Nonparametric methods of supervised classification

• Autorzy: Jóźwik A.
• Języki publikacji: EN

Abstrakty

EN

Selected nonparametric methods of statistical pattern recognition are described. A part of them form modifications of the well known k-NN rule. To this group of the presented methods belong: a fuzzy k-NN rule, a pair-wise k-NN rule and a corrected k-NN rule. They can improve classification quality as compared with the standard k-NN rule. For the cases when these modifications would offer to large error rates an approach based on class areas determination is proposed. The idea of class areas can be also used for construction of the multistage classifier. A separate feature selection can be performed in each stage. The modifications of the k-NN rule and the methods based on determination class areas can be too slow in some applications, therefore algorithms for reference set reduction and condensation, for simple NN rule, are proposed. To construct fast classifiers it is worth to consider also a pair-wise linear classifiers. The presented idea can be used as in the case when the class pairs are linearly separable as well as in the contrary case.

Słowa kluczowe

EN

pattern recognition; feature selection; k-NN rules; pair-wise classifier; artificial features; linear classifier; reference set size reduction

PL

rozpoznawanie wzorca; wybór funkcji; reguła k-NN; sztuczne cechy; klasyfikator liniowy

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2013
• Tom: Vol. 22
• Strony: 21--32
• Opis fizyczny: Bibliogr. 15 poz., rys., tab., wykr.

Twórcy

autor

Jóźwik A.

• Institute of Biocybernetics and Biomedical Engineering, Polish Academy of Science, Warsaw, Poland and Łódź University, Faculty of Physics and Applied Informatics, Łódź, Poland.

Bibliografia

• [1] CARPENTER G. A., GROSSBERG S., Learning, categorization, rule formation, and prediction by fuzzy neural networks, in the book "Fuzzy logic and neural network handbook", edited by C.H. Chen, McGraw-Hill Series on Computer Engineering, New York, 1996, pp. 1.3-1.45.
• [2] FIX E., HODGES J. L., Discriminatory analysis: nonparametric discrimination small sample performance, Project 21-49-004, report number 11, USAF school of aviation medicine, Randolph Field, Texas, 2001, pp. 280-322.
• [3] JÓŹWIK A., A learning scheme for a fuzzy k-NN rule, Pattern Recognition Letters 1, 1983, pp. 287-289.
• [4] JÓŹWIK A., Pattern recognition method based on k nearest neighbor rule, Journal of Communications, 1994, Vol. XLV, pp. 27-29.
• [5] JÓŹWIK A., Nieparametryczne metody klasyfikacji nadzorowanej, Wydawnictwo Instytutu Biocybernetyki i Inżynierii Biomedycznej PAN, 2013.
• [6] JÓŹWIK A., KIEŚ P., Reference set reduction for 1-NN rule based on finding mutually nearest and mutually furthest pairs of points, Advances in Soft Computing, Computer Recognition Systems, Springer-Verlag, Berlin-Heidelberg, 2005, pp. 195-202.
• [7] JÓŹWIK A., SERPICO S. B., ROLI F., Condensed Version of the k-NN rule remote sensing image classification, Image and Signal Processing for Remote Sensing II, EUROPTO Proceedings, SPIE, 1995, Vol. 2579, pp. 196-198.
• [8] JÓŹWIK A., SERPICO S., ROLI F., A parallel network of modified 1-NN and k-NN classifiers-application to remote-sensing image classification, Pattern Recognition Letters 19, 1998, pp. 57-62.
• [9] JÓŹWIK A., STAWSKA Z., Wielostopniowy klasyfikator typu najbliższy sąsiad z każdej klasy, Materiały VIII Konferencji "Sieci i Systemy Informatyczne", Łódź, 2000, str. 339-346 (in Polish).
• [10] JÓŹWIK A., VERNAZZA G., Recognition of leucocytes by a parallel k-NN classifier, Lecture Notes of the ‘ICB Seminar, 1988, pp. 138-153.
• [11] KOZINIEC B. N., Recurent algorithm separating convex hulls of two sets (V. N. Vapnik, Ed.), Soviet radio, Moscow, 1973, pp. 43-50 (in Russian).
• [12] LACHENBRUCH P. A., Estimation of Error Rates in Discriminant Analysis, Ph.D. dissertation, University of California, Los Angeles, 1965, Chapter 5.
• [13] LESIAK B., JÓŹWIK A., Quantitative analysis of AuPd alloys from the shape of XPS spectra by the fuzzy rule, Surface and Interface Analysis, 2004, Vol. 36, pp. 793-797.
• [14] SANCHEZ J. S., High training set size reduction by space partitioning and prototype abstraction, Pattern Recognition 37, 2004, pp. 1561-1564.
• [15] TOMEK I., Two modifications of CNN, IEEE Trans. Systems, Man, and Cybernetics, 1977, Vol. 7, No. 2, pp. 92-94.