Best clustering configuration metrics: towards multiagent based clustering
ADMA'10 Proceedings of the 6th international conference on Advanced data mining and applications: Part I
Agent enriched distributed association rules mining: a review
ADMI'11 Proceedings of the 7th international conference on Agents and Data Mining Interaction
Hi-index | 0.00 |
This paper commences with a discussion of the advantages that Multi-Agent Systems (MAS) can bring to the domain of Knowledge Discovery in Data (KDD), and presents a rational for Agent-Enriched Data Mining (AEDM). A particular challenge of any generic, general purpose, AEDM system is the extensive scope of KDD. To address this challenge the authors suggest that any truly generic AEDM must be readily extendable and propose EMADS, The Extendable Multi-Agent Data mining System. A complete overview of the architecture and agent interaction models of EMADS is presented. The system's operation is described and illustrated in terms of two KDD scenarios: meta association rule mining and classifier generation. In conclusion the authors suggest that EMADS provides a sound foundation for both KDD research and application based AEDM.