Some problems with construction of the k-NN classifier for recognition of an experimental respiration pathology

• Autorzy: Jóźwik A. , Sokołowska B.
• Języki publikacji: EN

Abstrakty

EN

An objective of the work is to demonstrate some difficulties with construction of a classifier based on the k-NN rule. The standard k-NN classifier and the parallel k-NN classifier have been chosen as the two most powerful approaches. This kind of classifiers has been applied to automatic recognition of diaphragm paralysis degree. The classifier construction consists in determination of the number of nearest neighbors, selection of features and estimation of the classification quality. Three classes of muscle pathology, including the control class, and five ventilatory parameters are taken into account. The data concern a model of the diaphragm pathology in a cat. The animals were forced to breathe in three different experimental situations: air, hypercapnic and hypoxic conditions. A separate classifier is constructed for each kind of the mentioned situations. The calculation of the misclassification rate is based on the leave one out and on the testing set method. Several computational experiments are suggested for the correct feature selection, the classifier type choice and the misclassification probability estimation.

Słowa kluczowe

EN

pattern recognition; supervised classification; k-NN rule; feature selection; respiration; ventilation; paralysis; diaphragm

PL

rozpoznawanie wzorców; klasyfikacja nadzorowana; zasada k-NN; wybór funkcji; oddychanie; wentylacja; paraliż; przepona

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2002
• Tom: Vol. 3
• Strony: MI89--97
• Opis fizyczny: Bibliogr. 13 poz., tab.

Twórcy

autor

Jóźwik A.

• Institute of Biocybernetics & Biomedical Engineering, PAS, Trojdena 4, 02-109 Warsaw, Poland
• Technical University of Łódź, Computer Engineering Department, Al. Politechniki 11, 90-924 Łódź, Poland

autor

Sokołowska B.

• Medical Research Centre, Department of Neurophysiology, PAS, Pawińskiego 5, 02-106 Warsaw, Poland

Bibliografia

• [1] Devijver, P.A., Kittler, J., Pattern recognition: a statistical approach, Prentice Hall International, London, pp.356-357, 1982.
• [2] Duda R., Hart P., Pattern classification and scene analysis, Wiley Interscience, New York, 1973.
• [3] Epstein S.K., An overview of respiratory muscle function, Clinics Chest Medicine, Vol.15, No.4, pp.619-639, 1994.
• [4] 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, pp. 280-322, 1952, reprinted in the book: Dasarathy B. V., NN pattern classification techniques, IEEE Computer Society Press, pp. 40-56, 1991.
• [5] Jóźwik A., Eksperymentalne badanie zależności pomiędzy prognozowaną jakością klasyfikacji a wielkością zbioru uczącego i liczbą cech, Materiały IX Krajowej Konferencji Biocybernetyki i Inżynierii Biomedycznej, Warszawa, pp.28-30, 2001.
• [6] Jóźwik A., Sokołowska B., Budzińska K., An example of computer aided decision-making system for recognition of respiration pathology, Medical Informatics and Technologies, Ustroń , pp. MI42-MI48, 2001.
• [7] Jóźwik A., Vernazza G., Recognition of leucocytes by a parallel k-NN classifiers, Lecture Notes of ICB Seminar, Warsaw, pp.138-153, 1988.
• [8] Katagiri M., Young R.N., Platt R.S.Kieser T.M., Easton P.A., Respiratory muscle compensation for unilateral or bilateral hemidiaphragm paralysis in awake canines, Journal of Applied Physiology, Vol.77, No.4, pp.1972-1981, 1994.
• [9] Pole D.C., Sexton W.L., Farkas G.A., Powers S.K.,Reid M.B., Diaphragm structure and function in health and disease, Medicine & Science in Sports & Exercise, Vol. 29, No.6, pp.738-754, 1997.
• [10] Rocco, P.R.M., Faffe, D.S., Feijoo, M., Menezes, S.L., Vasconcellos, F.P., Zin, W.A., Effects of uni- and bilateral phrenicotomy on active and passive respiratory mechanics in rats, Respiration Physiological. Vol. 110, pp. 9-18, 1997.
• [11] Sieck, G.C., Diaphragm muscle: structural and functional organization, Clinics in Chest Medicine, Vol.9, No.2, pp.195-210, 1988.
• [12] Siedlecki W., A formula for multi-class distributed classifiers, Pattern Recognition Letters, Vol. 15, pp. 739-742, 1994.
• [13] Stawska Z., Jóźwik A., Sokołowska B., Budzińska K., A multistage classifier based on distance measure and its use for detection of respiration pathology, Komputerowe Systemy Rozpoznawania (KOSYR2001), Wrocław, pp. 67-71, 2001.