Application of neural networks

T A and H Kalayeh 1991. Applications of Neural Networks in Quantitative Structure-Activity ationships of Dihydrofolate Reductase Inhibitors, journal of Medicinal Chemistry 34 2824-2836. ik M and R C Glen 1992. Applications of Rule-induction in the Derivation of Quantitative icture-Activity Relationships. Journal of Computer-Aided Molecular Design 6 349-383. 

TA Andrea, H Kalayeh. Applications of neural networks in quantitative structure-activity relationships of dihydrofolate reductase inhibitors. J Med Chem 34 2824-2836, 1991. 

Application of neural networks to modelling, estimation and control... 

Applications of neural networks are becoming more diverse in chemistry [31-40]. Some typical applications include predicting chemical reactivity, acid strength in oxides, protein structure determination, quantitative structure property relationship (QSPR), fluid property relationships, classification of molecular spectra, group contribution, spectroscopy analysis, etc. The results reported in these areas are very encouraging and are demonstrative of the wide spectrum of applications and interest in this area. 

The ANN as a predictive tool is most effective only within the trained range of input training variables. Those predictions that fall outside the trained range must be considered to be of questionable validity. Even so, whenever experimental data are available for validation, neural networks can be put to effective use. Since an extensive experimental body of data on polymers has been published in the literature, the application of neural networks as a predictive tool for physical, thermodynamic, and other fluid properties is, therefore, promising. It is a novel technique that will continue to be used, and it deserves additional investigation and development. 

Non-linear PCA can be obtained in many different ways. Some methods make use of higher order terms of the data (e.g. squares, cross-products), non-linear transformations (e.g. logarithms), metrics that differ from the usual Euclidean one (e.g. city-block distance) or specialized applications of neural networks [50]. The objective of these methods is to increase the amount of variance in the data that is explained by the first two or three components of the analysis. We only provide a brief outline of the various approaches, with the exception of neural networks for which the reader is referred to Chapter 44. 

Especially the last few years, the number of applications of neural networks has grown exponentially. One reason for this is undoubtedly the fact that neural networks outperform in many applications the traditional (linear) techniques. The large number of samples that are needed to train neural networks remains certainly a serious bottleneck. The validation of the results is a further issue for concern. 

Naidu, S., Zafiriou, E., and McAvoy, T. J., Application of neural networks on the detection of sensor failure during the operation of a control system, Proc. Amer. Control Conf, Pittsburgh, PA (1989). 

Allanic AL, Jezequel JY, Andre JC (1992) Application of neural networks theory to identify two-dimensional fluorescence spectra. Anal Chem 64 2618... 

Boger Z, Karpas Z (1994) Application of neural networks for interpretation of ion mobility and X-ray fluorescence spectra. Anal Chim Acta 292 243... 

Giles, A. E. Aldrich, C. van Deventer, J. S. J. Hydrometallurgy 1996, 43, 241. Slater, M. J. Aldrich, C. Application of Neural Network and Other Learning Technologies in Process Engineering Mujtaba, I. M. Hussain, M. A. Eds. Imperial College Press London, 2001 3. 

J. J. Ferrada, M. D. Gordon, and I. W. Osbome-Lee, "Application of Neural Networks for Fault Diagnosis in Plant Production," paper presented at AIChE National Meeting, San Francisco, 1989. 

Murray, A. F., Ed. Applications of Neural Networks. Kluwer, Dordrecht, 1994. 

Mujtaba, I. M. and Hussain, M.A., Application of Neural Networks and Other Learning Technologies in Process Engineering (Imperial College Press, London, 2001). 

One of the most important applications of neural network methodology is in the extrapolation of electrochemical impedance data obtained in corrosion studies.34 Electrochemical impedance spectroscopy (EIS) can be used to obtain instantaneous corrosion rates. The validation of extension of EIS data frequency range, which is conventionally difficult, can be done using a neural network system. In addition to extension of impedance data frequency range, the neural network identifies problems such as the inherent variability of corrosion data and provides solutions to the problems. Furthermore, noisy or poor-quality data are dealt with by neural works through the output of the parameters variance and confidence.33... 

D21. Douglas, T. H., and Mold, J. W., Applications of neural networks in urologic oncology. Semin. Urol. Oncol. 16, 35-39 (1998). 

There are many excellent introductory books and journal articles on the subject of neural networks. Just a few of them are listed below in the references. Additionally, there are tutorials online at various web sites. However, the applications of neural network techniques to problems in molecular biology and genome informatics are largely to be found in scientific journals and symposium proceedings. 

Other applications of neural networks are sequence classification and feature detection... 

Abremski, K., Sirotkin, K. Lapedes, A (1991). Application of neural networks and information theory to the identification of E.coli transcriptional promoters. Math Model Sci Comput 2, 634-41. 

Lapedes, A., Barnes, C Burks, C., Farber, R. Sirotkin, K. (1989). Application of neural networks and other machine learning algorithms to DNA sequence analysis. In Computers and DNA, SFI Studies in the Sciences of Complexity, vol. 7 (ed. Bell, G. I. Marr, T. G.), pp. 157-82. Addison-Wesley, Rosewood City, CA. 

Applications of neural networks can be broadly classified into three categories ... 

Another fitting procedure, based on the application of neural networks has also been developed [235-238]. The artificial neural-network approach has been shown to produce algebraic models that are good approximations of kinetic mechanisms. Simulations based on this model are much faster than the solution of differential equations but slower than the use of an algebraic model obtained from the polynomial approximation. 

A very novel application of neural networks recently reported was that of maximizing tablet yield in a production environment. The authors analyzed a data set of 100 typical batches of tablets, classified and rated the inputs according to their importance (influence on tablet yield) and used a neural network model to maximize tablet yield while holding tablet quality within specified limits. 

Andrea, T.A. and Kalayeh, H. (1991). Applications of Neural Networks in Quantitative Structure-Activity Relationships of Dihydropholate Reductase Inhibitors. JMetLChem., 34, 2824-2836. 

---