Paper Info
Title
Computational Neural Networks In Conjunction With Principal Component Analysis For Resolving Highly Nonlinear Kinetics
Abstract
A method based on the use of an orthogonal linear filter, principal component analysis (PCA), for preprocessing data used as input for a feed-forward neural network is proposed. The method analyzes the significance of the eigenvalues of the correlation matrix associated with the first principal components of the data in order to select the subset of principal components for the sample that provides the optimum generalization value. The generalization error was estimated by using the leave-one-out method, because it provides the most reliable results for the fairly small data set used. The performance of the proposed method was assessed by applying it to the resolution of mixtures of species exhibiting a very similar kinetic behavior in the presence of a mutual kinetic (synergistic) effect. In addition, use of the continuous-addition-of-reagent (CAR) technique, a second-order approach, increased the nonlinearity of the system studied. Based on the results, the proposed designs provide accurate estimates in the kinetic resolution of binary mixtures, with errors of prediction about 5%. The results obtained in this respect are quite good taking into account that the kinetic behavior of the mixtures studied conforms to highly complex differential equations.
Year
DOI
Venue
1997
10.1021/ci960084o
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES
Keywords
Field
DocType
kinetics,neural network,principal component analysis
Nonlinear system,Small data,Computer science,Artificial intelligence,Artificial neural network,Eigenvalues and eigenvectors,Combinatorics,Sparse PCA,Linear filter,Algorithm,Covariance matrix,Principal component analysis,Machine learning
Journal
Volume
Issue
ISSN
37
2
0095-2338
Citations 
PageRank 
References 
3
0.82
2
Authors
4
Name
Order
Citations
PageRank
S. Ventura12318158.44
Manuel Silva230.82
Dolores Pérez-bendito371.80
César Hervás418314.38