Literature on Neural Networks


Question Description:

30

Look for and summarize the following three articles. Submit a one-page summary single space per article. For each article please answer the followings: What the research problem is? Describe the methodology used to solve the problem? What and how data was collected and analyzed? Describe the neural network technique used? Describe their results in regards to solving the problem? see the attaches Document Preview: Neural Comput & Applic (2002)10:311–317 Ownership and Copyright ? 2002 Springer-Verlag London Limited Application of a Recurrent Neural Network to Prediction of Drug Dissolution Profiles W. Y. Goh1, C. P. Lim1, K. K. Peh2 and K. Subari1 1School of Electrical & Electronic Engineering; 2School of Pharmaceutical Sciences, Universiti Sains Malaysia, Penang, Malaysia The Elman Recurrent Neural Network was employed for the prediction of in-vitro dissolution profiles of matrix controlled release theophylline pellet preparation, leading to the potential use of an intelligent learning system in the development of pharmaceutical products with desired drug release characteristics. A total of six different formulations containing various matrix ratios of substance to control the release rate of theophylline were used for experimentation. By using the leave-one-out cross-validation approach, the dissolution profiles of all the matrix ratios were consumed for training, except for one set that was taken as a reference profile, with which the network predicted profiles were compared. Performance of the network was assessed using the similarity factor, f2, a criterion for dissolution profile comparison recommended by the United States Food and Drug Administration. Simulation results indicated that the Elman network was capable of predicting dissolution profiles that were similar to the reference profiles with an error of less than 8%. In addition, the Bootstrap method was used to estimate the confidence intervals of the f2 values. The results revealed the potential of a neural-network-based intelligent system in solving nonlinear time-series prediction problems in pharmaceutical product development. Keywords: Bootstrap confidence interval; Elman network; Pharmaceutical product formulation; Prediction of drug dissolution profile; Recurrent Neural Networks; Similarity factor Correspondence and offprint requests to: Dr C. P. Lim, School of Electrical & Electronic Engineering,… Attachments: Application-o….pdf Artificial-ne….pdf Optimization-….pdf

Answer

30