Comparison between two types of Artificial Neural Networks used for validation of pharmaceutical processes

被引:42
作者
Behzadi, Sharareh Salar [1 ]
Prakasvudhisarn, Chakguy [2 ]
Klocker, Johanna [3 ]
Wolschann, Peter [3 ]
Viernstein, Helmut [1 ]
机构
[1] Univ Vienna, Dept Pharmaceut Technol & Biopharmaceut, A-1090 Vienna, Austria
[2] Shinawatra Univ, Sch Technol, Bangkok 10900, Thailand
[3] Univ Vienna, Dept Theoret Chem, A-1090 Vienna, Austria
关键词
Bayesian neural network; Feed-forward back-propagation network; Leave-one-out cross validation; Granulation processes; Validation of pharmaceutical processes; FLUIDIZED-BED GRANULATION; SIZE DISTRIBUTION; OPTIMIZATION; DESIGN; WET; DISSOLUTION; FORMULATION; SIMULATION; PREDICTION; BEHAVIORS;
D O I
10.1016/j.powtec.2009.05.025
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Two types of Artificial Neural Networks (ANNs), a Multi-Layer Perceptron (MLP) and a Generalized Regression Neural Network (GRNN), have been used for the validation of a fluid bed granulation process. The training capacity and the accuracy of these two types of networks were compared. The variations of the ratio of binder Solution to feed material, product bed temperature, atomizing air pressure, binder spray rate, air velocity and batch size were taken as input variables for training the MLP and GRNN. The properties of size, size distribution, flow rate, angle of repose and Hausner's ratio of granules produced, were measured and used as Output variables. Qualitatively, the two networks gave comparable results, as both pointed out the importance of the binder spray rate and the atomizing air pressure to the granulation process. However, the averaged absolute error of the MLP was higher than the averaged absolute error of the GRNN. Furthermore, the correlation coefficients between the experimentally determined and the calculated output values, the corresponding prediction accuracy for the different granule properties as well as the overall prediction accuracy using GRNN were better than using MLP. In conclusion, the comparison of two different networks (MLP, a so-called feed-forward back-propagation network and GRNN, a so-called Bayesian Neural Network) showed the higher capacity of the latter for validation of such granulation processes. (c) 2009 Elsevier B.V. All rights reserved.
引用
收藏
页码:150 / 157
页数:8
相关论文
共 41 条
[1]   Validation of fluid bed granulation utilizing artificial neural network [J].
Behzadi, SS ;
Klocker, J ;
Hüttlin, H ;
Wolschann, P ;
Viernstein, H .
INTERNATIONAL JOURNAL OF PHARMACEUTICS, 2005, 291 (1-2) :139-148
[2]   Comparison of artificial neural networks (ANN) with classical modelling techniques using different experimental designs and data from a galenical study on a solid dosage form [J].
Bourquin, J ;
Schmidli, H ;
van Hoogevest, P ;
Leuenberger, H .
EUROPEAN JOURNAL OF PHARMACEUTICAL SCIENCES, 1998, 6 (04) :287-300
[3]  
Bozic DZ, 1997, EUR J PHARM SCI, V5, P163
[4]   Search for predictive generic model of aqueous solubility using Bayesian neural nets [J].
Bruneau, P .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2001, 41 (06) :1605-1616
[5]   The application of an artificial neural network and pharmacokinetic simulations in the design of controlled-release dosage forms [J].
Chen, YX ;
McCall, TW ;
Baichwal, AR ;
Meyer, MC .
JOURNAL OF CONTROLLED RELEASE, 1999, 59 (01) :33-41
[6]   A versatile strategy for achieving the second-order advantage when applying different artificial neural networks to non-linear second-order data:: Unfolded principal component analysis/residual bilinearization [J].
Garcia-Reiriz, Alejandro ;
Damiani, Patricia C. ;
Culzoni, Maria J. ;
Goicoechea, Hector C. ;
Olivieri, Alejandro C. .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2008, 92 (01) :61-70
[7]   Viscosity prediction of lipophilic semisolid emulsion systems by neural network modelling [J].
Gasperlin, M ;
Tusar, L ;
Tusar, M ;
Smid-Korbar, J ;
Zupan, J ;
Kristl, J .
INTERNATIONAL JOURNAL OF PHARMACEUTICS, 2000, 196 (01) :37-50
[8]  
Hansen JV, 1996, DECIS SUPPORT SYST, V18, P317, DOI 10.1016/S0167-9236(96)80007-8
[9]   APPLICATION OF NEURAL COMPUTING IN PHARMACEUTICAL PRODUCT DEVELOPMENT [J].
HUSSAIN, AS ;
YU, XQ ;
JOHNSON, RD .
PHARMACEUTICAL RESEARCH, 1991, 8 (10) :1248-1252
[10]   DROPLET SIZE MEASUREMENT .1. EFFECT OF 3 INDEPENDENT VARIABLES ON DROPLET SIZE DISTRIBUTION AND SPRAY ANGLE FROM A PNEUMATIC NOZZLE [J].
JUSLIN, L ;
ANTIKAINEN, O ;
MERKKU, P ;
YLIRUUSI, J .
INTERNATIONAL JOURNAL OF PHARMACEUTICS, 1995, 123 (02) :247-256