Application of covering algorithm for classification of melanoma spots on the skin

• Autorzy: Grzymała-Busse J. W. , Hippe Z. S.
• Języki publikacji: EN

Abstrakty

EN

An in-house elaborated and implemented covering algorithm was applied. For the development of learning models (in the form of production rules), used then for computer-assisted classification (hence, diagnosing) of melanoma spots on the skin. In our research, four types of marks (namely, Benign nevus, Blue nevus, Suspicious nevus, and Melanoma malignant) have be en investigated. One of the generated learning models (the most promimissing one) was optimized by execution of selected generic operations on production rules, what lead to a very concise set of rules (4 rules only) giving errorless classification of unseen cases tested.

Słowa kluczowe

EN

covering algorithm; melanoma; medical diagnostic; GTS algorithm; computer-assisted diagnostics

PL

algorytm pokryciowy; czerniak; diagnostyka medyczna; algorytm GTS; diagnostyka wspomagana komputerowo

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2002
• Tom: Vol. 10, nr 2
• Strony: 27--33
• Opis fizyczny: Bibliogr. 10 poz.

Twórcy

autor

Grzymała-Busse J. W.

• Departament of Electrical Engineering and Computer Science, University of Cansas, Lawrence KS 66045, U.S.A.

autor

Hippe Z. S.

• Department of Expert Systems and Artificial Intelligence, University of Information Technology and Management, Sucharskiego 2, 35-225 Rzeszów, Poland

Bibliografia

• [1] Hippe Z.S.: Machine Learning - A promising strategy for business information processing?, In: Business Information Systems’97, Abramowicz W., Academy of Economy Edit. Office, Poznań 1997, pp. 603-622.
• [2] Hippe Z.S. and Hippe T.M.: An attempt to automatize modelling of medical data, In: Computers in Medicine, Kącki E., Polish Society of Medical Informatics, Łódź 1997, pp. 24-31.
• [3] Grzymała-Busse J.W. and Hippe Z.S., Data mining experiments with a Melanoma training set, In: Intelligent Information Systems, Kłopotek M., Michalewicz M. and Wierzchoń S.T., Physica-Verlag, Heidelberg 2000, pp. 27-34.
• [4] Grzymała-Busse J.W. and Hippe Z.S.: Melanoma prediction using k-Nearest Neighbor and LEM2 algorithms, In: Intelligent Information Systems, Kłopotek M., Michalewicz M. and Wierzchoń S.T., Physica-Verlag, Heidelberg 2001, pp. 43-55.
• [5] Grzymała-Busse J.W.: LERS - A system for learning from examples based on rough sets, In: Intelligent Decision Support. Handbook of Applications and Advances of the Rough Sets Theory, Słowiński R., Kluwer Academic Publishers, Norwell, MA, 1992, pp. 3-18.
• [6] Grzymała-Busse J.W.: LERS - A knowledge discovery system, In: Rough Sets in Knowledge Discovery 2. Applications, Case Studies and Software Systems, Polkowski L. and Skowron A., Physica-Verlag, Heidelberg 1998, pp. 562-565.
• [7] BAJCAR S. and GRZEGORCZYK L.: Endangerment by skin cancer of population of south-east part of Poland, Hospital #1 Research Report, Rzeszów 1997.
• [8] Hippe Z.S.: Data mining in medical diagnosis, In: Computers in Medicine, Kącki E., Polish Society of Medical Informatics, Łódź 1999, Vol. 1, pp. 25-34.
• [9] Braun-Falco O., Stolz W., Bilek P„ Merle T. and Landthaler M.: Das Dermatoskop. Eine Vereinfachung der Auflichtmikroskopie von pigmentierten Hautveranderungen, Hautarzt 1999, Vol. 40, pp. 131-135.
• [10] Hippe Z.S. and Iwaszek G.: From research on a new method of development of quasi-optimal decision trees, In: Intelligent Information Systems IX, Kłopotek M., Michalewicz M. and Wierzchoń S.T., Instytut Informatyki PAN, Warszawa 2000, pp. 31-35.