been widely used. Indoor applications require a precise estimation that GPS can not achieve. Several technologies have been tried out as WI-FI, RFID, Bluetooth, Zigbee and others. This paper describes an experiment conducted in a medium- sized room in which six zones have been identified and two Bluetooth transmitters were installed. The aim is to enable continuous monitoring of areas where a person moves. For this purpose, we have used the technique of RSSI fingerprinting and tested three different algorithms. The best results were obtained with an algorithm based on SVM, which yielded success rates of 88.54%. Based on this algorithm, we intend to develop a cheap and easily configurable indoor localization system.

María Rodríguez-Damián, Xosé Antón Vila Sobrino, Leandro Rodríguez-Liñares

Dynamically Improving Collective Environments through Mood Induction Procedures

Abstract

In our daily living, the environment surrounding us influences us as much or more than we influence it. Whether it is a domestic, leisure or working environment, its conditions will certainly have short and long-term effects on aspects such as stress, mood or fatigue, which will in turn influence indicators such as productivity, quality of work, quality of life, personal/group performance or even health. In this paper a dynamic environment is proposed that, based on the behavioural analysis of its users, will adapt its conditions to improve particular indicators. This will result in better working environments, with an impact on the quality of the work produced.

Davide Carneiro, Paulo Novais, Fábio Catalão, José Marques, André Pimenta, José Neves

CAFCLA: An AmI-Based Framework to Design and Develop Context-Aware Collaborative Learning Activities

Abstract

Ambient Intelligence (AmI) promotes the integration of Information and Communication Technologies (ICT) in daily life in order to ease the execution of everyday tasks. In this sense, education becomes a field where AmI can improve the learning process by means of context-aware technologies. However, it is necessary to develop new tools that can be adapted to a wide range of technologies and application scenarios. Here is where Agent Technology can demonstrate its potential. This paper presents CAFCLA, a multi-agent framework that allows developing learning applications based on the pedagogical CSCL (Computer Supported Collaborative Learning) approach and the Ambient Intelligence paradigm. CAFCLA integrates different context-aware technologies, so that learning applications designed, developed and deployed upon it are dynamic, adaptive and easy to use by users such as students and teachers.

Óscar García, Ricardo S. Alonso, Dante I. Tapia, Juan M. Corchado

AndroWI: Collaborative System for Fuel Saving Using Android Mobile Devices

Abstract

This paper implements and validates a system to save fuel based on the collaboration of drivers. The system gets the optimal speed pattern evaluating the driving of nearby drivers. A fuzzy logic system is used to assess drivers and the information about nearby vehicles is obtained through WIFI-Direct. Best driver sends the optimal speed pattern to the other vehicles and the mobile device notifies the user through a vibration pattern or speaker if the user should slow down or speed up.

Víctor Corcoba Magaña, Mario Muñoz Organero

A Query Expansion Approach Using the Context of the Search

Abstract

In this paper; we propose a solution to one of the most known problems in information retrieval field which is the ambiguity of short queries. In fact, short queries are often ambiguous and their execution by search tools engenders a lot of noise. The proposed contribution consists of a query expansion approach that exploits the recent browsing history of the user and the time parameter to expand short queries based on the feedback returned by the users having search behaviours similar to that of the current user.

Djalila Boughareb, Nadir Farah

Guidelines to Design Smartphone Applications for People with Intellectual Disability: A Practical Experience

Abstract

Applications for smartphones have a great potential to facilitate the lives of people with intellectual disability. In fact, it is possible to design specific applications adapted to their needs. But even in this case, users may experience accessibility issues with some structural elements of smartphones. In this study, we have identified these elements through a 2-month test period with some people with intellectual disability. They used a simple smartphone application that met some needs identified by their caregivers. Through this practical experience, problems with the notification bar and the home, back, menu, search, volume and power buttons have been detected. Potential solutions to overcome these issues have also been proposed.

Raul Igual, Inmaculada Plaza, Lourdes Martín, Montserrat Corbalan, Carlos Medrano

A Verbal Interaction Measure Using Acoustic Signal Correlation for Dyadic Cooperation Support

Abstract

We introduce a method for detecting whether two users are engaged in focused interaction using a windowed correlation measure on their acoustic signals, assuming that a continued exchange of verbal turns contributes to anticorrelation of acoustic activity. We tested our method with manually annotated transitions between focused and unfocused interaction stemming from experiments on AR-based cooperation within a research project on alignment in communication. The results show that a high degree and extended duration of speech activity anticorrelation reliably indicates focused interaction, and might thus be a valuable asset for situation-aware technical systems.

Alexander Neumann, Thomas Hermann

Server to Mobile Device Communication: A Case Study

Abstract

Develop a client-server application for a mobile environment can bring many challenges because of the mobile devices limitations. So, in this paper is discussed what can be the more reliable way to exchange information between a server and an Android mobile application, since it is important for users to have an application that really works in a responsive way and preferably without any errors. In this discussion two data transfer protocols (Socket and HTTP) and three serialization data formats (XML, JSON and Protocol Buffers) were tested using some metrics to evaluate which is the most practical and fast to use.

Ricardo Anacleto, Lino Figueiredo, Ana Almeida, Paulo Novais

Zappa: An Open Mobile Platform to Build Cloud-Based m-Health Systems

Abstract

Cloud computing and associated services are changing the way in which we manage information and access data. E-health services are not impermeable to novel technologies, especially those that involve mobile devices. At present, many patient monitoring m-health (mobile-health) platforms consist of close, vendor-dependent solutions based on particular architectures and technologies offering a limited set of interfaces to interoperate with. This fact hinders to advance in quality attributes such as customization, adaptation, extension, interoperability and even transparency of cloud infrastructure of existing solutions according to the specific needs of their users (patients and physicians). This paper presents an extensible, scalable, highly-interoperable and customizable platform called Zappa, designed to support e-Health/m-Health systems and that is able to operate in the cloud. The platform is based on components and services architecture, as well as on open and close source hardware and open-source software that reduces its acquisition and operation costs. The platform has been used to develop several remote mobile monitoring m-health systems.

Ángel Ruiz-Zafra, Kawtar Benghazi, Manuel Noguera, José Luis Garrido

Elicitation of Quality Characteristics for AAL Systems and Services

Abstract

Ambient Assisted Living (AAL) is a promising and fast growing area of technologies and services to assist people with special needs (e.g. elderly or disabled) in managing more independently their everyday life. AAL is founded on increasing needs for welfare technologies, as well as on significant effort from many scientific disciplines, the society, and the industry. The research has so far been primarily concentrated on elicitation of the functional aspects and on providing the technical solutions for the AAL systems and services. The problem of eliciting non-functional requirements and quality characteristics that are specific and critical for AAL, however, has been addressed to a much lesser extent. Failing to ensure the necessary system and service quality regarding critical characteristics may represent a significant obstacle to the wider acceptance of AAL in the society. There is hence a need to increase awareness of quality of AAL systems and services by providing the necessary supplement to the established state of the art. This paper reports on the process and the results from elicitation of AAL specific quality characteristics. The approach is based on established reference architectures and roadmapping material, as well as the ISO/IEC 9126 software product quality standard. The paper demonstrates how to do the elicitation in practice, and proposes the set of quality characteristics that are most important in the AAL context.

Aida Omerovic, Anders Kofod-Petersen, Bjørnar Solhaug, Ingrid Svagård

universAAL: Provisioning Platform for AAL Services

Abstract

universAAL is a European research project that aims at creating an open platform and standards which will make it technically feasible and economically viable to develop Ambient Assisted Living (AAL) solutions. It defined hardware and software infrastructure for smart environments called AAL Spaces, which enable context sharing and reasoning about activities carried out by the assisted person. AAL Services developed with the universAAL platform may be a combination of hardware, software and human resources. Tools for the development, publishing and provisioning of such services have been defined to support the whole chain of stakeholders involved in the AAL domain. The paper focuses on the provisioning of AAL Services by describing the main components involved in the service life cycle.

Roni Ram, Francesco Furfari, Michele Girolami, Gema Ibañez-Sánchez, Juan-Pablo Lázaro-Ramos, Christopher Mayer, Barbara Prazak-Aram, Tom Zentek

Separating the Content from the Presentation in AAL: The universAAL UI Framework and the Swing UI Handler

Abstract

When it comes to user interaction elderly and people with special needs have special requirements, that evolve over time. Ambient Assisted Living (AAL) envisions ubiquitous, intuitive human-machine interaction running on heterogeneous devices (tablets, televisions, smart-phones, etc.) and by means of multiple modalities (graphics, voice, gesture recognition, etc.). This vision often represents a strong technological challenge for any developer of AAL services. In order to relieve the developer from the burden of repeatedly adapting the interfaces, the universAAL platform [6] offers a framework for user interaction that separates the content, that is exchanged between the user and the application, and its actual representation. The main drawback of this solution is that it delegates all the responsibility of the representation of the content to the platform, which, in turn, must be able to adapt to all kinds of showable messages. This paper explains how a so-called UI Handler has been designed and implemented to render messages in universAAL, as well as the results of its technical and usability evaluations.

Alejandro Martín Medrano Gil, Dario Salvi, María Teresa Arredondo Waldmeyer, Patricia Abril Jimenez, Andrej Grguric

Performance Considerations in Ontology Based Ambient Intelligence Architectures

Abstract

One limitation that still exists for the use of ontologies in pervasive and ambient intelligence environments is the performance of the reasoning task, which can slow down the use of an application and make a solution inappropriate for some scenarios. In this paper we first present the results of a user evaluation that substantiates the amount of time, that is acceptable (from the point of view of a user) as a delay resulting from the reasoning process in ontology based scenarios. Based on this results we introduce an experimental setup to test the performance of an ontology based architecture. This test shall demonstrate the performance of the state of the art technology without specific performance optimizations and provide concrete measurements for such a setup.

Martin Peters, Christopher Brink, Sabine Sachweh, Albert Zündorf

Using 3D Virtual Agents to Improve the Autonomy and Quality of Life of Elderly People

Abstract

Nowadays, the percentage of elderly people is increasing, especially in developed countries. Technological products can be used to propel a cohesive and inclusive inter-generational society, although they should be adapted to satisfy the needs and preferences of elderly people. In this paper, we present 3D virtual agents as a promising system to improve the autonomy and Quality of Life (QoL) of elderly people, as they are technological systems that look and act like a person, thanks to the use of speech recognition and voice communication, and they can facilitate users’ everyday life. In this work, the connection between a virtual agent with a SQL database engine allows our agent to be connected to the health center, thus being able to assist users in their daily intake of medication.

Piedad Garrido, Angel Sanchez, Francisco J. Martinez, Sandra Baldassarri, Eva Cerezo, Francisco J. Seron

Multimodal Indoor Tracking of a Single Elder in an AAL Environment

Abstract

In this paper we present a proof-of-concept practical architecture of a system for tracking older adults living alone in an ambient intelligence environment by using multi-modal sensory information, such as audio and video input from Kinect and Arduino devices. This AAL (Ambient Assisted Living) system collects data into a Database of Trajectories, used to automatically generate training examples. We then show how the Database of Trajectories can be used in conjunction with a set of well-trained algorithms to alert remote caregivers in case of an unfortunate event, such as the elder falling down - one of the leading causes of injury and death.

Andrei-Adnan Ismail, Adina-Magda Florea

Distributed Neural Computation over WSN in Ambient Intelligence

Abstract

Ambient Intelligence (AmI) applications need information about the surrounding environment. This can be collected by means of Wireless Sensor Networks (WSN) that also analyze and build forecasts for applications. The RUBICON Learning Layer implements a distributed neural computation over WSN. In this system, measurements taken by sensors are combined by using neural computation to provide future forecasts based on previous measurements and on the past knowledge of the environment.

Davide Bacciu, Claudio Gallicchio, Alessandro Lenzi, Stefano Chessa, Alessio Micheli, Susanna Pelagatti, Claudio Vairo

Optimizing OSGi Services on Gateways

Abstract

Currently, the number of devices and services contained in the user’s home has considerably grown. Sometimes these devices are provided and managed remotely by service providers by facilitating installation or uninstallation of services. In a typical situation service providers install their services in the user’s home gateway from their remote repositories, regardless of the rest of the software installed on it. However, when various service providers work on a given gateway, the number of services and components installed on it increases. Therefore it is possible that this fact may lead to duplication or replacement of components necessary for other installed services, causing performance problems or service interruptions. This paper presents a system for analyzing and automatically optimizing the OSGi components deployed on a home gateway.

Iván Bernabé Sánchez, Daniel Díaz-Sánchez, Mario Muñoz-Organero

Extremely Small and Incredibly Everywhere

Abstract

Ambient Intelligence technologies call for new space concepts building on an understanding of how humans interrelate with objects. This paper argues for an environmental perspective on the analysis of persuasive technologies. It assumes that dualistic thinking, which recurs to categories such as society/technology or subject/object, has to be questioned. This paper resumes the approach of the PhD project ‘Thinking Space’ on the spatial dimensions of intelligent technologies. Space concepts from physics, sociology and literature theory form the basis for an empirically informed philosophical approach.

Louise Beltzung Horvath, Julia Grillmayr, Tanja Traxler

Kitchen AS-A-PAL: Exploring Smart Objects as Containers, Surfaces and Actuators

Abstract

Technological advancements have taken us closer to the “kitchen of the future” where everyday kitchen activities are seamlessly integrated with smart computing services. While there exist smart kitchen approaches, the explorative nature of the field encourages novel designs. This paper follows the trend by describing the design and development of the Kitchen AS-A-PAL, an infrastructure for facilitating smart kitchen services. Smart objects are the building blocks of Kitchen AS-A-PAL where three types of smart objects namely Containers, Surfaces and Actuators are explored through smart kitchen applications including interactive cookbook, health’n shopping and kaffe, god morgon.

Dipak Surie, Helena Lindgren, Arslan Qureshi

Ambient Sensorization for the Furtherance of Sustainability

Abstract

Energy efficiency is regarded as an important objective in a world of limited resources. The sustainable use of energy is necessary for the continuity of life styles that do not jeopardize the future. Nevertheless, due to poor information about the impact of human actions on the environment, it is hard to promote and warn for sustainability. This work focuses on the use of ambient intelligence as a mean to constantly revise sustainability indicators in a way they may be used for user awareness and recommendation systems within communities. The approach in this research makes use of sustainable indicators monitored through ambient sensors which enable user accountability concerning their actions inside each environment. Also, it is possible to compare the effect of user actions in the environment, enabling decision making based on such comparison factors.

Fábio Silva, Cesar Analide, Luís Rosa, Gilberto Felgueiras, Cedric Pimenta

Distributed Intelligent Rule-Based Wireless Sensor Network Architecture

Abstract

This paper describes the design of a new system architecture for monitoring and controlling purposes of a group of sensors and actuators within a wireless sensor network (WSN). This system can manage an undefined amount of clustered networks. The proposed system architecture enables Internet communications to reach the WSN in a highly efficient way. This structure reduces the bottleneck of the Internet/WSN bridge and the amount of messages inside the WSN when an Internet request arrives. Besides, each individual WSN implements an Intelligent Rule-Based System Automation (IRBSA) that performs the automation of the behaviour of the network motes according to the previously included rules. These rules describe the actions that are executed when all the conditions of that rule are met. Opposite to traditional approaches, IRBSA is placed in the WSN Header Mote rather than in the Internet server or in every mote.

Antonio Cubero Fernández, José María Castillo Secilla, José Manuel Palomares Muñoz, Joaquín Olivares Bueno, Fernando León García

Face Detection in Intelligent Ambiences with Colored Illumination

Abstract

Human face detection is an essential step in the creation of intelligent lighting ambiences, but the constantly changing multi-color illumination makes reliable face detection more challenging. Therefore, we introduce a new face detection and localization algorithm, which retains a high performance under various indoor illumination conditions. The method is based on the creation of a robust skin mask, using general color constancy techniques, and the application of the Viola-Jones face detector on the candidate face areas. Extensive experiments, using a challenging state-of-the-art database and a new one with a wider variation in colored illumination and cluttered background, show a significantly better performance for the newly proposed algorithm than for the most widely used face detection algorithms.

Christina Katsimerou, Judith A. Redi, Ingrid Heynderickx

Easy Carbon Offsetting and Trading with Ambient Technologies

Abstract

This paper presents a novel approach to carbon credit trading with ambient computing technologies, particularly RFID or barcode technology. It introduces RFID tags as certificates for the rights to claim carbon credits in carbon offsetting and trading. It enables buyers, including end-consumers, that buy products with carbon credits to hold and claim these credits unlike existing carbon offsetting schemes. It also supports the simple intuitive trading of carbon credits by trading RFID tags coupled to the credits. The approach has been already constructed and evaluated with real customers and real carbon credits in a real supply chain.

Ichiro Satoh

Ethically Intelligent? A Framework for Exploring Human Resource Management Challenges of Intelligent Working Environments

Abstract

With advances in the development of intelligent environments (IEs) social scientists and ethicists have begun to gauge the social impact of the diverse emerging technology assemblages and to work with developers and stakeholders in order to improve design and deployment of such technologies. Research conducted to better understand specific socio-technical settings faces multiple challenges due to the complexity of most scenarios, making it imperative to approach the attempt of understanding IEs both from multi-disciplinary perspectives and to include practitioners and managers of IEs. In this paper we introduce our framework for setting up a competence center (CC) for defining and managing socio-ethical challenges of intelligent working environments (IWEs). We detail practical steps to successfully build a CC in order to allow other research projects to adopt some of these steps or the whole framework to positively anticipate and manage socio-ethical challenges of IWEs.

Céline Ehrwein Nihan, Katharina Kinder-Kurlanda

Conversational Agents as Full-Pledged BDI Agents for Ambient Intelligence

Abstract

The need for conversational agents based on the Belief-Desire-Intention (BDI) architecture rise to support natural interfaces in many application areas of ambient intelligence, among which are the smart homes, health monitoring and assistance, care for the elderly, transportation, education, and tourism. The objective of this paper is to present an implementation of a conversational agent as a full-pledged BDI agent. This is achieved through mapping the BDI constructs in intelligent agents to the natural language processing components in a classic conversational agent, Eliza. Discussions focus on the process of reengineering the conversational agent technologies into BDI approach.

Aida Mustapha, Mohd Sharifuddin Ahmad, Azhana Ahmad

Supporting Workers and Quality Management in Sterilization Departments

Abstract

Sterilization of medical instruments is a complex task because of legal prescriptions and many regulatory specifications. Complicated instruments must be correctly disassembled and loaded on a rack before they can be automatically processed in a cleaning and disinfection machine. This paper proposes an assistive system helping workers to avoid fatal errors during reprocessing. The system provides disassembly instructions and important information for the reprocessing of medical instruments to attract the worker’s attention to critical issues. Continuous improvements and context-sensitive instructions are integrated by the use of business process models, a tabletop projection system with a gestural interface and radio-frequency identification (RFID) for instrument tracking. The user interface adapts to the criticality levels of instruments, which are continuously gathered and updated from the quality management of a sterilization department.

Stefan Rüther, Thomas Hermann, Maik Mracek, Stefan Kopp, Jochen Steil

An Intelligent System to Setup Meetings, Capture, Organize and Record Information in Smart Offices

Abstract

An ambient intelligent environment aims to have a pervasive computing, being a new paradigm that supports the projects of the next generation of intelligent systems and introducing new means of communication between man and machine. This paper reflects our efforts to develop an integrated control system for our Laboratory of Ambient Intelligent Decisions (LAID) in GECAD. The main purpose was to develop an application that is able to control three IP cameras Sony SNC-RZ25, together with the ability to monitor, control and view lab computers, thus adding a component of artificial intelligence in preparing and tracking a meeting in a smart environment. Therefore, this intelligent system is now closer to make decisions and interact with users without human intervention.

Joaquim Teixeira, Carlos Lima, Lino Figueiredo, Goreti Marreiros, Ricardo Costa

Backmatter