Neural Computing and Applications

, Volume 21, Issue 1, pp 45–53 | Cite as

Framework of fully integrated hybrid systems

  • A. SantosEmail author
  • J. J. Romero
  • A. Carballal
  • A. Pazos
Original Article


A framework of fully integrated hybrid systems (HSs) is proposed for the development and management of HS which involve databases, advanced user interfaces, symbolic systems, and artificial neural networks. This framework provides a common input–output interface among those HS modules developed on the framework, with a completely two-directional flow control and a highly parallel processing. This integration framework facilitates the incorporation of heterogeneous modules, together with their subsequent management and updating.


Advanced user interfaces Artificial neural networks Databases Data mapping Symbolic systems 


  1. 1.
    McGarry K, Wermter S, MacIntyre J (1999) Hybrid neural systems: from simple coupling to fully integrated neural networks. Neural Comput Surv 2:62–94Google Scholar
  2. 2.
    Wermter S, Sun R (2000) Hybrid neural systems. Springer, New YorkCrossRefGoogle Scholar
  3. 3.
    Sun R (2002) Hybrid systems and connectionist implementationalism. In: Encyclopedia of cognitive science. Nature Publishing Group (MacMillan), London, pp 697–703Google Scholar
  4. 4.
    Sun R (1994) Integrating rules and connectionism for robust commonsense reasoning. Wiley, New YorkzbMATHGoogle Scholar
  5. 5.
    Corchado E, Corchado JM, Abraham A (2007) Innovations in hybrid intelligent systems. Springer, HeidelbergzbMATHCrossRefGoogle Scholar
  6. 6.
    Christos C, Giua A, Seatzu C, Zaytoon J (2006) Analysis and design of hybrid systems. Elsevier, AlgheroGoogle Scholar
  7. 7.
    Al-Zobaidie A, Grimson JB (1987) Expert systems and database systems: how can they serve each other? Expert Syst 4:30–37CrossRefGoogle Scholar
  8. 8.
    Codd EF (1972) Derivability, redundancy and consistency of relations in large data banks. IBM research report RJ 599Google Scholar
  9. 9.
    Codd EF (1982) Relational database: a practical foundation for productivity. Commun ACM 25:109–117CrossRefGoogle Scholar
  10. 10.
    Santos A (1998) Methodology for hybrid systems including expert systems, artificial neural networks and databases. Ph.D. thesis. University of A Coruña, A CoruñaGoogle Scholar
  11. 11.
    Santos A, Arcay B, Dorado J, Pazos A (2002) Artificial neural networks manipulation server. Research on the integration of data bases and artificial neural networks. Neural Comput & Appl 11:3–16zbMATHCrossRefGoogle Scholar
  12. 12.
    Weiss SM, Kulikowski CA (1991) How to estimate the true performance of a learning system. In: Weiss SM, Kulikowski CA (eds) Computer systems that learn. Morgan Kaufmann, San Francisco, pp 17–49Google Scholar
  13. 13.
    Walker LJ, Johnston J (1999) Guidelines for the assessment of indirect and cumulative impacts as well as impact interactions. Office for official publications of the European Communities, LuxembourgGoogle Scholar
  14. 14.
    Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Wesley, MassachusetszbMATHGoogle Scholar
  15. 15.
    Holland JH (1975) Adaptation in natural and artificial systems. University of Michigan Press, MichiganGoogle Scholar
  16. 16.
    Holland JH (1996) Complex adaptive systems. In: Pazos A (ed) Artificial neural networks and adaptive systems. University of A Coruña Press, A Coruña, pp 259–295Google Scholar
  17. 17.
    Fogel LJ, Owens AJ, Walsh MJ (1966) Artificial intelligence through simulated evolution. Wiley, New YorkzbMATHGoogle Scholar
  18. 18.
    Fogel DB (1995) Evolutionary computation: toward a new philosophy of machine intelligence. IEEE Press, New JerseyGoogle Scholar
  19. 19.
    Dasgupta D (1999) Artificial immune systems and their applications. Springer, BerlinzbMATHCrossRefGoogle Scholar
  20. 20.
    Feldman JA, Ballard DH (1982) Connectionist models and their properties. Cogn Sci 6(1):205–254Google Scholar
  21. 21.
    Tickle A, Maire F, Bologna G, Andrews R, Diederich J (2000) Lessons from past, current issues and future research directions in extracting the knowledge embedded in artificial neural networks. In: Wermter S, Sun R (eds) Hybrid neural systems. Springer, Heidelberg, pp 230–245Google Scholar
  22. 22.
    Teodorescu H (2000) Intelligent systems and interfaces. Kluwer, BostonCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  • A. Santos
    • 1
    Email author
  • J. J. Romero
    • 1
  • A. Carballal
    • 1
  • A. Pazos
    • 1
  1. 1.Department of Communications and Information Technologies, School of Computer ScienceA Coruña UniversityA CoruñaSpain

Personalised recommendations