Fig 3 - uploaded by Anders Kofod-Petersen
Content may be subject to copyright.
Source publication
A lot of research has been done in the area of context-aware com- puting. Even though, the term context seems often not to be well defined. We attribute this problem partly to the fact that research often focuses on syntactical and technical issues of contextuality and does not take a knowledge level per- spective on context. When including the kno...
Context in source publication
Context 1
... of AT in general can be found in the works of Vygotsky and Leont'ev [25,26,27] Activity Theory is a descriptive tool to help understand the unity of consciousness and activity. Its focus lies on individual and collective work practise. One of its strengths is the ability to identify the role of material artefacts in the work process. An activity (Fig. 3) is composed of a subject, an object, and a mediating artefact or tool. A subject is a person or a group engaged in an activity. An object is held by the subject and motivates activity, giving it a specific direction. Some basic properties of the AT are: -Hierarchical structure of activity: Activities (the topmost category) are composed ...
Citations
... Activity represents a set of related tasks. In applying activity landscape to analyse an e-work environment, we integrate activity landscape with the concept of activity theory [19, 20]. Activity theory provides a hierarchical structure for our actions and operations. ...
In the context of e-health, professionals and healthcare service providers in various organisational and geographical locations are to work together, using information and communication systems, for the purpose of providing better patient-centred and technology-supported healthcare services at anytime and from anywhere. However, various organisations and geographies have varying contexts of work, which are dependent on their local work culture, available expertise, available technologies, people's perspectives and attitudes and organisational and regional agendas. As a result, there is the need to ensure that a suggestion - information and knowledge - provided by a professional to support decision making in a different, and often distant, organisation and geography takes into cognizance the context of the local work setting in which the suggestion is to be used. To meet this challenge, we propose a framework for context-aware knowledge modelling in e-health, which we refer to as ContextMorph. ContextMorph combines the commonKADS knowledge modelling methodology with the concept of activity landscape and context-aware modelling techniques in order to morph, i.e. enrich and optimise, a knowledge resource to support decision making across various contexts of work. The goal is to integrate explicit information and tacit expert experiences across various work domains into a knowledge resource adequate for supporting the operational context of the work setting in which it is to be used.
... Activity represents a set of related tasks. In applying activity landscape to analyse an e-work environment, we integrate activity landscape with the concept of activity theory [12,13,8,9,10]. Activity theory provides a hierarchical structure for our actions and operations. At the highest level, activity acts as a meaningful and goaldirected frame for holding together actions and operations within a context [19], and for providing a coherent view of the interrelationships in a collaborative work environment. ...
In organisation-based work groups, experts often approach problem solving by combining explicit domain knowledge and information with their practice-based knowledge in ways that are largely driven by their specific work context. In collaborative ework, such common grounds for decision making offered by a shared work context hardly exist. Designing context-aware systems to support decision making in collaborative e-work, thus, poses a huge challenge because of the inherent difficulty in establishing a shared context of work and users adequate for supporting cohesive collaboration and knowledge sharing among experts across organisational and geographical boundaries. To address this problem, this paper proposes a framework, which incorporates an explicit model of context between the domain model of an application and the activity landscapes of various individuals, workgroups and organisations collaborating across borders, and between these landscapes and the knowledge resource space model in an intelligent ubiquitous environment. We argue that an explicit context model will enable a clearer understanding of the way experts integrate knowledge during problem solving, and thus provide common grounds for decision making and knowledge sharing during collaborative e-work. We demonstrate how a system based on our proposed model can be applied to support the reactive, collaborative and proactive modes of decision support in collaborative e-work.
... This part is concerned with notions such as roles, artefacts, and communities, and their relationships. For a thorough discussion on the use of Activity Theory for context modelling see [24,25]. This Basic Context Model is structured around a taxonomy inherited from the context-aware pervasive computing tradition [26]. ...
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.
... However, work has been initiated to implement this architecture to health care situations, such as ward rounds, where the reasoning capabilities of the system is to be thoroughly tested. This work will also use Activity Theory to model activities in health care, thus aiding us in constructing plans and Application Agents [21]. Parts of the UPML standard have not yet been implemented. ...
As users are becoming more mobile and information services are increasingly being personalised, the need for computer systems to adapt to the user is also increasing. One important aspect of this adaptation is the ability to solve problems in a dynamic environment. We propose a multiagent based approach to dynamically planning and problem solving. This approach allows for construction of plans based on available resources in the environment. We demonstrate the capabilities of this system by showing an implemented prototype.
... They can be used together to get a more complete model, but this is not always possible or even necessary. For example, in recent work we have investigated how Activity Theory alone can be used to model the knowledge needed in context-aware systems [13]. On the other hand, combining these three approaches allows modelling different aspects of human-computer interaction ranging from the socio-technical network to the design of the user interface itself on the knowledge level. ...
This paper addresses the problem of embedding explanation- aware intelligent systems into a workplace environment. We outline an approach with three different perspectives, focusing on the work process as a whole as well as user interaction from an interface and a system view. The theoretical background consists of Actor Network Theory, Semiotics, and Activity Theory. We further propose to integrate this workplace analysis into a design process for knowledge-intensive and explanation- aware Case-Based Reasoning systems.
... Context-awareness is defined as: "the awareness of facts or circumstances that surround a situation (or a chain of) events" 1 . Furthermore, we should note that the Environment is not limited to the device's immediate surrounding but also includes the user's spatial and temporal attributes [10] such as to-do tasks (shopping, laundry), events (meeting, lunch, party), reminders etc [9].Figure 1: Mind map describing the relationship between the entities of context-awareness A context-aware system also tries to build an understanding of other user's activity to provide context for its own ac- tivities [6]. We classify context-awareness as: ...
... The architecture should allow any pertinent data to be shared as context between users. Based on the classification provide by Petersen et al. [10] and Schmidt et al. [16] we re-enumerate factors pertinent to context-awareness in a social environment: 1. User's activity: based on life patterns (generic dailyschedule or repetitive schedules like, weekly beerdrinking with college buddies), emotional state, and spatio-temporal activities (such as reminders, to-do, events etc). 2. User's Social Environment: based on proximity to others, social interaction, relationships etc. ...
Modern mobile phones in the near future will adapt their applications, services, and look-and-feel based on their usage and environment. This ability of the devices to adapt based on user's context provides new challenges in areas of context sharing, context management, and in the associated area of privacy. Inadequate relationship models make control over disclosure impossible, which manifests itself in either sharing too much information -compromising ones privacy, or sharing too little -con-straining the use of context in a shared environment. In this paper, we define a new pseudo-hierarchical tag based relationship model to overcome the constraints of control over disclosure. Furthermore, we discuss some of the pit-falls of sharing context on user's privacy.
Recent research in pervasive computing and distributed decision support systems aims to enable users to share knowledge easily to support one another in problem solving in a manner that adapts to their varying contexts of work. However, existing approaches, most often, are restricted by formal models of task analysis and, as such, are not able to capture the informal work practices, which workers often adopt in problem solving, and which are largely dependent on workplace context, personal experience, available expertise, tools and technologies, and organisational and regional agenda. As a result, designing context-aware systems to support decision making in cross-boundary e-health poses a huge challenge because of the inherent difficulty in establishing a shared context of work and users adequate for supporting knowledge sharing and decision making among workers across organisational and geographical boundaries. In this paper, we propose a context model, which we refer to as practice ontology, to enable cross- boundary decision support in e-health. We describe how the context model is represented within the framework of an abstract cross-boundary collaboration model. We describe the practice ontology design and a prototype system based on the model using a clinical case study.
This paper presents the design of Cad Health, a system aimed at enabling knowledge and work practice transfer among clinicians across geographical, regional and workplace boundaries for effective clinical decision support in e-health. The system offers a unifying structure that allows clinicians to make sense of clinical work situations across regional and workplace boundaries in an e-health environment. The approach we have taken in Cad Health is motivated by the fact that 1) patterns of clinical work practice have been found to vary significantly across work settings, and 2) the contextual cues and practice-based knowledge, which are offered by common problem solving contexts in co-located work settings, and which enable clinicians, in such settings, to share information and knowledge to support one another's clinical decision making do not exist in e-health and other distributed work contexts. In particular, we highlight a number of user-informed design considerations, and describe the architecture and prototype of Cad Health.
In collocated organisation-based work settings, knowledge workers often approach problem solving by combining explicit domain information with their practice-based knowledge in ways that are largely driven by their specific work context. In virtual collaborative work, such common grounds for decision making offered by a shared work context hardly exist. Designing context-aware systems to support decision making in virtual collaboration, thus, poses a huge challenge because of the inherent difficulty in establishing a shared context of work and users adequate for supporting cohesive collaboration and knowledge sharing among individuals across boundaries. To address this problem, this paper proposes a framework, which incorporates an explicit model of context between the domain model of an application and the activity landscapes of various individuals, workgroups and organisations collaborating across borders, and between these landscapes and the knowledge resource space model in an intelligent ubiquitous environment. We suggest that as a result of the high level of knowledge required in collaborative e-work as well as its changing work contexts, e-work support systems need to provide not only information in the form of documents and articles, but also expert-level explanations in the form of supporting literature and references to theories and related cases, to justify retrieved information and offer cognitive support to e-work.
In order to realise the goals of e-health, future e-health systems will require the capability to support patientspsila information management and medical decision making in an open and dynamic ubiquitous medical environment. Such an environment will be knowledge-rich, and sensitive and responsive to the needs of patients, and will allow effective collaborative healthcare service delivery by virtual teams working across geographical boundaries. However, building intelligent systems to support collaborative decision making by virtual teams remains a huge challenge because of lack of appropriate infrastructure support in ubiquitous environments. In this paper, we present e-workbench, a prototype intelligent e-work support system, and demonstrate its potentials for supporting collaborative decision making in a ubiquitous medical environment.
