Probabilistic neural network classification for model β-Glucan suspensions

The problems encountered in brewing commonly attributed to excess β-glucan levels include low extract yield, increased lauter runoff times, formation of gelatinous precipitates during aging, and decreased filtration efficiency. Several rheological techniques were used to determine C* or critical concentration where β-glucan aggregates begin to entangle and there was a relationship between intrinsic viscosity and C*. This study reports applying Probabilistic Neural Network (PNN) to get new data set of relation between reciprocal of logarithm of relative viscosity 1/log (ηrel) and β-glucan concentration in seven model buffer systems and thus could be used for C* valure determination with better statistical correlation.

[1]  W. Kozicki,et al.  An alternative method for evaluation of intrinsic viscosity , 1996 .

[2]  M. Kasaai,et al.  Master curve for concentration dependence of semi-dilute solution viscosity of chitosan homologues: the Martin equation , 2000 .

[3]  Igor Aleksander,et al.  Introduction to Neural Computing , 1990 .

[4]  A. Kelemen,et al.  Probabilistic neural network classification for microarraydata , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[5]  Leorey Marquez,et al.  Neural network models as an alternative to regression , 1991, Proceedings of the Twenty-Fourth Annual Hawaii International Conference on System Sciences.

[6]  M.E. El-Hawary,et al.  Power system dynamic load modeling using adaptive-network-based fuzzy inference system , 1999, Engineering Solutions for the Next Millennium. 1999 IEEE Canadian Conference on Electrical and Computer Engineering (Cat. No.99TH8411).

[7]  M.E. El-Hawary,et al.  Wavelet neural network based short term load forecasting of electric power system commercial load , 1999, Engineering Solutions for the Next Millennium. 1999 IEEE Canadian Conference on Electrical and Computer Engineering (Cat. No.99TH8411).

[8]  Hongnian Yu,et al.  Novel probability neural network , 2005 .