See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/228688210
Building an Agent Based Community Care
Demonstrator on a Worldwide Agent Platform
Article · August 2003
DOI: 10.1007/978-3-0348-7976-7_3
CITATIONS
READS
4
25
3 authors:
Martin D. Beer
Richard Hill
90 PUBLICATIONS 606 CITATIONS
115 PUBLICATIONS 322 CITATIONS
Sheffield Hallam University
SEE PROFILE
University of Derby
SEE PROFILE
Andrew Sixsmith
Simon Fraser University
134 PUBLICATIONS 1,646 CITATIONS
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
Multi Agent Systems for Educational Uses View project
All content following this page was uploaded by Andrew Sixsmith on 13 January 2017.
The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the original document
and are linked to publications on ResearchGate, letting you access and read them immediately.
Building an Agent Based Community Care Demonstrator
on a Worldwide Agent Platform
Martin D. Beer
Richard Hill
Andrew Sixsmith
School of Computing &
Management Sciences
Sheffield Hallam University
Sheffield, United Kingdom
School of Computing &
Management Sciences
Sheffield Hallam University
Sheffield, United Kingdom
Department of Primary Care
University of Liverpool
Liverpool, United Kingdom
m.beer@shu.ac.uk
r.hill@shu.ac.uk
ABSTRACT
This paper describes a project designed to show how a global
multi-agent architecture can be used effectively to support
care in the community. Services in this area are notoriously
difficult to coordinate with the direct and indirect involvement of a large number of independent, autonomous agencies, each of which has its own priorities and aspirations.
Also, by the very nature of the services provided the caring
community is highly mobile and distributed making the collection and dissemination of information extremely difficult.
The Integrated Community Care (INCA) project has been
designed to show how multi-agent technology can be used
effectively to address some of these issues in a timely and
cost-effective manner. The flexibility provided by such an
architecture allows an integration of services based on a regularly updated Individual Care Plan in a way that has been
very difficult to achieve in practice. This increased flexibility not only allows the better customisation of the care to
the current needs of the client but also provides an effective
means of recovery when things go wrong.
1.
INTRODUCTION
The need to support the elderly and disabled population
in the community is widely recognised, however managing
the care provision and health of such a group by established
means is highly resource intensive. For example, about 13%
of the European population are currently aged over 65, with
about 7% aged over 75 years. In the UK, there will be 1.2m
people aged 85+ by the year 2000, an increase of 30% over
a ten year period. Expectations for the EU-wide population
are that around 30% of people will be aged over 65 by 2025.
This growth, and the physical distribution of the population,
severely limits the future effectiveness of conventional health
and ability assessment methods.
Recent years have seen a shift in focus in the services provided to older and chronically sick people from institutional
sixsmith@liv.ac.uk
care to care in the community. Community Care is typically
provided by a range of independent organisations and agencies, each needing to meet its own targets and objectives
and to integrate the service with their other responsibilities
in a coherent and efficient manner. This often leads to serious service inefficiencies, as there are inadequate systems
in place to share relevant information without compromising the security of the information held. Another factor is
that a considerable amount of community support is provided by informal carers who are excluded from the general
care management system because of difficulties in integrating them without breaching the official confidentiality requirements. The growth of an effective open agent network
such as AgentCities [20] allows effective co-operation (information sharing and communication between autonomous
information systems) to take place without compromising
the security of the client and the agencies involved. Since
each agent has complete autonomy it can respond according to the rules of the organisation it represents, providing
an effective and assured guardian that is totally under that
organisation’s control.
In this paper we describe the principles behind a distributed multi-agent-based Integrated Community Care (INCA)
system. A demonstrator system, implemented using the
ZEUS agent-building toolkit [16] is also described in order
to demonstrate the feasibility of the approach and its potential practical benefits. This demonstrator shows that the
technologies proposed allow effective communication without compromising integrity and privacy. In particular they
allow an approach to be taken that allows minimum collection of information in that the Home service agent can be
configured so that it only releases private or sensitive data
in case of an emergency, when such information is of value.
The objective of the INCA Project is to investigate how
community care can be developed in the internet age through
the use of multi-agent technology. The motivation for this
has been a consideration of the agent society’s social abilities
in:
• Promoting effective care systems that:
Permission to make digital or hard copies of all or part of this work for
personal or classroom use is granted without fee provided that copies are
not made or distributed for profit or commercial advantage and that copies
bear this notice and the full citation on the first page. To copy otherwise, to
republish, to post on servers or to redistribute to lists, requires prior specific
permission and/or a fee.
Copyright 2001 ACM X-XXXXX-XX-X/XX/XX ...$5.00.
– provide better services and resources to clients,
– enhance social interaction between them, and with
their carers
– deliver more effective care
• Providing the high-abstraction level care management
strategies by linking all relevant agencies into a single
framework of accountability.
• Giving an in-depth understanding of the health information framework that underpins the delivery of high
quality, effective community care, including the formularisation of the links between the disparate agencies
involved.
• Establishing a single agent-based care monitoring facility that can be used by all care professionals to assist
in effective monitoring and diagnosis.
• Developing cooperative structures within the community structures to change service provision and care
policies through the use of automated agents involvement in planning, scheduling, organising (both formal
and informal) care and even directing care service programs.
• Devolving care management and responsibility to those
providing the care by providing shared supervision and
teamwork and by separating the organisational from
the social requirements, developing a much more responsive and client centred environment that adapts
rapidly to changing needs.
Some of these objectives have already been investigated in
the medical domain through the use of multi-agent system
architectures. For example, the GUARDIAN system [10]
considered patient monitoring in a Surgical Intensive Care
Unit. Support is provided for collaboration among specialists, each an expert in a specific domain but fully committed to sharing information and knowledge among each other
and the nurses that continuously monitor the patient in the
physicians’ care. A system devoted to diabetes care has been
presented, where cooperation not only between the medical
specialists, but also others, such as administrators is supported within the agent community [13]. An agent-based
system has also been described that supports collaboration
among general practitioners and specialists about patient
healthcare [11].
A more general agent-based telemedicine framework has
been reported [5] that can assist specialists in diagnosing
difficult cases through information sharing, cooperation and
negotiation. In this case each specialist has their own Telemedicine-Oriented Medical ASsistant (TOMAS) agent that
behaves as a medical assistant and has two generic functions:
• an agenda for managing appointments, and
• methods for access to patient records.
Support for tele-medicine is given by software features for
remote exchange of patient data, cooperative annotation of
cases and negotiation of appointments. These approaches
have been greatly assisted by moves to standardise medical information through attempts to formalise patient and
other records [6]. Some of the flexibility offered by the mobile access to records and services is being demonstrated
by the Ward-in-Hand project[1], but only in the relatively
restricted environment of a conventional hospital ward.
The INCA project aims to take these forward from the
purely medical domain and integrate them into the general
community care environment, where the linkages are less
formal and effective cooperation and negotiation is essential
if appropriate care is to be delivered. A major difference
is that it is rarely possible to share information as freely
as within the purely medical domain because of the involvement of different agencies and individuals with widely differing requirements. The agent community therefore has to act
as a coordinator and filter to ensure that appropriate and
correct information is distributed to all concerned. Also,
since help is likely to have to travel some distance it is often
better to provide whatever assistance is readily available in
a timely manner, rather than the optimal solution that may
arrive too late.
2.
OBJECTIVES OF THE DEMONSTRATOR
This paper describes a demonstrator that uses multi-agent
technology within such an open networked agent environment as a means of enhancing the mechanisms for the systematic and widespread assessments of the health of the
elderly out-side of a conventional clinical care regime. Enhanced assessment will provide valuable and timely source
of information and knowledge that will enable the optimisation of care provision and management. Non-invasive assessment technology can also provide a source of health information that is well suited to identifying subtle, yet important, changes in an individual’s condition. When this is
combined with appropriate knowledge sources available elsewhere on the agent network it can trigger pre-emptive care
and treatment. [9] Appropriate care can then be provided
in a timely manner so that it can be most effective. Agents
can also communicate across the network to proactively provide information of interest to combat social isolation and
exclusion.
The specific approach taken towards this problem is to
develop and evaluate technologies suitable for relating behaviour in the home to information and knowledge sources
that health management professionals require. The demonstrator explores the following three functional elements:
Within-home monitoring techniques The objective is
to develop devices that can be readily integrated into
existing home environments. Such technology may be
passive such as movement monitors, etc. However, we
shall also focus on explicitly designed assistive technologies for communication, mobility and environmental control, which are also important. The value of
using assistive technologies, as a means of monitoring
behaviour is that the data generated is semantically
richer and better suited to comparison between individuals. [8]
Automated Log Analysis Usage data can be retrieved
via an established communication mechanism, and automated analysis techniques will be developed to provide preliminary information on end-users activities.
The key requirement of the analysis is to provide data
abstractions that are relevant and meaningful to care
professionals, both in terms of an individual’s behaviour
and in terms of in community status as a whole.
Agent based knowledge management The AgentCities
network can be developed to provide mechanisms for
aiding the review care for specific individuals and at
the community in general, and directing care management and delivery.
MODEL OF
CARE
Direct Care
Activities
Indirect Care
Activities
Organizational
Activities
Routine
Assessbbment
Marketing
Emergency
Planning
Personnel
Quality of
life
Quality
assurance
Financial
Figure 2: The Basic Components of the INCA Architecture
describes the Individual Care Plan as:
’not simply a ’basket of goods and services’, it
is a complex set of human relations, and the
achievement and maintenance of which requires
skills, both in the negotiation and management
of change’ [p61]
Management
Figure 1: High Level Activity Model of Care
3.
THE CARE ENVIRONMENT
Current health and social care policy reflects the view
that most older frail or disabled people would prefer to live
in their own homes rather than in hospital or nursing home
settings. ”Community care” refers to the range of services
delivered in the person’s own home or community setting, in
order to help them to continue to live independently. Typical services include home helps, meals, domestic help and
community medical and nursing services.
Although the humanitarian perspective is compelling, the
delivery of community-based services presents a number of
organisational, managerial and logistical problems that undermine the effectiveness and efficiency of services. While
community care has typically involved limited use of information technology, recent developments have seen significant application development, a trend that is likely to
significantly develop in the future. An information technology within community care currently involves a number of autonomous systems; home monitoring, community
alarms, care management systems and emergency systems
command and control systems. Each element of care is provided by different autonomous bodies, which maintain their
own individual management information systems. The overall management of the care typically resides outside of these
systems, protecting individual bodies from disclosing sensitive and irrelevant information. Key to the development of
a proper care regime for any client is the Individual Care
Plan that provides the link between the client’s needs and
the means by which they should be met. This not only includes the Direct Care activities normally associated with
community care and discussed elsewhere [3], but also the
indirect and organisational activities as showen in Figure
1. These need to be reviewed and updated continuously
as the client’s requirements change both by monitoring and
analysis of information collected [8] and through negotiation
between the agencies, as appropriate. Indeed McDonald [14]
Its preparation is therefore a complex process that requires
flexibility and support for contingencies so that the necessary services are provided in a timely and efficient manner.
Figure 2 gives the basic components of this process.
4.
REASONS FOR AN AGENT APPROACH
One area that is critically dependent on the ability to negotiate appropriate solutions effectively is Community Care.
The move towards franchising of different aspects of care
delivery with the responsible agency (in the United Kingdom this is usually the Social Services Department of the
Local Authority) being responsible for preparing a detailed
specification, in the form of an Individual Care Plan. It
then contracts various agencies to actually deliver the various components of the care, as appropriate. There is now
no single agency with the overall authority to plan, manage,
deliver and monitor the provision of community care, and
so no single control authority and network. To this must
be added the various health care services, and the emergency services, each of which have their own independent
records and command and control structures, but are essential components in the delivery of the overall package.
In addition, there are the large numbers of informal carers
(family, friends, neighbours etc.) who are currently almost
totally ignored by the system, but provide invaluable support. Jennings et al. [12] in reviewing the ADEPT project
interpreted organisations as distributed federated structures
incorporating competition and coordination and proposed
that agent architectures are highhly suitable for mirroring
this structure. This is basically the approach taken by INCA
but care has to be taken not to take this analogy too far as
for example when Symonds and Kelly [19] talk about the
’myth of the market’ since in our case:
• the prime consumers (the Clients are not the actual
purchasers
• occupational regulation overrides market regulation
• legal obligation overrides market opportunities
• risk to others makes it a social issue rather than an
individual matter.
All these are prime research issues for the agent community
and need to be addressed if widespread deployment of any
but the most basic trading agent-based solutions are to come
about. In particular, the AgentCities approach can:
5.
THE AGENT ENVIRONMENT
An agent mediated approach makes it possible to integrate
the existing care systems in a way that makes cooperation
natural between highly heterogeneous agencies, since only
the communication now has to be standardized. It allows
• Replace conventional technology, such as existing telephone- the INCA system to interface directly to a wide range of exbased services [7]
isting databases, knowledge bases and control systems that
are already in place. The much broader care picture can
• Integrate specific functions into a single, comprehentherefore be monitored effectively, and is of great help to
sive, framework for service delivery. The end users will
care managers in developing the most effective and efficient
then have a single access point to services, rather than
care programme for each individual, including the eliminathe piecemeal approach currently adopted.
tion of unnecessary duplication of resources.
Ensuring that the most appropriate assistance is provided
• Enhance information sharing between all parties in a
in reasonable time is a significant focus of the research. The
controlled and open manner through the interoperavarious potential agencies have differing capabilities and can
tion and cooperation of different sets of agents from
respond in various ways, and in differing time frames, each
different communities.
having its own defined cost. Depending on the nature of
the incident to which a response is required a decision as to
• Develop new services, particularly those aimed at enthe most appropriate response has to be arranged. This will
hancing quality of life. These may well include more
require multi-dimensional negotiation at a number of levels
general services from other service providers and agent
if acceptable levels of service are to be assured. The current
communities.
arrangements have great difficulty with this as only limited
information is available. It may for example be appropriate
• Provide flexible, rather than dedicated, solutions, which
to notify an informal carer who can respond rapidly because
are readily customisable to an individual’s changing
they are close to the scene either in place of or in addition
requirements.
to a professional carer or the emergency services so that at
least some assistance is available at the scene. This more
The objective is to provide a very much more responsive
sophisticated approach can only work effectively with full
and effective service. If each has to rely on only its own inforcooperation and information exchange between all parties
mation valuable time and resources will inevitably be lost in
involved.
duplicating actions. Even a minimal level of co-ordination
The issue of timely intervention when delivery of the ascan therefore be extremely valuable. It must however be
sistance promised fails also needs to be addressed, in that
managed effectively to:
the appropriate agent must identify the anticipated failure
as soon as the problem becomes evident. It must then at• Maintain the autonomy of all agencies
tempt to renegotiate its commitment, either by finding another agent that will take it on, or by making a revised
• Maintain the privacy of the older person as far as poscommitment. The agent can then develop a record of the
sible
reliability of the various agencies and build this into its negotiating strategy. The process of negotiation is not as well
• Ensure the security and integrity of the information
founded in conversation theory as request and response exheld
changes, because there are much many more conditions that
may apply. In the case of the INCA project these are simpli• Link with others involved (such as informal carers),
fied somewhat as it can be expected that all agents will use
who do not have their own systems, but are a valuable
their best endeavours to meet all commitments that they
part of the total care package.
enter into. This simplifies the analysis, without losing too
much generality.
The AgentCities approach adopted in the demonstrator:
A major advantage of this approach is that the Home Unit
(and sensors attached to it) can provide a range of services,
• Effectively separates out actions that require different
rather than just one, as in the case of a Home Alarm or simscenarios to be followed
ple monitoring unit. Services can be added, modified and
removed as required, providing a very high level of flexibility
• Provides an effective means of co-ordinating separate
so that the changing requirements of the Older Person can
autonomous agencies through integration with their
be met in the most effective manner. This flexibility also exown systems
tends to the various care agents who may be linked through
their existing command and control systems or through spe• Allows additional information to be added through the
cial mobile agents or both, depending on their position and
use of mediators and agent-based negotiation stratecurrent status. This approach follows that outlined by Beer
gies, based on the established need, in the form of an
et al. [2]
Individual Care Plan.
• Effectively integrates informal carers into the planning,
delivery and monitoring of care, even though they do
not themselves have either the use of or access to complex planning and control systems.
6.
THE PROBLEM AREA ADDRESSED
While community care covers a wide range of activities,
four basic scenarios are considered in this paper, chosen to
illustrate the effectiveness of the agent-based approach in
developing a fully cooperative environment for providing the
care required:
1. The development and updating of an Individual Care
Plan. Care Planning is the specification of a package
of care services according to an assessment of the needs
of the individual.
2. The monitoring of the effectiveness of that Individual
Care Plan
Table 1: The Actors
3. Responding to failure to deliver the specified care in a
timely and effective manner
4. Reviewing the Individual Care Plan so that it continues to meet the objectives and desires of the client.
NAME
Care co-ordinator
A number of organisations and individuals play a part in
these activities. They can be grouped effectively into groups
of actors, as shown in Table 1. The interactions between
these actors can then be shown in the form of Use Case
diagrams.
6.1 Developing an Individual Care Plan
Before care can be provided effectively, the care co-ordinator
has to assess need, and develop an individual care plan that
meets the older persons requirements. This can be quite difficult, particularly with the severely disabled or those with
dementia. If assessment is undertaken at an assessment centre it ignores the specific circumstances and problems that
occur in the home environment. However observation of a
person in their own home requires considerable resources if
an effective result is to be achieved. The monitoring facilities
of the INCA system provide an effective means by which this
assessment can be made within the client’s familiar environment, which can be further refined as additional information
is collected.
A significant part of the assessment is determining what
the overall objectives of the care regime are to be. These
may include enhancing the quality of life by for example
maintaining or improving one or more of:
Care provider
Informal carer
• physical health and wellbeing
• emotional or mental health
• peace of mind
• safety and security
• practical support
• personal care
• personal finances
• control over day-to-day life
• reduction of risk
as well as rehabilitation outcomes such as:
• regaining skills and capabilities
• improving confidence and morale
• improving the ability to go out
• reducing symptoms
Client
DESCRIPTION
The agency responsible for providing
the range of services necessary to ensure that the Older person is properly
cared for. The Care co-ordinator is responsible for preparing a Care plan and
for monitoring its effectiveness in meeting the needs of the Older person. This
is often the Local Authority or some
other official body with a legal duty to
provide the necessary care.
The various agencies and individuals
responsible for providing the care specified by the Individual Care Plan. This
will include Social Workers, Health
Care Professionals, Care Assistants,
Emergency Services, Social Services
etc. who can provide and extremely
wide range of care services, if required.
The various relatives, friends, neighbours etc. who provide some form of
support and assistance in an informal
way (i.e. outside the Individual Care
Plan), but is often essential to allow
the older person to remain living at
home. This is often flexible and responsive and can range from totally unstructured and so not recognised at all
in the Individual Care Plan through
to fully recognised and integrated with
the efforts of the professional carers.
The person who lives in their own
dwelling (either an ordinary house or
a sheltered home) and who receives
a package of community care services.
This package may range from very minimal interventions, such as social alarm
systems, through to an intensive mix of
community support services.
Invite Tender
Care Provider
Care Provider
Arange Cover
Negotiate
Informal Carer
Make Contact
Speciy services required
Select Provider
Notify assesment
Informal Carer
Assess needs
Inform
C|lient
Call Centre
Care Coordinator
Client
Figure 3: Individual Care Plan Development
Decide if Cover Needed
Monitor
Intervene
IIndividual Care Plan
Figure 5: Responding to Failure
Update Intervention Log
Internal Carer
Care Provider
Liase
Care Coordinator
Check Interventions against Schedule
Client
Figure 4: Monitoring the Individual Care Plan
This means that the care regime needs to be developed continuallyt as the balance of these objectives changes. Also,
the choice of carer depends not only on their own capabilities but also on the current set of objectives that the
Care Coordinator wishes to achieve. This makes the choice
of carer not just a simple resource allocation issue, bu one
where quite complex negotiations both with the client and
the carers may be required.
The INCA architecture also allows informal carers to be
recognised as an integral part of the care regime and for
them to be properly informed at all stages. This is important as many of the objectives outlined above can be
best achieved by close friends and family, but this must be
recognised within the framework otherwise considerable duplication of resources will ensue. This is a major issue with
current care systems, where they are often effectively ignored.
The stages in doing this are shown in Figure 3.
6.2 Monitoring the Care Plan
Once the care plan has been established it needs to be
continuously monitored, and regularly reviewed, otherwise
the care regimewill rapidly drift away from meeting the real
needs of the client. The INCA architecture provides for this
by continuously monitoring both the client and the care interactions, and identifying when further intervention is required.
Figure 4 shows the interactions involved in informing all
concerned of the care required at any time.
6.3 Responding to Failure
In any system dependent on such a wide variety of autonomous individuals, there are inevitably occasions when
the necessary levelof care, as specified in the Individual Care
Plan can not be delivered at the time specified. This can
range from a particular carer being held up in traffic to serious problems that put the safety and wellbeing of the client
in jepordy. Contingancy arrangements havre therefore to be
included, that are triggered as soon as the potential failure to
meet the care obligations is identified. Agent architectures
can be shown to perform well in this respect, without developing serious instabilities that would affect large numbers
of other individuals. This is important both for maintaining
the stability of care to all clients and for scalability reasons.
Figure 5 shows the interactions involved.
6.4 Reviewing the Care Plan
Finally we need to consider the processes required to review the Individual Care Plan as shown in Figure 6. Considerable volumes of information are being generated continuously about both the client and the operation of the care
regime. When the safety and security of the client is assured,
much of this information will simply stay in the Home Unit
where it will be used to identify longer-term trends. When
ann issue arises, not only will an emergancy response be
triggered to deal with the immediate problem, but the diustributed agent architecture also provides for the Individual
Care Plan to be reviewed. Since different information is required for this purpose than for immediate response to the
initial emergancy the data filtering and knowledge synthesis capabilities of an agent-based information system come
directly into play [17][18].
7.
USING THE DEMONSTRATOR
The current demonstrator deploys home agents across the
Agentcities network. They then communicate with the rest
of the agents on the main platform. Potential users can
download the necessary code to deploy their home agent
from the project web site. They then need to install this in
their own version of the Zeus agent plqatform [16] and when
the full set of local agents are started communication is es-
5. differing configurations to deal with a range
of circumstances. For example, the monitoring facilities could be used in burglar
alarm mode when the property is unoccupied and carers could be informed as appropriate to avoid wasted journeys.
Informal Carer
Client
Monitoring
uses
Care Provider
Trigger
uses
Assess
Care Coordinator
uses
Sespecify Package
Figure 6: Reviewing the Care Plan
tablished with the INCA server and a minimal Individual
Care Plan is prepared. This deals solely with the handling
of emergancy alerts which are routed directly to the Emergancy Services. The system is thus able to respond to basic
requests for help immediately. Once this initial plan is entered in the database the user is able to access it through
a web interface that allows it to be modified as required to
meet individual need and the home unit agent can be used
to assess the effectiveness of the INCA architecture to meet
that need.
8.
FURTHER WORK
There are a number of additional agents that could benificially be deployed to demonstrate the capabilities andf flexibility of the INCA architecture. These might include:
The mobile agents are already under development using the
JADE/LEAP platform. These will deploy to PC hosted
simulators for typical mobile devices in the first instance.
Whether we shall be able to allow free deployment in the
same way as the home unit agent will depend on the licens
restrictions imposed on us by the various software suppliers.
Current intention is to allow free deployment of as many
different types of agent as possible so that we gain a wide
evaluation of the technology from as many potrential users
as possible.
The current demonstrator is concerned primarily with the
delivery of a specified service level. It therefore deals with
the communication and negotiation between the various interested parties rather than the detailed operation of the
sensor networks in the home. There are other projects that
are concerned more directly with this.[4][8]
9.
CONCLUSIONS
The INCA project can now demonstrate the effective deployment of a set of agents designed to cooperate in the
timely and effective delivery of community care across the
Agentcities network. The cooperative activities are very different from the trading situations that have been studied
extensively, and so this project gives very different insights
into the design and construction of large-scale multi-agent
networks. In pareticular we can study:
• the architectural consequences of using an open multiagent system to support an application domain that
requires high levels of reliability and security
• the interactions between the various autonomous information sources and the architectural requirements for
their reliable interoperation with the various agents.
This brings us into the area of Web Services and will
allow us to inform the debate on how such services
should be built and integrated.
1. mobile agents that emulate wireless connected
Personal Digital Assistants (PDAs) that can
demonstrate the communication possibilities
for the various care workers involved
• the use of mobile and static agents to deliver the necessary services and the implications for doing this on
a global platform
2. a global monitor that shows the home agents
connected and their status at any time. This
is likely to be Web based and be linked to
the pages that allow modification of the Individual Care Plan.
• scalability issues as any realistic scenario for deploying
INCA would require the linking of thousands of home
units and hundreds of carers. We need to study the
behaviour of networks of this size before we can even
think of trying to deploy such agents.
3. customised help and information services based
on information agents that know of the client’s
interests and requirements. This can have
a considerable benefit in combatting social
isolation.
4. monitoring facilities not only for the home,
but also for the carers so that the client
knows when to expect them, and is kept
fully informed of any necessary changes in
plan.
The use of a general agent network architecture means
that agents can be deployed on existing and future agent
architecture without the necessity to construct independent
architectureal frameworks as has previously been the case.
As more facilities and services become agent based they can
be readily integrated into the INCA framework in a way
that is just not possible with existing community care frameworks. The current demonstrator intentionally does not use
security features that are becoming available on agent platforms, as it is intended as a testbed with which to investigate some of the issues discussed in this paper. The use of
a standard agentView
architecture
and a readily available agent
publication stats
development platform means that such features as this, and
many others can be added very quickly when standards are
agreed and they are added to the development environments.
10. ACKNOWLEDGEMENTS
The programming of the demonstrator has been undertaken by Iain Anderson, Wei Huang an Philip Doherty as
part of the project work required within their degree studies. The project is also in receipt of an Agentcities Deployment Grant from the European Union Agentcities.rtd
project (IST-2000-28385).
11. REFERENCES
[1] M.Ancona, E.Coscia, G.Dodero, M.Earney, V.Gianuzzi,
F.Minuto, S.Virtuoso (2001)”Ward-In-Hand: wireless
access to clinical records for mobile healthcare
professionals” Proc. TEHRE 2001 m-Health
Conference, 1st Annual Conference on Mobile &
Wireless Healthcare Applications, 11 - 14 November
2001, London, UK.
[2] Beer, M. D., Bench-Capon, T., & Sixsmith, A. (1999b),
’The Delivery of Effective Integrated Community Care
with the aid of Agents’, Proceedings of ICSC99, Hong
Kong, December 1999. (Lecture Notes in Computer
Science 1749, Springer-Verlag pp303-398)
[3] Beer, M. D, Huang W. & Sixsmith, A. ”Using Agents
to Build a Practical Implementation of the INCA
(Intelligent Community Alarm) System”, in L. C. Jain
& Z. Chen, & N. Ichalkaranje, ”Intelligent Agents &
their Applications”, Springer (2002), pp320-345.
[4] Celler, B. G.,Earnshaw, E. W., Ilsar, E.D,
Betbeder-Matibet, L., Harris, M. F., Clark, E. D.,
Hesketh, T. and Lovell, N. H. (1995), Remote
monitoring of health status of the elderly at home: A
Multidisciplinary Project on Ageing at the University
of NSW, Int. Journal of Biomedical Computing, vol.40,
pp147-155.
[5] Della Mea, V., (2001), ”Agents acting and moving in
healthcare scenario: a paradigm for telemedical
collaboration”, IEEE Transactions on Information
Technology in Bioscience, 5, 10-13.
[6] Department of Health (2001), Building the Information
Core: Implementing the NHS Plan, January 2001.
[7] Fisk, M. (1989), Alarm Systems and Elderly People,
Planning Exchange, London.
[8] Haigh, K. Z., Phelps, J. & Geib, C. W., (2002), ”An
Open Agent Architecture for Assisting Elder
Independence”, in The First International Joint
Conference on Autonomous Agents and MultiAgent
Systems (AAMAS), pages 578- 586. July 2002.
[9] Haigh, K. Z. & Yanco, H., (2002), ”Automation as
Caregiver: A Survey of Issues and Technologies”, in
AAAI-02 Workshop on Automation as Caregiver: The
Role of Intelligent Technology in Elder Care, pages
39-53. July 2002.
[10] Hays-Roth, B., and Larsson, J. E., (1996), ”A domain
specific architecture for a class of intelligent agent
monitoring systems”, Journal of Experimental and
Theoretical Artificial Intelligence, 8, 149-171.
[11] Huang, J., Jennings, J. R., and Fox, J. (1995), ’An
Agent- based Approach for Distributed Care
Management’, Applied Artificial Intelligence: An
International Journal, vol. 9, no. 4, pp401-420.
[12] N. R. Jennings and T. J. Norman and P. Faratin
(1998), ’ADEPT: An Agent-based Approach to
Business Process Management’, ACM SIGMOD
Record, 27:4, 32-39.
[13] Lanzola, G., Falsconi, S, and Stefanellii, M., (1995),
”Cooperative software agents for patient management”,
Lecture Notes in Artificial Intelligence, 934, 173-184.
[14] McDonald, A. (1999), ’Understanding Community
Care’, MacMillan Press Ltd., London, UK.
[15] Christopher A. Miller, (2001). Automation as
Caregiver; The Role of Advanced Technologies in
ElderCare. Proceedings of the Human Factors and
Ergonomics Society Annual Meeting, Minneapolis, MN
October 8-12.
[16] Nwana, H., Ndumu, D., Lee, L., and Collis, J., (1999)
’ZEUS: A Tool-Kit for Building Distributed
Multi-Agent Systems’, Applied Artifical Intelligence
Journal, vol. 13, no. 1 pp129- 186.
[17] Preece A. D., Hui, K-Y., Gray, W. A., Marti, P.,
Bench- Capon, T. J. M., Jones, D. M., and Cu, Z.,
(1999) ’The KRAFT Architecture for Knowledge
Fusion and Transformation’, 19th SGES International
Conference on Knowledge-based Systems and Applied
Artificial Intelligence (ES’99), Springer, Berlin.
[18] Sahuguet, A., and Azavant, F. (1998), W4F: the
WysiWyg Web Wrapper Factory. Technical report,
University of Pennsylvania, Department of Computer
and Information Science. http://cheops.cis.upenn.edu/
sahuguet/WAPI/.
[19] Symonds, A. & Kelly, A. (eds) (1998), ’The Social
Construction of Community Care’, Macmillan Press
Ltd., London, UK.
[20] Willmott, S. et al, (2002), ”Agentcities Network Architecture”, in Proceedings of the first International Workshop on
Challenges in Open Agent Systems, July 2002