Modeling of production processes by naive Bayesian classifierand artificial neural networks

by

Modeling of production processes by naive Bayesian classifierand artificial neural networks

Marcin Perzyk, Robert Biernacki

Instytut Technologi Materiałowych Politechniki Warszawskiej.

DOI:

https://doi.org/10.7494/cmms.2004.3.0058

Abstract:

Modeling qualities of two types learning systems are compared: naive Bayesian classifier (NBC) and artificial neural networks (ANN), based on prediction errors and relevant importance factors of input signals. Simulated and real industrial data were used. It was found that NBC can be an effective and a better tool in some applications, compared to ANN.

Cite as:

Perzyk, M., Biernacki, R. (2004). Modeling of production processes by naive Bayesian classifierand artificial neural networks. Computer Methods in Materials Science, 4(3), 98 – 104. https://doi.org/10.7494/cmms.2004.3.0058

Article (PDF):

Keywords:

,

References:

Perzyk, M., Kochański, A. (2001). Prediction of ductile cast iron quality by artificial neural networks. J. Mat. Proc. Techn., 109, 305-307.

Perzyk, M., Kochański, A., Kozłowski, J. (2003). Istotność względna sygnałów wejściowych sieci neuronowej. /nformatyka w Technologii Materiałów, 3, 125-132.

Perzyk, M., Kochański, A. (2003). Detection of causes of casting defects assisted by artificial neural networks. J. Eng. Manufacture, Proc. of the Institution of Mechanical ers, Part B. 217, 1279-1284.

Yescas, M.A., Bhadeshia, H.K.D.H., MacKay, D.J. (2001). Estimation of the amount of retained austenite in austempered ductile irons using neural networks. Mat. Sci. Eng., A311, 162 ? 173.

Perzyk, M., Kochanski, A., Kozlowski, J. (2004). Significance analysis of production parameters assisted by artificial neural networks. Proc. Int. Conf: Advances in Production Engineering, Warsaw University of Technology, Warsaw. Engine