Ebook: Smart Homes and Beyond

After three successful editions held in France (2003), Singapore (2004), and Canada (2005), ICOST2006, hosted in Belfast, aims to continue to develop an active research community dedicated to explore how Smart Homes and Health Telematics can foster independent living and offer an enhanced quality of life for ageing and disabled people.

As we begin to witness the effects of changing demographics on today's society we begin to appreciate that the increase in the number of elderly and in the prevalence of those suffering from chronic disease and disabilities are likely to further increase in the next 2–3 decades. To react to the needs of this cohort to provide an environment within which they can reside for as long as possible, whilst maintaining their quality of life and independence, is a widespread concern for all. As such, there is real benefit to further investigate the role of technologies to address these changes and subsequently offer practical solutions to support independent living. We feel that within the realms of Smart Homes and Health Telematics real, affordable and useful services can be developed which will have the necessary underlying technological and service delivery infrastructures to allow seamless integration into existing care delivery paradigms.

Each year, ICOST has a specific flavour. ICOST2003 focused on usability. The theme was “Independent living for persons with disabilities and elderly people”. The theme for ICOST2004 was “Towards a Human-Friendly Assistive Environment” and for ICOST2005 was “From Smart Homes to Smart Care”. This year the conference has the theme “Smart Homes and Beyond”. The introduction of technology can provide a positive impact, however, it is necessary to avoid any detrimental effects if reliance upon technology within the home environment becomes so great that people will not leave their own home in fear of losing the support once outside of the home, or its close proximity. ICOST2006 focuses on promoting personal autonomy and extending the quality of life by considering including smart services inside and outside of the home. Specifically, those participating were encouraged to consider topics addressing inclusive smart home services, situation awareness, location-based services and mobility of service delivery.

The Conference proceedings begins with the two Invited Papers by Stephen Intille and Toshiyo Tamura. These are then followed by 36 research papers to be delivered as oral presentations and a further 15 short papers to be delivered as poster presentations. The proceedings has been divided into 6 Chapters in an attempt to broadly categorise the wide spectrum of topics covered. Firstly, Chapter 1 focuses on Human–Computer Interaction and provides an insight into the latest developments of how systems can interact with and for people. Chapter 2 addresses a core topic for this event: Smart Homes and Healthcare. Papers in this Chapter report on the importance of technology as a healthcare facilitator and on the innovative ways that Smart Homes can be used to provide healthcare services. Context Awareness and Activity Monitoring is the theme for Chapter 3. This Chapter provides contributions which offer solutions to the problems of context characterization and activity identification, all distinctive behavioural features that Smart Home related systems are expected to exhibit. Chapter 4 details technological advances in the area of Sensors, Wearable Systems, Smart Devices and Robotics, all of which allow the environment to collect ambient information. This technology is fundamental to transform an environment into an active space that can be sensitive to situations of interest and to react sensibly when required. Next, Chapter 5 provides us with an insight into the recent developments in Smart Homes and Health Telematics relating to the core areas of Communications, Middleware and Privacy. Finally, Chapter 6 presents a series of short papers addressing a range of the aforementioned topics covered in Chapters 1–5.

We would like to take this opportunity to thank a number of people who have helped in making this conference a success. First of all we would wish to thank all of the authors for their excellent contributions. We would wish to thank the Scientific and Technical Committees for their support during the review process. In addition we would wish to thank the members of the Local Organising Committee for all of their efforts in the organising of the conference itself. In particular we would wish to recognise the efforts of Liam Burns and Steven Devlin who managed the conference website and also assisted with the production of the proceedings. We would like to express our gratitude for the following organisations who very kindly sponsored the event: University of Ulster, Innovation Relay Centre, Invest Northern Ireland, Centre for Competitiveness, Tynetec, UUTech, BioBusiness Ireland, British Telecom Northern Ireland/Ireland, DHSSPS-NI, Institut National des Telecommunications – Évry, France, Scientific Direction of GET, Groupe des Écoles des Télécommunications, France. Finally we wish to express our thanks to Prof. Mounir Mokhtari, Dr. Daqing Zhang, Dr. Sylvain Giroux, Prof. Zenn Bien and Prof. Sumi Helal for their invaluable guidance and support throughout the organisation of ICOST2006.

The ICOST community, although only in its fourth year of existence, is making substantial progress and indeed an impact for its end users. We hope that ICOST2006 will further extend these developments and create a forum whereby further needs and challenges can be openly discussed and addressed on an International and multidisciplinary level.

Thank you for joining us and we hope that you enjoy ICOST2006 and have a pleasant stay in Belfast.

Chris Nugent and Juan Carlos Augusto

At MIT, a multi-disciplinary team of researchers from the House_n Consortium is studying how to create pervasive computing environments for the home. We are developing technologies and design strategies that use context-aware sensing to empower people by providing information when and where decisions and actions can be made. Contrary to many visions of future home environments in the literature, we advocate an approach that uses technology to teach as opposed to using technology primarily for automated control. We have designed and constructed a live-in laboratory (or “living laboratory”) that provides a unique, flexible infrastructure for scientifically studying the power of pervasive computing for motivating learning and behavior change in the home.

An automated monitoring system characterised as a smart house and called the Welfare Techno House (WTH) has been designed for home health care to prevent disease and improve the quality of life in the elderly. In this paper, we describe the smart house project in Japan and evaluate its effectiveness. The WTH concept involves a monitoring system for the continuous measurement of physiological parameters. Using this system, we collected physiological data and then analysed the key features of the data with regard to health monitoring. We review the previous 10-year trial of the WTH experimental project and discuss future developments.

This paper introduces Scylla, a toolkit for designing highly reconfigurable interaction within Smart Spaces. Using Scylla, users can define, edit and configure their interactions. Scylla's toolkit is part of our framework for studying and improving multimodal Human Environment Interaction (HEI). This article is in continuation with the work previously presented in [8]. In the first section of the paper, we describe our approach and the HEI framework. In the second section, we introduce Scylla that is part of the framework. We provide a use case and scenario that consist in building a HEI configuration using Scylla.

This paper introduces a human-friendly interface based on hand gesture recognition so as to endow the users with the ability to control various home appliances naturally at various places without individual remote controller for each appliance. Through the developed system, the user first selects the device that he/she wants to control by pointing it with his/her hand. Then, the user can command the operation of desired functions via 10 predefined basic hand motion commands. In order to complement the errors in recognizing the user's pointing directions, we adopt the concept of feedback by which the user can adjust the pointing direction and confirm the recognition result. The developed system complements some inconveniences of conventional remote controllers specially by giving additional freedom to persons with movement deficits.

This paper describes our experiences in collecting user data on human-robot interaction in nursing homes for the elderly. Learnings from two experiments were used to develop guidelines to support human-robot user studies with elderly users, in particular for experiments in an eldercare institution. Our experiences show that this demands a very strict organization, full cooperation by nursing personnel and extreme attention to informing the participants both before and during the experiment. Furthermore, first analysis of data from the studies suggests that social abilities in a robotic interface contribute to feeling comfortable talking to it and invite elders to be more expressive.

Building smart homes requires technology for monitoring activities which is accurate, and cheap. Monitoring a living environment through audio only is cheap, non-invasive and if we use wireless devices with a long lifetime such as sensor network nodes or motes, then it can also be easy to retro-fit in an existing home. Here we report our work on detecting events that occur in a domestic living environment using an audio source alone. Using data from only one microphone in an actual home we show how root mean square (RMS) of volume, which is cheap to compute, can detect most events though eliminating cross-talk from outside noise remains an issue to be overcome. We also outline how we are building cheap, wireless, power-efficient sensor nodes to realise the home monitoring described here.

In this paper we propose a new approach to human-centred system design, which is applied to the development of a ubiquitous multimodal dialogue system for a smart home. Our proposal takes into account three main features of a system: interaction management, user modelling and multimodal interface. We consider that user opinions about the system to be developed are crucial. Thus, we present the conclusions obtained from a survey we have carried out among the intended system users.

Demographic forecasts fo r the next few decades indicate that the numbers of over 65s are set to double throughout the developed and developing nations, peaking at around 40% of their populations, as their birthrates continue to fall substantially. As the aging population become larger, the birthrate fall and the workforce shrinks, the growing need for care services will have to be met by a greater reliance on assistive technologies to mitigate the effect of scarce physical health and social care services, coupled with greater reliance on information and communications technologies to support informed self help.

Smart home technologies allow for monitoring of senior residents and provide large datasets that pertain to activity levels, sleeping patters and other information describing the daily activities of the residents. These large data sets have to be processed and presented in a form that is usable and accessible to health care providers who need to have timely access to the data and make decisions based on the information provided. The focal point of this study is the facilitation of participatory design that allows nurses as end-users of the application to be involved in the system design. The setting is TigerPlace, a state-of-the-art senior independent living and care facility including 32 apartments. The aim of the study is to obtain nurses' feedback as end-users in the design of interfaces for the display of monitoring data related to the activity levels and sleep patterns of older adults.

Telemedicine for patient in residence, in particular remote monitoring of vital patients data – also called in France for last years “Télévigilance” – are one of the IST axes the most inclined to be developed in the next years. It concerns elderly persons, people with cardiac pathologies and persons in convalescence after hospitalisation, all needing a close medical supervision. A televigilance system for patients at home also allows a more reactive medicalisation remotely released by Urgency units (diagnosis, intervention). It corresponds to major concerns of hospital emergency bodies. Our proposed system is composed of three main components: (1) a terminal placed on the patient, continuously recording his physiological data, (2) an in-door reception base-station, processing physiological signals to detect emergency situation and create an alarm, which is retransmitted to the 3^rd component corresponding to a remote medical monitoring server hosted in the televigilance centre exploiting all these data to decide any intervention. This system can also be coupled to a fixed sensors system, coupled to the mobile patient's terminal, aiming at decreasing the risk of alarm identification error, namely in case of patient's falls. TelePat system has been technically validated from end-to-end, through its sensors, terminal and remote server parts.

This paper describes work in progress regarding personalized heart monitoring using smart phones. Our research combines ubiquitous computing with mobile health technology. We use wireless sensors and smart phones to monitor the wellbeing of high risk cardiac patients. The smart phone analyses in real-time the ECG data and determines whether the person needs external help. Depending on the situation the smart phone can automatically alert pre assigned caregivers or call the ambulance. It is also used to give advice (e.g. exercise more) or to reassure the patient based on the sensors and environmental data.

This project deals with technical assistance for persons of reduced mobility. We propose to study the technical, psychological and clinical impact of an original approach which consists of mounting a prehensile arm on to a mobile base. The use of this mobile unit in relation to patient's wheelchair is carried out on a master-slave basis. This study therefore has a pluridisciplinary nature: Science for the Engineer (Science Pour l'Ingénieur, known as “SPI”), Human and Social Science (Science Humaine et Sociale known as “SHS”) and Clinical. We will present a short synthesis of the various points which were approached during the three years of research on the above-mentioned project.

Medication adherence is a pervasive and difficult problem in health care that incurs tremendous cost in lives and general health, particularly among the elderly. We describe a two phase effort to develop a smart context-aware medication adherence system. In the first phase, a probe study was conducted by placing three existing reminder products in the homes of ten community-dwelling, healthy older adults to understand the contextual aspects of adherence and to inform the development of the system. We then describe the second phase of the research called CAMP (Context Aware Meds Prompting). We discuss the system that has been developed, and how we will demonstrate the efficacy of the system.

Stroke is the largest factor to severe disability in the UK, with the majority of cases linked to the elderly population. The SMART project aims to develop a home-based stroke rehabilitation system, that can provide support until maximum recovery has been achieved. This paper describes the design and development of the information and communication (ICT) platform, interface module and user feedback. Process and outcomes of User involvement in the development of the system are also described.

To many people, home is a sanctuary. For those people who need special medical care, they may need to be pulled out of their home to meet their medical needs. As the population ages, the percentage of people in this group is increasing and the effects are expensive as well as unsatisfying. We hypothesize that many people with disabilities can lead independent lives in their own homes with the aid of at-home automated assistance and health monitoring. In order to accomplish this, robust methods must be developed to collect relevant data and process it to detect and/or predict threatening long-term trends or immediate crises.

The main objective of this work is to design techniques for using agent-based smart home technologies to provide this at-home health monitoring and assistance. Specifically, we address the following technological challenges: 1) identifying lifestyle trends, 2) detecting anomalies in current data, and 3) designing a reminder assistance system. We discuss one such smart environment implementation in the MavHome project and present results from testing these techniques in simulation and with a volunteer in an apartment setting.

In this paper, we propose a non-quantitative logical approach to ADL recognition in a smart home, dedicated to Alzheimer's patients. Our formal framework for the recognition process is based on lattice theory and action description logic. Our framework reduces the uncertainty about the prediction of the observed patient's behaviour, allowing the assistant agent to anticipate the opportunities for assistance. This is achieved by dynamically generating the future potentially incoherent intentions of the patient, which result from the symptoms of their cognitive impairments (disorientation, memory lapse, etc.). This approach offers an effective solution to actual recognition of ADL in a smart home, in order to provide assistance to persons suffering from Alzheimer's disease.

Evaluation of the consequences of the development of a new technical device and of its implementation in a true-life setting is often difficult. We thereafter describe the methodology we used to implement a follow up of acceptability and ethic issues associated with the deployment of an experimental “Habitat Intelligent pour la Santé” (Health Smart Home) in an University Hospital Geriatric Long Term Care Unit.

This paper introduces novel techniques for person-centric services in pervasive spaces. These are focused on the support of independent living spaces for people with mild cognitive impairment, for example. We demonstrate from a technical perspective, how such services could be realised based on the emerging concepts of a distributed network of knowledge, facilitating dynamically composable and flexible service provision that engenders service continuity - beyond the home for example.

The National Institute of Information and Communications Technology of Japan completed a real-life test bed, called the “Ubiquitous Home,” for home context-aware service experiments in 2004. Various kinds of sensors are installed in this test bed to collect residents' behavior data and comprehend their situation. Phyno, a dialogue-based interface robot, intermediates between the the Ubiquitous Home and the residents. Three kinds of context-aware services were implemented: TV program recommendation service, cooking recipe showing service and forgotten-property check service. We have conducted a real-life living experiment with a couple of husband and wife in their sixties to evaluate the context-aware services and Phyno's ability. In this paper, we introduce the Ubiquitous Home and Phyno briefly. After explanation of the implemented context-aware services, the experimental results are presented.

Automatically determining the situation of an ad-hoc group of people and devices within a smart environment is a significant challenge in pervasive computing systems. Current approaches often rely on an environment expert to correlate the situations that occur with the available sensor data, while other machine learning based approaches require long training periods before the system can be used. This paper presents a novel approach to situation determination that attempts to overcome these issues by providing a reusable library of general situation specifications that can be easily extended to create new specific situations, and immediately deployed without the need of an environment expert. The architecture of an accompanying situation determination infrastructure is provided, which autonomously optimises and repairs itself in reaction to changes or failures in the environment.