Intelligent Software Agents Applications and Classification

1
Intelligent Software AgentsApplications and
Classification

• Written by Nick Moraitakis
• Published in 1997
• You can find this paper at http//www.doc.ic.ac.u
  k/nd/surprise_97/journal/vol1/nm1
• Srihari Atluri

2
Abstract

• This paper aims to answer the following questions
• What are agents
• What types of agents can be identified
• What are the properties and characteristics with
  respect to which aforementioned identifications
  can be achieved.

3
Agents applications

• To begin with we first ask the questions
• Who is interested in agent technology? And
• Who is currently investigating agents?
• Personal Assistants Self-Contained systems that
  schedule, organise and optimize personal
  productivity tasks. Example Mail filtering

4
Agents applications -2

• Visitor Hosting Systems The hosting and
  scheduling of activities , meetings and events
  participated to by visitors at site, are
  organized and coordinated through the cooperation
  of local agents with the visitors, personal
  agents.
• Data Mining Information-specific agents provide
  a context for data searches in vast databases or
  other information sources (like the web for
  example) from which, cooperating intelligent
  personal agents will extract a selection of
  useful information. This field is one of the
  fastest-evolving ones at the moment given the
  explosive growth of the amount of accessible
  information via networks and communications

5
Agents application -3

• Network Management Collaborative agents collect
  and exchange local information on network
  statistics in order to achieve automation and
  optimization of decisions on network
  administration tasks like routing, access,
  service provisions, monitoring and statistical
  evaluation, within a global view.
• Air/Land Traffic Control A multi-agent system
  is installed in both controlling sites and
  travelling vehicles to help resolve control
  decisions in routing and scheduling

6
Agenthood

• Definition of Agent An agent ha the following
  properties.
• Autonomy the ability to self support its
  operations and to retain control over its actions
  and internal states
• Social ability the ability to interface and
  interact with other agents via communication
  language
• Reactivity Behavior according to which
  perception of environmental changes results to a
  response by the agent in a timely fashion
• Proactiveness the ability to take the initiative
  and thus exhibit, self-contained goal-directed
  behavior

7
Agent types

• Classification criteria
• Mobility
• Behavioral model
• Primary attributes
• Roles

8
Collaborative agents

• Focused into autonomy, cooperation, a little of
  learning
• Uses autonomy, responsiveness and proactive ness
  to achieve negotiation.
• They are static
• Suitable for
• problems too large, need distribution
• need for interconnection
• enhancement of modularity is of prime interest

9
Interface agents

• Focused in autonomy, learning and whose goal is
  to perform tasks for the owner
• Examples
• personal organisers
• informational filters
• financial decision systems
• tutorial systems

10
Mobile agents

• Move around the WAN, interact with remote hosts,
  collect information on behalf of the owner, and
  return to the home.
• Exhibits social ability, proactive ness and
  autonomy
• Used in
• less local recourses and need for remote
  recourses
• where asynchronous distributed computation is
  needed
• bringing remote information is expensive

11
Information agents

• Used to filter down the unmanageable large
  information to select the most useful pieces is
  needed. Information agents are tools that
  coordinate the retrieval, management, selection
  and manipulation of information. They may be
  mobile or collaborative, and perhaps they will
  exhibit many of the properties (especially the
  learning ones) of interface agents.

12
Conclusion

• Explosive growth
• Major role in the following years