An Agent-Based Soft Computing Society

  • Chengqi Zhang
  • Zili Zhang
  • Ong Swee San
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2005)


Soft computing (SC) techniques such as fuzzy logic (FL), neural networks (NN), and genetic algorithms (GA) are complementary. Each SC technique has particular computational properties that make them suited for particular problems and not for others. Thus, in solving complex, real-world problems, we need to incorporate some SC techniques into the application systems to increase the systems’ “intelligence”. In this paper, we first propose an agent-based framework for integrating SC techniques into practical application systems. We then discuss the design and implementation of a platform independent soft computing support environment based on the framework. We call such an environment agent-based softcomputing society. Such a society can facilitate the design of truly robust, flexible and adaptive hybrid intelligent systems.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Z. Zhang and C. Zhang, Approaches to Incorporating Soft computing Technologies into Software Agents, Proceedings of ICONIP'99, IEEE Press, 1999, 952–957.Google Scholar
  2. 2.
    Z. Zhang and C. Zhang, A Serving agent for Integrating Soft Computing and Software Agents, Proceedings of Australia AI'99, Springer, 1999, 476–477.Google Scholar
  3. 3.
    G. J. Deboeck (Ed.), Trading on the Edge-Neural, Genetic, and Fuzzy Systems for Chaotic Financial Markets, Wiley, 1994.Google Scholar
  4. 4.
    R. J. Bauer, Genetic Algorithms and investment Strategies, Wiley, 1994.Google Scholar
  5. 5.
    R. A. Ribeiro, H. J. Zimmermann, R. R. Yager, and J. Kacprzyk (Ed.), Soft Computing in Financial Engineering, Physica-Verlag, 1999.Google Scholar
  6. 6.
    S. Goonatilake and S. Khebbal (Eds.), Intelligent Hybrid Systems, Wiley, 1995.Google Scholar
  7. 7.
    L. R. Medsker, Hybrid Intelligent Systems, Kluwer Academic Publisher, 1995.Google Scholar
  8. 8.
    L. C. Jain and R. K. Jain (Eds.), Hybrid Intelligent Engineering Systems, World Scientific, Singapore, 1997.zbMATHGoogle Scholar
  9. 9.
    M. Hilario, C. Pellegrini, and F. Alexandre, Modular Integration of Connectionist and Symbolic Processing in Knowledge-based Systems, in: Int. Symposium on Integrating Knowledge and Neural Heuristics, Pensacola, Florida, 1994, 123–132.Google Scholar
  10. 10.
    R. Khosla and T. Dillon, Engineering Intelligent Hybrid Multi-Agent Systems, Kluwer Academic Publishers, Boston, 1997.zbMATHGoogle Scholar
  11. 11.
    M. R. Genesereth and S. P. Ketchpel, Software Agents, Commun. ACM, Vol.37, No.7, 1994, 48–53.CrossRefGoogle Scholar
  12. 12.
    T. Finin, Y. Labrou and J. Mayfield, KQML as an Agent Communication Language, in J. M. Bradshaw (ed.), Software Agents, AAAI Press/ The MIT Press, Menlo Park, CA, 1997, 291–316.Google Scholar
  13. 13.
    M. Wooldridge, Agent-Based Software engineering, IEE Proc. Software Engineering, Vol. 144, No. 1, 1997, 26–37.Google Scholar
  14. 14.
    N. R. Jennings, On Agent-Based Software Engineering, Artificial Intelligence, Vol. 117, 2000, 277–296.zbMATHCrossRefGoogle Scholar
  15. 15.
    N. R. Jennings, K. Sycara, and M. Wooldridge, A Roadmap of Agent Research and Development, Autonomous Agents and Multi-Agent Systems, Vol. 1, 1998, 7–38.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Chengqi Zhang
    • 1
  • Zili Zhang
    • 1
  • Ong Swee San
    • 1
  1. 1.School of Computing and MathematicsDeakin UniversityGeelong VictoriaAustralia

Personalised recommendations