Adaptive reordering of observation space to improve pattern recognition

• Autorzy: Kulikowski J.L.
• Języki publikacji: EN

Abstrakty

EN

The problem of observation space reordering is presented as a novel approach to pattern recognition based on non-parametric, combinatorial statistical tests. It consists in linearly ordering the elements of a discrete multi-dimensional observation space along a curve such that elements belonging to different similarity classes are as close to each other as possible, the similarity classes are mutually separated, and the length of the curve is kept to minimum. The problem is NP-difficult and it is shown how its approximate solution can be reached by a series of transformations improving the initial lexicographic linear order of a discrete observation space. Recommendations are formulated for linear order improvement leading to a pattern recognition algorithm based on serial statistical test.

Słowa kluczowe

EN

pattern recognition; serial statistical tests; linear ordering; permutations

• Wydawca: Politechnika Gdańska
• Czasopismo: TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk
• Rocznik: 2007
• Tom: Vol. 11, No 1-2
• Strony: 59--69
• Opis fizyczny: Bibliogr. 7 poz., rys.

Twórcy

autor

Kulikowski J.L.

• Institute of Biocybernetics and Biomedical Engineering, Polish Academy of Sciences, 4 Ks. Trojdena Str., 02-109 Warsaw, Poland,

Bibliografia

• [1] Abe S 2005 Support Vector Machines for Pattern Classification, Springer, London
• [2] Duda R and Hart P 1973 Pattern Classification and Scene Analysis, John Wiley & Sons, New York - London - Sydney
• [3] Tou J and Gonzales R 1974 Pattern Recognition Principles, Addison-Wesley Publishing Co, London - Amsterdam - Sydney
• [4] Kulikowski J L and Wierzbicka D 2004 Biocybernetics and Biomedical Eng. 24 (2) 27
• [5] Kulikowski J L and Wierzbicka D 2005 Biocybernetics and Biomedical Eng. 25 (3) 65
• [6] Kulikowski J L 2006 Proc. Int. Multiconf. on Computer Science and Information Technology, Wisla, Poland, PIPS, pp. 103-109 on CD
• [7] Kulikowski J L, Przytulska M and Wierzbicka D 2005 Proc. 4th Int. Conf. on Computer Recognition Systems CORES'O5 (Kurzynski M et al. Eds), Springer-Verlag, Berlin, pp. 235-242