Using agent based modeling and simulation for data mining


Kuğu E., Altay L., Sahingoz O. K.

19th International Conference on Neural Information Processing, ICONIP 2012, Doha, Qatar, 12 - 15 Kasım 2012, cilt.7664 LNCS, ss.258-265 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 7664 LNCS
  • Doi Numarası: 10.1007/978-3-642-34481-7_32
  • Basıldığı Şehir: Doha
  • Basıldığı Ülke: Qatar
  • Sayfa Sayıları: ss.258-265
  • Anahtar Kelimeler: Agent, MAS, Data Mining, Agent Based Modeling and Simulation
  • TED Üniversitesi Adresli: Hayır

Özet

In recent years, there is an exponential growth of information sources, especially with the increasing usage of Internet. Therefore, there is a growing need for automated tools for obtaining valuable information from these raw data in different data warehouses. Data Mining represents the process of extracting valuable and useful knowledge from large amounts of data. Generating appropriate abstractions from these distributed data warehouses is a challenging task for data mining tools. Data mining is a multidisciplinary research area and it includes database technology, neural networks, artificial intelligence and machine learning etc. It enables valuable information to the end users. However, if the system is newly set and it is in the cold start position with no or little processed data, this influences the system efficiency. There is an additional mechanism for producing realistic data. Agent Based Modeling and Simulation system is a powerful technology by using autonomous intelligent agents and usually can run in distributed environment. This paper emphasizes the approach of using Agent Based Modeling and Simulation for Distributed Data Mining technologies. © 2012 Springer-Verlag.