Semantic Web Technologies and Artificial Neural Networks for Intelligent Web Knowledge Source Discovery

  • M. L. CaliuscoEmail author
  • G. Stegmayer
Part of the Advanced Information and Knowledge Processing book series (AI&KP)


This chapter is focused on presenting new and recent techniques, such as the combination of agent-based technologies and Artificial Neural Network (ANN) models that can be used for intelligent web knowledge source discovery in the new and emergent Semantic Web.

The purpose of the Semantic Web is to introduce semantic content in the huge amount of unstructured or semi-structured information sources available on the web by using ontologies. An ontology provides a vocabulary about concepts and their relationships within a domain, the activities taking place in that domain, and the theories and elementary principles governing that domain. The lack of an integrated view of all sources and the existence of heterogeneous domain ontologies, drives new challenges in the discovery of knowledge sources relevant to a user request. New efficient techniques and approaches for developing web intelligence are presented in this chapter, to help users avoid irrelevant web search results and wrong decision making.

In summary, the contributions of this chapter are twofold:
  1. 1.

    The benefits of combining Artificial Neural Networks with Semantic Web Technologies are discussed.

  2. 2.

    An Artificial Neural Network-based intelligent agent with capabilities for discovering distributed knowledge sources is presented.



Artificial Neural Network Artificial Neural Network Model Mobile Agent Resource Description Framework Software Agent 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Baeza-Yates, R.: Web mining. In: Proc. LA-WEB Congress, p. 2 (2005) Google Scholar
  2. 2.
    Berners-Lee, T., Hendler, J., Lassila, O.: The Semantic Web. Scientific American 5(1), 29–37 (2001) Google Scholar
  3. 3.
    Breitman, K., Casanova, M.A., Truszkowski, W.: Semantic Web: Concepts, Technologies and Applications. Springer, London (2007) zbMATHGoogle Scholar
  4. 4.
    Castano, S., Ferrara, A., Montanelli, S.: Dynamic knowledge discovery in open, distributed and multi-ontology systems: techniques and applications. In: Web Semantics and Ontology. Idea Group Inc, London (2006) Google Scholar
  5. 5.
    Chortaras, A., Stamou, G.B., Stafylopatis, A.: Learning ontology alignments using recursive neural networks. In: Proc. Int. Conf. on Neural Networks (ICANN), Poland. Lecture Notes in Computer Science, vol. 3697, pp. 811–816. Springer, Berlin (2005) Google Scholar
  6. 6.
    Cybenko, G.: Neural networks in computational science and engineering. IEEE Computational Science and Engineering 3(1), 36–42 (1996) CrossRefGoogle Scholar
  7. 7.
    Curino, C., Orsi, G., Tanca, L.: X-SOM: Ontology mapping and inconsistency resolution. In: 4th European Semantic Web Conference (ESWC’07), 3–7, June 2007 Google Scholar
  8. 8.
    Davies, J., Studer, R., Warren, P.: Semantic Web Technologies: Trends and Research in Ontology-Based Systems. Wiley, London (2007) Google Scholar
  9. 9.
    Doan, A., Madhavan, J., Domingos, P., Halevy, A.: Ontology matching: A machine learning approach. In: Handbook on Ontologies in Information Systems, pp. 385–403. Springer, New York (2004) Google Scholar
  10. 10.
    Ehrig, M., Sure, Y.: Ontology mapping—an integrated approach. In: Proc. 1st European Semantic Web Symposium (ESWS 2004), Greece. Lecture Notes in Computer Science, vol. 3053, pp. 76–91. Springer, Berlin (2004) Google Scholar
  11. 11.
    Euzenat, J., Barrasa, J., Bouquet, P., Bo, J.D., et al.: State of the art on ontology alignment. D2.2.3, Technical Report IST-2004-507482, KnowledgeWeb, 2004 Google Scholar
  12. 12.
    Euzenat, J., Shvaiko, P.: Ontology Matching. Springer, London (2007) zbMATHGoogle Scholar
  13. 13.
    Gómez-Pérez, A., Fernández-López, M., Corcho, O.: Ontological Engineering—with Examples from the Areas of Knowledge Management, e-Commerce and the Semantic Web. Springer, London (2004) Google Scholar
  14. 14.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice-Hall, New York (1999) zbMATHGoogle Scholar
  15. 15.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2(5), 359–366 (1989) CrossRefGoogle Scholar
  16. 16.
    Hendler, J.: Agents and the Semantic Web. IEEE Intelligent Systems 16(2), 30–37 (2001) CrossRefGoogle Scholar
  17. 17.
    Huang, J., Dang, J., Vidal, J., Huhns, M.: Ontology matching using an artificial neural network to learn weights. In: Proc. IJCAI Workshop on Semantic Web for Collaborative Knowledge Acquisition (SWeCKa-07), India (2007) Google Scholar
  18. 18.
    Lam, T., Lee, R.: iJADE FreeWalker—an intelligent ontology agent-based tourist guiding system. Studies in Computational Intelligence 72, 103–125 (2007) CrossRefGoogle Scholar
  19. 19.
    Li, W., Clifton, C.: SEMINT: a tool for identifying attribute correspondences in heterogeneous databases using neural networks. Data and Knowledge Engineering 33(1), 49–84 (2000) zbMATHCrossRefGoogle Scholar
  20. 20.
    López, V., Motta, E., Uren, V.: PowerAqua: fishing the semantic web. In: Proc. 3rd European Semantic Web Conference, Montenegro. Lecture Notes in Computer Science, vol. 4011, pp. 393–410. Springer, Berlin (2006) Google Scholar
  21. 21.
    Maes, P.: Intelligent software. Scientific American 273(3), 84–86 (1995) MathSciNetGoogle Scholar
  22. 22.
    Marquardt, D.: An algorithm for least-squares estimation of nonlinear parameters. SIAM Journal on Applied Mathematics 11, 431–441 (1963) MathSciNetzbMATHCrossRefGoogle Scholar
  23. 23.
    Nejdl, W., Wolf, B., Qu, C., Decker, S., Sintek, M., Naeve, A., Nilsson, M., Palmér, M., Risch, T.: EDUTELLA, A P2P networking infrastructure based on RDF. In: Proc. 11th World Wide Web Conference (WWW2002), USA, pp. 604–615 (2002) Google Scholar
  24. 24.
    Peis, E., Herrera-Viedma, E., Montero, Y.H., Herrera, J.C.: Ontologías, metadatos y agentes: Recuperación semántica de la información. In: Proc. II Jornadas de Tratamiento y Recuperación de la Información, España, pp. 157–165 (2003) Google Scholar
  25. 25.
    Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numerica 1, 143–195 (1999) MathSciNetCrossRefGoogle Scholar
  26. 26.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986) CrossRefGoogle Scholar
  27. 27.
    Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice-Hall, New York (2002) Google Scholar
  28. 28.
    Stegmayer, G., Caliusco, M.L., Chiotti, O., Galli, M.R.: ANN-agent for distributed knowledge source discovery. In: On the Move to Meaningful Internet Systems 2007: OTM 2007 Workshops. Lecture Notes in Computer Science, vol. 4805, pp. 467–476. Springer, Berlin (2007) CrossRefGoogle Scholar
  29. 29.
    Werbos, P.: The Roots of Backpropagation. From Ordered Derivatives to Neural Networks and Political Forecasting. Wiley, New York (1994) Google Scholar
  30. 30.
    Wermter, S.: Neural network agents for learning semantic text classification. Information Retrieval 3(2), 87–103 (2000) CrossRefGoogle Scholar
  31. 31.
    Wooldridge, M.: An Introduction to Multiagent Systems. Wiley, New York (2002) Google Scholar
  32. 32.
    Wray, J., Green, G.: Neural networks, approximation theory and precision computation. Neural Networks 8(1), 31–37 (1995) CrossRefGoogle Scholar
  33. 33.
    Zhu, X., Huang, S., Yu, Y.: Recognizing the relations between Web pages using artificial neural network. In: Proc. ACM Symposium on Applied Computing, USA, pp. 1217–1221 (2003) Google Scholar

Copyright information

© Springer-Verlag London 2010

Authors and Affiliations

  1. 1.CONICETCIDISI-UTN-FRSFSanta FeArgentina

Personalised recommendations