This site has been archived on

INCO 977113 KNIXMAS

Knowledge Shared XPS-Based Research Network
Using Multi-Agent-Systems

Keywords: high performance computing, intelligent research network, decision support system, intelligent self adapting knowledge retrieval, multi agent systems, decision supported collaborative working
Technical: AI-modules, knowledge broker modules, decision support modules, Corba standards
Application: distributed management systems, collaborative research and development system, enterprise engineering

Due to the increasing demand of globally distributed information within complex researching and developing there is a need for intelligent self adapting global research and development networks, especially under GroupWare aspects.
The main objective is to design and establish a framework (shell) for an intelligent global research network consisting of connected local (national) working and research networks. This framework will consist of distributed co-operating expert systems (Intelligent Base Systems) with decision support modules for research management and intelligent knowledge retrieval provided by applied multi-agent systems. For the prototype the local research networks and working spaces will be realized as Intranets in 5 different European countries (Germany, Finland, Hungary, Poland, Bulgaria). The center of each local network will be an intelligent base system conceived as expert system with co-operating and communication facilities via Internet/Intranet. The entire knowledge will be shared over the whole network and managed by Intelligent Knowledge Brokers .
The main characteristics of the research network are the following: The entire network is supplied with AI-components and methods. Modularity and flexibility will be guaranteed by structuring and designing the whole system in an object oriented way. Adaptiveness and flexible adjustment will be provided by reflecting and evaluating user response and acceptance data via complex feedback and influence loops. Developing this research network as a modular AI-system ensures a high degree of transferability and adjustment capabilities . Using dynamic knowledge and databases and digital repositories controlled by intelligent knowledge brokers guarantees inter- and exchange of specialized knowledge. For the intelligent knowledge retrieval global and local standard multi-agent systems will be installed on heterogeneous platforms using CORBA standards.
The flexible modular structure of the framework gives the possibility to apply the system to others than technical or scientific areas. It will be universally applicable for several areas in industry and economics. At first it is planned to process the knowledge of high-tech areas like control theory and communication techniques. In addition several testing partners are involved to test the system in other than scientific areas (customizing of SPP/(R/3) software, enterprise modeling, Tele teaching etc.).
Contact Point
H.-J. Nern
University of Wuppertal
Group of Automatic Control and Technical Cybernetics E-mail: (E-mail removed)
Fuhlrottstr. 10
D-42097 Wuppertal http : to be announced
Participants

Country

Role

Prof. Dr. sc.techn. H.A. Nour Eldin
(Institute of Automatic Control and Technical Cybernetics, BUGHW)

D

C

Prof. Dr. sci. J. D. Zaprianov
(Institute of Control and Systems Research, BAS)

BG

P

Prof. Dr. hab. A. Dziech
(Telecommunication Department, AGH)

PL

P

Prof. Dr. Laszlo Kovacs
(MTA SZTAKI, Hungarian Academy of Science)

HU

P

Prof. Dr. Matti Hämäläinen
(Espoo-Vantaa Institute of Technology, Espoo)

FIN

P

Prof. Dr.-Ing. J. Wassermann
(Institute of Applied Science, FHD Stuttgart)

D

P

Start Date Duration
October 1998 24 months

This page is located at /esprit/src/977113.htm
It was last updated on 13 October 1998, and is maintained by (E-mail removed)

DCSIMG