A component-based architecture for problem solving environments
Mathematics and Computers in Simulation - IMACS sponsored special issue: 1999 international symposium on computational sciences, to honor John R. Rice
Clustering by pattern similarity in large data sets
Proceedings of the 2002 ACM SIGMOD international conference on Management of data
Distributed Data Mining in Credit Card Fraud Detection
IEEE Intelligent Systems
Design and Mathematical Analysis of Agent-Based Systems
FAABS '00 Proceedings of the First International Workshop on Formal Approaches to Agent-Based Systems-Revised Papers
Parallel k/h-Means Clustering for Large Data Sets
Euro-Par '99 Proceedings of the 5th International Euro-Par Conference on Parallel Processing
Cluster ensembles --- a knowledge reuse framework for combining multiple partitions
The Journal of Machine Learning Research
Design and application of hybrid intelligent systems
Numerical methods for fuzzy clustering
Information Sciences: an International Journal
Clustering in a multi-agent data mining environment
ADMI'10 Proceedings of the 6th international conference on Agents and data mining interaction
Multi-agent based clustering: towards generic multi-agent data mining
ICDM'10 Proceedings of the 10th industrial conference on Advances in data mining: applications and theoretical aspects
JABAT middleware as a tool for solving optimization problems
Transactions on computational collective intelligence II
Hi-index | 0.00 |
The paper deals with the non-distributed and distributed clustering and proposes an agent-based approach to solving the clustering problem instances. The approach is an implementation of the specialized A-Team architecture called JABAT. The paper includes an overview of JABAT and the description of the agent-based algorithms solving the non-distributed and distributed clustering problems. To evaluate the approach the computational experiment involving several well known benchmark instances has been carried out. The results obtained by JABAT-based algorithms are compared with the results produced by the non-distributed and distributed k -means algorithm. It has been shown that the proposed approach produces, as a rule, better results and has the advantage of being scalable, mobile and parallel.