The agent architecture of the University of Michigan Digital Library

Durfee, Edmund H.; Kiskis, Daniel L.; Birmingham, William P.

doi:10.1049/ip-sen:19971024

Cited by 33 publications

(13 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiagent systems are computational systems in which several cooperative agents interact with each other in order to achieve their individual goals and also the overall system goal. The multi-agent approach has been applied to different domains, for example electronic commerce (He, Jennings, & Leung, 2003;Lee, 2004), information filtering, retrieval and management (Ardissono, Goy, Petrone, & Segnan, 2004;Durfee, Kiskis, & Birmingham, 1997;Moukas, 1997), resource planning and allocation (Haque, Jennings, & Moreau, 2005;Sycara, Pannu, Williamson, Zeng, & Decker, 1996), and mobile services (Panatiotou & Samaras, 2004;Ratsimor, Chakraborty, Joshi, Finin, & Yesha, 2004).…”

Section: Multi-agent Systems As Solutionsmentioning

confidence: 99%

Deploying personalized mobile services in an agent-based environment

Lee

2007

Expert Systems with Applications

View full text Add to dashboard Cite

Section: Multi-agent Systems As Solutionsmentioning

confidence: 99%

Deploying personalized mobile services in an agent-based environment

Lee

2007

Expert Systems with Applications

View full text Add to dashboard Cite

“…However, as also noted in section 1, this system had a number of limitations. Related to this, [2] developed a system that used a competitive market-based allocation of consumer attention space as a means of investigating the user's behaviour in making choices when faced with multiple items and [6] used a variety of marketplaces to moderate a range of digital library services. However, neither of these systems are specifically targetted at making recommendations.…”

Section: Related Workmentioning

confidence: 99%

Recommender systems

Yan

Moreau

Jennings

2003

Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems

View full text Add to dashboard Cite

Recommender systems have been widely advocated as a way of coping with the problem of information overload for knowledge workers. Given this, multiple recommendation methods have been developed. However, it has been shown that no one technique is best for all users in all situations. Thus we believe that effective recommender systems should incorporate a wide variety of such techniques and that some form of overarching framework should be put in place to coordinate the various recommendations so that only the best of them (from whatever source) are presented to the user. To this end, we show that a marketplace, in which the various recommendation methods compete to offer their recommendations to the user, can be used in this role. Specifically, this paper presents the principled design of such a marketplace; detailing the auction protocol and reward mechanism and analyzing the rational bidding strategies of the individual recommendation agents.

show abstract

“…Motivated by these issues, the Trilogy system uses intelligent agents to present information and to provide access to tools in response to a user's expressed requirements (see also the UMDL [4]). As discussed in the following section, agents may also proactively suggest other possibilities that a user may not have considered.…”

Section: Introductionmentioning

confidence: 99%

Constructing a virtual training laboratory using intelligent agents

Norman¹,

Jennings²

2002

IJCEELL

View full text Add to dashboard Cite

This paper reports on the results and experiences of the Trilogy project; a collaborative project concerned with the development of a virtual research laboratory using intelligent agents. This laboratory is designed to support the training of research students in telecommunications traffic engineering.Training research students involves a number of basic activities. They may seek guidance from, or exchange ideas with, more experienced colleagues. High quality academic papers, books and research reports provide a sound basis for developing and maintaining a good understanding of an area of research. Experimental tools enable new ideas to be evaluated, and hypotheses tested. These three components-collaboration, information and experimentation-are central to any research activity, and a good training environment for research should integrate them in a seamless fashion. To this end, we describe the design and implementation of an agent-based virtual laboratory.

show abstract

The agent architecture of the University of Michigan Digital Library

Cited by 33 publications

References 2 publications

Deploying personalized mobile services in an agent-based environment

Deploying personalized mobile services in an agent-based environment

Recommender systems

Constructing a virtual training laboratory using intelligent agents

Contact Info

Product

Resources

About