Data Fitting and Experimental Design
in Dynamical Systems with EASY-FIT ModelDesign - User's Guide
K. Schittkowski, Report, Department of Computer Science, University of Bayreuth
(2009)
Abstract:
EASY-FIT
ModelDesign
is an interactive software system to identify parameters in explicit model
functions, dynamical systems of equations, Laplace transformations, systems of
ordinary differential equations, differential algebraic equations, or systems of
one-dimensional time-dependent partial differential equations with or without
algebraic equations. Proceeding from given experimental data, i.e., observation
times and measurements, the minimum least squares distance of measured data from
a fitting criterion is computed, that depends on the solution of the dynamical
system. Moreover, it is possible to predetermine an optimal experimental design
by fixing the model parameters. Additional design parameters, for example
initial concentrations or input feeds, are used to minimize the size of
confidence intervals. Weight optimization helps to identify relevant time values
where experiments can be taken.
The software system is implemented in form of a database under Microsoft Office
Access 2007 running under Windows XP or higher, and comes with the royalty-free
runtime version. The underlying numerical algorithms are coded in Fortran and
are executable independently from the interface. Model functions are either
interpreted and evaluated symbolically by a program called PCOMP permitting
automatic differentiation of nonlinear model functions, or by user-provided
Fortran subroutines.The documentation gives an
extensive review of the applied techniques, the underlying numerical routines,
the declaration of model functions, the data definitions, and the
generated output. The usage of the GUI and the underlying Fortran codes is
outlined, and a set of 1,300 test examples is described which is part of the
database. The report comes with about 500 references.
To download the report, click here: easy_fit.pdf