Anders Kofod-Petersen

Using activity theory to model context awareness

One of the cornerstones of any intelligent entity is the ability to understand how occurrences in the surrounding world influence its own behaviour. Different states, or situations, in its environment should be taken into account when reasoning or acting. When dealing with different situations, context is the key element used to infer possible actions and information needs. The activities of the perceiving agent and other entities are arguably one of the most important features of a situation; this is equally true whether the agent is artificial or not. This work proposes the use of Activity Theory to first model context and further on populate the model for assessing situations in a pervasive computing environment. Through the socio-technical perspective given by Activity Theory, the knowledge intensive context model, utilised in our ambient intelligent system, is designed.

Context: Representation and reasoning: Representing and reasoning about context in a mobile environment

Today the computer is changing from a big, grey, and noisy thing on our desk to a small, portable, and ever-networked item most of us are carrying around. This new found mobility imposes a shift in how we view computers and the way we work with them. When interaction can occur anywhere at any time it is imperative that the system adapts to the user in whatever situation the user is in. To facilitate this adaptivity we propose a two tier architecture. A middleware layer implementing a general mechanism for aggregating and maintaining contextual information. The second part offers automatic situation assessment through Case-Based Reasoning. We demonstrate a multi-agent system for supplying context-sensitive services in a mobile environment.

Contextualised ambient intelligence through case-based reasoning

Ambient Intelligence is a research area that has gained a lot of attention in recent years. One of the most important issues for ambient intelligent systems is to perceive the environment and assess occurring situations, thus allowing systems to behave intelligently. As the ambient intelligence area has been largely technology driven, the abilities of systems to understand their surroundings have largely been ignored. This work demonstrates the first steps towards an ambient intelligent system, which is able to appreciate the environment and reason about occurring situations. This situation awareness is achieved through knowledge intensive case-based reasoning.

Designing a reliable pain drawing tool: avoiding interaction flaws by better tailoring to patients' impairments

AbstractPatients with advanced cancer are influenced by the disease itself and by treatment side effects, both of which may have great impact on their lives. One of the most distressing symptoms is pain. However, pain in cancer patients can in most cases be relieved if the patient is able to communicate the nature and severity of the problem to the healthcare professionals through an effective assessment process. The main goal of this paper is to help form an understanding of central patient characteristics that should be taken into account when designing pain assessment tools for patients with advanced cancer. Traditionally, pain has been assessed by paper-based questionnaires and pain drawings. An iterative study was conducted based on repeated cycles of usability testing of a computerized pain body map for communicating pain by advanced cancer patients. Our aim was to provide a patient interface that most patients were able to interact with, collecting valuable, granular pain information with a minimum of strain on the patient. Through this process, we identified and solved design issues related to the sickest and frailest cancer patients. We further created a web-based solution for collecting individual pain drawings for evaluation by clinicians. The concept was appreciated by the patients, and the information provided was considered valuable by physicians. The main contribution of this paper is a list of suggestions to guide the design of an interactive tool for patients with advanced cancer.

Explanations and context in ambient intelligent systems

Ambient intelligent systems are context aware by perceiving and reasoning about their environment, they perceive the needs of their users and proactively respond to these needs by being context sensitive. Users do not interact with these systems by traditional means only, but also through behavioural interfaces. This combination of mixed initiative systems and unconventional interfaces puts strong requirements on the explanatory capabilities of any system. The work presented here focuses on explaining the behaviour of an ambient intelligent systems to its users. It demonstrates how explanations can be combined with context to deal with the different types of explanations that are required for a meaningful interaction of a system and its users.

ESUMS: A mobile system for continuous home monitoring of rehabilitation patients

The pressure on the healthcare services is building up for several reasons. The ageing population trend, the increase in life-style related disease prevalence, as well as the increased treatment capabilities with associated general expectation all add pressure. The use of ambient healthcare technologies can alleviate the situation by enabling time and cost-efficient monitoring and follow-up of patients discharged from hospital care. We report on an ambulatory system developed for monitoring of physical rehabilitation patients. The system consists of a wearable multisensor monitoring device; a mobile phone with client application aggregating the data collected; a service-oriented-architecture based server solution; and a PC application facilitating patient follow-up by their health professional carers. The system has been tested and verified for accuracy in controlled environment trials on healthy volunteers, and also been usability tested by 5 congestive heart failure patients and their nurses. This investigation indicated that patients were able to use the system, and that nurses got an improved basis for patient follow-up.

Learning in an Ambient Intelligent Environment - Towards Modelling Learners through Stereotypes

E-learning in higher education faces challenges related to variation and personalization, after a decade of attention to learning objects and computer-supported collaboration. The main objective of the thesis is to investigate how to assure the quality of the development process of e-learning applications by the implementation of pedagogical principles into the software design process. Specifically this includes the pedagogical principles of individualization, variation, meta-learning and best practice. This thesis contributes to the field of e-learning by four main contributions (C1-C4): C1: Design pattern-based wizards to implement best practice The first main contribution of the thesis is the idea of using pedagogical design patterns as a basis for the development of wizards in e-learning applications. Design patterns are archetypes on well-used solutions and enable the implementation of best practice and the expertise of experienced online teachers into the application. In the process of a pedagogical and technological configuration of an application, the design pattern-based wizard provides an interface presenting pedagogical opportunities, hints and comments to novice online teachers.C2: The E-learning Circle The E-learning Circle is a software design tool, assuring the quality of the design process of e-learning applications, focusing on variation, individualization and meta-learning. It consists of a number of concentric circles, which are divided into three sectors; student, teacher and learning objectives. The inner circles cover pedagogical considerations, while the outer circles specify how the pedagogical theories may be implemented with technology. The strengths of the E-learning Circle are the compact presentation combined with the overview it provides. It is also useful in dealing with complexity, providing a common language and embedding best practice. The E-learning Circle is not a prescriptive method, but is useful in several design models and processes. It represents a holistic approach to the design of e-learning applications and prevents the overexposure of e.g. learning objects or assessment in an e-learning system.C3: The E-learning ontology The E-learning ontology is a contribution to the need of a formal representation of a set of concepts and the relationships between those concepts within the e-learning field. This is necessary when planning to use topic maps as a HCI-solution within e-learning. The E-learning ontology suggests a representation of topics useful for developing topic maps and illustrates an approach how to develop personalized e-learning applications.C4: The PLExus prototype The PLExus prototype is a working prototype of a personal learning environment based on the semantic technology of topic maps. PLExus provides a student interface allowing customized views of learning objects and learning activities. The customized views are mainly based on pedagogical methods, learning objective types and proficiency stages. PLExus provides a wizard for the teacher in the process of adding and structuring learning objects into the topic map. The research method of this thesis is Grounded Theory. This inductive, theory discovering approach allows the grounding of theory in empirical data and is appropriate for the exploratory nature of this thesis. The empirical data of the thesis were collected through 21 interviews, three focus groups, and three expert groups.

Proceed with Caution: Transition from Paper to Computerized Pain Body Maps☆

Abstract Patients with advanced-stage cancer often have a high symptom burden and reduced functional status, implying that the patients themselves should be involved in development and testing of interactive assessment tools. This paper reports on an assessment of use of a pain tool, which led to changes in both medium and program in order to adapt to the patients’ needs and abilities. Our study shows how a change in medium for pain assessment from paper via laptop to iPad affects the interaction with the tool on important aspects of use. We also show how changes of medium affect the readability of the output for health care workers. We achieved better results with an iPad-based pain assessment tool developed through user-centered design compared to both a paper-based and conventional laptop-based tool.

Elicitation of Quality Characteristics for AAL Systems and Services

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.

The Non-Accidental Tourist:Using Ambient Intelligence For Enhancing Tourist Experiences

An Ambient Intelligent environment is aware of the presence of a person, perceives her needs and responds intelligently. Ambient intelligence can be used to guide a tourist through the city in such a way that is mutually beneficial for both the tourist and the city. The composite set of services delivered to a tourist can be personalized. This adaptive behaviour is best supported by Virtual Enterprises that are formed dynamically, at runtime. This paper considers an Ambient Intelligent scenario from the service providers’ perspective and discusses how such scenarios can be realized through Virtual Enterprises.