The original version of this chapter was revised: The copyright line was incorrect. This has been
corrected. The Erratum to this chapter is available at DOI:
L. M. Camarinha-Matos (ed.), Collaborative Business Ecosystems and Virtual Enterprises
© IFIP International Federation for Information Processing 2002
10.1007/978-0-387-35585-6_68
REMOTE COLLABORATIVE
DATA MINING THROUGH
ONLINE KNOWLEDGE SHARING
Alfpio Jorge
1
, Steve Moyle
2
, Angi Vo8
3
1
LIACC-FEP, University of Porto, PORTUGAL amjorge@liacc.uo.pt,
2
0xford University Computing Laboratory UK, sam@comlab.ox,ac.uk
3
Fraunhofer-Gesellschaft zur Foerderung, Sankt Augustin, GERMANY.
angi. voss@ais.fraunhofer.de
The basic principles of a methodology for remote collabomtive data mining
are proposed. Starting from CRJSP·DM, a general data mining process
designed to carry out data mining projects; it is described how the principles
of knowledge sharing and ease of communication can be embedded in the data
mining process. The aim is to allow the execution of data mining projects, with
the paTticipation of multiple experts working from distant locations. AU the
participants in such a project can profit from the knowledge produced by
others and share their knowledge online with the other participants. The
produced knowledge (for exmnple data tmnsformations, working hypothesis,
models, results of experiments) is also stored for future inspection and use, in
pursuit of organizational learning. A prototypical implementation (RAMSYS)
of the remote coUabomtive methodology is described with examples.
1. INTRODUCTION
In many technical and scientific domains, expertise is spread throughout a number
of different locations. In such a setting, to solve a specific problem implies that
either experts must meet at one location, with high costs, or solving the problem
with local available expertise, which often leads to a sub-optimal solution. An
intermediate possibility is remote collaboration, where each expert or team of
experts located at a specific geographic point communicate with the other teams
whenever necessary. The following issues should be considered when developing a
remote collaborative problem-solving framework:
IJ Problem solving methodology: A specific problem solving methodology must
be known and utilized by all the participants. One way to ensure this is to
embed the problem solving methodology in a remote collaboration tool that is
used for both problem solving and communication.
IJ Knowledge sharing: Knowledge should be shared for both the immediate
problem solving and for the greater organizational good. When some piece of
knowledge relevant to the project is produced by one of the experts it should be
made available as soon as possible to the other experts. Furthermore, knowledge
produced and retained enables organizational learning (VoB et al. 2001).