An experimental design advisor and neural network analysis package
DANA [Design Advisor/Neural Analyzer] is a PC-based experimental design advisor and neural network analysis system for understanding and optimizing physical processes. Given a specified number of process inputs and outputs, the Design Advisor gives two options for a set of experiments to perform in order to map the input variables to the process output responses: a standard statistical design and a novel smaller design specifically developed for neural network analysis. The neural network employed in the Neural Analyzer is the back-propagation type, in which a single hidden layer is used to relate the input nodes (variables) to the output nodes (responses) for the experimental data set analyzed. The Network Output module uses the neural model to produce a number of useful graphs and a "Virtual Process" for interactive modeling.
Unable to display preview. Download preview PDF.
- Box, G. E. P., W. G. Hunter, and J. S. Hunter, 1978, Statistics for Experimenters, John Wiley and Sons, New York.Google Scholar
- Cybenko, G., 1989, Approximation by superpositions of a sigmoid function, Mathematics of Control, Signals, and Systems, 2, 303–314.Google Scholar
- Hertz, J., A. Krogh, and R. G. Palmer, 1991, Introduction to the Theory of Neural Computation, Addison-Wesley, New York, NY.Google Scholar
- Press, W. H., B. P. Flannery, S. A. Teukolsky, and W. T. Vettering, 1986, Numerical Recipes: The Art of Scientific Computing, Cambridge Univ. Press, Cambridge, UK.Google Scholar
- Piovoso, M. J., and A. J. Owens, 1991, Sensor data analysis using artificial neural networks, Fourth International Conference on Chemical Process Control (CPC IV), South Padre Island, TX.Google Scholar
- Rumelhart, D. E., G. E. Hinton, and R. J. Williams, 1986, Learning internal representations by error propagation, in Parallel Distributed Processing, Vol. 1, Foundations, D. E. Rumelhart and J. L. McClelland, ed., MIT Press, Cambridge, MA.Google Scholar