Membership function - ARTMAP neural networks

• Autorzy: Sinčák P. , Hric M. , Vaščák J.
• Języki publikacji: EN

Abstrakty

EN

The project deals with the application of computational intelligence (CI) tools for multispectral image classification. Pattern Recognition scheme is a global approach where the classification part is playing an important role to achieve the highest classification accuracy. Multispectral images are data mainly used in remote sensing and this kind of classification is very difficult to assess the accuracy of classification results. There is a feedback problem in adjusting the parts of pattern recognition scheme. Precise classification accuracy assessment is almost impossible to obtain, being an extremely laborious procedure. The paper presents simple neural networks for multispectral image classification, ARTMAP-like neural networks as more sophisticated tools for classification, and a modular approach to achieve the highest classification accuracy of multispectral images. There is a strong link to advances in computer technology, which gives much better conditions for modelling more sophisticated classifiers for multispectral images.

Słowa kluczowe

EN

pattern recognition principles; classifier design; classification accuracy assessment; contingency tables; backpropagation neural networks; fuzzy BP neural networks; ART and ARTMAP neural networks; modular neural networks; neural networks

• Wydawca: Politechnika Gdańska
• Czasopismo: TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk
• Rocznik: 2003
• Tom: Vol. 7, No 1
• Strony: 43--52
• Opis fizyczny: Bibliogr. 11 poz., rys., tab.

Twórcy

autor

Sinčák P.

• Siemens AG, Vienna PSE Department, ECANSE working group, Gudrunstrsse II, 1100 Vienna, Austria

autor

Hric M.

• Center for Intelligent Technologies, Faculty of EE and Informatics, Technical University, Letna 9, 04001 Kosice, Slovak Republic

autor

Vaščák J.

• Center for Intelligent Technologies, Faculty of EE and Informatics, Technical University, Letna 9, 04001 Kosice, Slovak Republic

Bibliografia

• [1] Duda R and Hart P 1973 Pattern Classification and Scene Analysis, Wiley, New York
• [2] Werbos P 1974 Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences, PhD Thesis, Harvard University
• [3] Ocelikova E and Klimesova D 2000 Proc. 4th Scientific Technical Conference Process Control - RIP 2000, Pardubice, Czech Republic, p. 108
• [4] Klimesova D and Ocelikova E 2001 Proc. Int. Conf. Agrarian Perspectives X-Sources of Sutainable Economic Growth in the Third Millenium. Globalisation versus Regionalism, Prague, Czech Republic, pp. 67-74
• [5] Carpenter G A, Gjaja M N, Gopal S and Woodcock C E 1997 IEEE Trans. Geoscience and Remote Sensing 35 (2) 308
• [6] Grossberg S 1976 Biological Cybernetics 23 187
• [7] Carpenter G A, Milenova B L and Noeskc B W 1998 Neural Networks 11 (5) 793
• [8] Williamson J R 1996 Neural Networks 9 881
• [9] Sinćak P, Kopćo N, Hric M and Veregin H 2000 Proc. 6th Int. Conf. on Computational Intelligence, IIZUKA, Iizuka, Japan (1)
• [10] Rutkowska D and Nowicki R 2000 Int. J. Appl. Math, and Comput. Sci. 10 (4) 675
• [11] Sinćak P, Veregin H and Kopćo N 2000 Geocarto Int. 15 11