Abstract
Enhanced uni-flow counterpropagation networks are used as pattern recognition systems and applied to the identification of chemical structure from corresponding infrared spectra. It is shown that such networks are more suitable for this type of problem than backpropagation networks, both in terms of training times and network performance. The problem of optimum classification between highly similar infrared spectra is addressed, and factors such as training set size, sampling rate, data pre-processing, output data representation and the number of Kohonen layer nodes are considered in this context. It is shown that such networks may achieve rates of correct classification in excess of 90%, although the learning of correct decision boundaries is highly sensitive to the above parameters in cases where the non-informational content of training and test data varies considerably with respect to the informational content, and hence clustering of classes in pattern space is incomplete.
Similar content being viewed by others
References
Bellamy LJ. The Infrared Spectra of Complex Molecules, Chapman & Hall, London, 1975
Clark NG. The Shapes of Organic Molecules, Murray, 1977
Meuzelaar HLC, Isenhour TL. Computer-Enhanced Analytical Spectroscopy, Plenum Press, New York, 1987
Preuss DR, Jurs PC. Pattern recognition techniques applied to the interpretation of infrared spectra, Analytical Chem 1974; 46(4): 520–525
Jurs PC. Pattern recognition used to investigate multivariate data in analytical chemistry. Science 1986; 232: 1219–1224
Tanabe K, Tamura T, Uesaka H. Neural network system for the identification of infrared spectra. Appl Spectroscopy 1992; 46(5): 807–810
Hecht-Nielsen R. Counterpropagation networks. In: IEEE First Int Conf on Neural Networks, 1987; Vol 2, 19–32
NeuralWare Inc. Neural Computing, NeuralWare, 1991
Hertz J, Krogh A, Palmer RG. Introduction to the Theory of Neural Computation. Addison-Wesley, Wokingham, UK, 1991
Beal R, Jackson T. Neural Computing, Adam Hilger, 1990
Skapura DM. Neural Networks: Algorithms, Applications & Programming Techniques, Addison-Wesley, Wokingham, UK, 1991
Storey N. Electronics — A Systems Approach, Addison-Wesley, Wokingham, UK, 1992
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Mackenzie, M.D. Counterpropagation networks applied to the classification of alkanes through infrared spectra. Neural Comput & Applic 2, 111–116 (1994). https://doi.org/10.1007/BF01414354
Issue Date:
DOI: https://doi.org/10.1007/BF01414354