Document Classification with Multi-layered Immune Principle
Automatic document classification is helpful in both organizing and finding information on huge resources. A novel multi-layered immune based document classification algorithm is presented. First, we represent the definition of the immune cells, antibody, antigen, and discuss the architecture of multi-layered immune system. Second, we evolve the dynamic models of immune response, immune regulation and immune memory, and establish the corresponding equations. Finally, we implement the simulation experiments, and compare the results with those obtained using the best methods for this application. Experiments show that the algorithm has higher classification accuracy than other document classification methods, and the attractive features such as diversity, self-learning, adaptive and robust etc. It provides a novel solution for document classification.
Keywordsdocument classification immune artificial intelligence
Unable to display preview. Download preview PDF.
- 1.Wang, P., Domeniconi, C.: Building semantic kernels for text classification using wikipedia. In: International Conference on Knowledge Discovery and Data Mining (KDD 2008), New York, USA (2008)Google Scholar
- 2.Ifrim, G., Theobald, M., Weikum, G.: Learning word-to-concept mappings for automatic text classification. In: Learning in Web Search Workshop, ICML (2005)Google Scholar
- 4.Hersh, W., Buckley, C., Leone, T.J., Hickam, D.: OHSUMED: An interactive retrieval evaluation and new large test collection for research. In: SIGIR 1994, pp. 192–201 (1994)Google Scholar
- 5.Porter, M.F.: An algorithm for suffix stripping. Program 14(3), 130–137 (1980)Google Scholar
- 6.Eui-Hong, S.H., George, K.: Centroid-Based Document Classification: Analysis and Experimental Results. In: Zighed, D.A., Komorowski, J., Żytkow, J.M. (eds.) PKDD 2000. LNCS (LNAI), vol. 1910, pp. 424–431. Springer, Heidelberg (2000)Google Scholar