Combining negative selection with immune K-means algorithm for improving the support vector machines method

• Autorzy: Bereta M. , Burczyński T.
• Konferencja: Evolutionary Computation and Global Optimization (10; Krajowa Konferencja Algorytmy Ewolucyjne i Optymalizacja Globalna; 11-13.06.2007; Będlewo, Poland)
• Języki publikacji: EN

Abstrakty

EN

This paper presents a novel method of using the ideas from Artificial Immune Systems for improving the performance of the support Vector Machines. By means of Immune K-Means algorithm a set of artificial data is generated based on the oryginal training data. The artificial data describes the most important information from the classifiers learning point of view - the information about the boundaries among the classes remain in the artificial data. Combining the Immune K-Means algorithm with Negative Selection methods allows for further improvements of the artificial data set. The proposed approach allows to speed up the learning process of SVM when the training data set is large by extracting the most important information first. The proposed method can also be used as a data compression, especially suited when the information about boundaries among classes is an important issue. The artificial data can be created once and then used for parameters tuning of different classification methods, speeding up the learning process.

Słowa kluczowe

EN

algorithms method; support vector machine

• Wydawca: Oficyna Wydawnicza Politechniki Warszawskiej
• Czasopismo: Prace Naukowe Politechniki Warszawskiej. Elektronika
• Rocznik: 2007
• Tom: z. 160
• Strony: 25--33
• Opis fizyczny: Bibliogr. 6 poz., rys., wykr.

Twórcy

autor

Bereta M.

autor

Burczyński T.

• Cracow University of Technology Cracow Poland,

Bibliografia

• [1] M. Bereta and T. Burczyński. Hybrid immune algorithm for feature selection and classification of ECG signals. In T. Burczyński, W. Cholewa, and W. Moczulski, editors, Recent Developments in Artificial Intelligence Methods, AI-METH Series, pages 25-28, Gliwice, 2005.
• [2] M. Bereta and T. Burczyński. Immune k-means: A novel immune algorithm for data clustering and multiple-class discrimination. In Proceedings of the IX Conference Evolutionary Computation and Global Optimization, KAEIOG 2006, Prace Naukowe PW s. Elektronika z. 156, Oficyna Wydawnicza PW, Warszawa 2006, pages 49-60, 2006.
• [3] D. Dasgupta and S. Forrest. Novelty detection in time series data using ideas from immunology. In ISCA 5th International Conference on Intelligent Systems, pages 19-21, Reno, Nevada, June 1996.
• [4] L.N. de Castro and J. Timmis. Artificial Immune Systems: A New Computational Approach. Springer-Verlag, London. UK., September 2002.
• [5] Fabio A. González, Dipankar Dasgupta, and Luis Fernando Niño. A randomized real-valued negative selection algorithm. In ICARIS, Artificial Immune Systems, Second International Conference, ICARIS 2003, Edinburgh, UK, September 1-3, 2003, pages 261-272, 2003.
• [6] Z. Ji and D. Dasgupta. Real-valued negative selection algorithm with variable-sized detectors. In Deb K. et al., editor, International Conference on Genetic and Evolutionary Computation (GECCO-2004), pages 287-298, Seattle, Washington USA, June 26-30 2004. Springer-Verlag.
• [7] P.D'haeseleer, S. Forrest, and P. Helman. An immunological approach to change detection: algorithms, analysis, and implications. In Proceedings of the 1996 IEEE Symposium on Computer Security and Privacy, 1996.
• [8] J. Plat. Sequential minimal optimization: A fast algorithm for training support vector machines. Technical report 98-14. Technical report, Microsoft Research, Redmond, Washington, http://www.research.microsoft.com/jplatt/smo.html, 1998.
• [9] Y. Shengfa and C. Fulei. Fault diagnosis based on support vector machines with parameter optimisation by artificial immunisation algorithm. Mechanical Systems and Signal Processing, 21:1318-1330, 2007.
• [10] Vladimir N. Vapnik. The nature of statistical learning theory. Springer-Verlag New York, Inc., New York, NY, USA, 1995.
• [11] Andrew Watkins, Jon Timmis, and Lois Boggess. Artificial immune recognition system (AIRS): An immune-inspired supervised machine learning algorithm. Genetic Programming and Evolvable Machines, 5(3):291-317, September 2004.
• [12] S. T. Wierzchoń. Artificial Immune Systems. Theory and Applications. Akademicka Oficyna Wydawnicza EXIT, Warszawa, 2001.