Taehee Lee wrote that,
>But i have difficulty in finding the time phase model of SEM.
> Especially, the relationship of each variable in SEM which might be called
Spatial
> model of system is general problem, but the time lag for affecting with
each
> variable called Temporal model is very difficult problem.
> If anyone knew the methods or theorical foundation for calculating that
problem, please inform me by Email.
Very accurate predictions of NY Stock Exchange indexes and models
of another different complex objects were obtained with the aid of
twice-multilayered neuronet with active neurons, where each neuron
is modelling GMDH algorithm. In this approach, which corresponds
to the actions of human nervous system, the connections between
several neurons are not fixed but change depending on
the neurons themselves.
The Group Method of Data Handling (GMDH) is self-organizing approach
based on sorting-out of gradually complicated models and evaluation of
them by external criterion on separate part of data sample. As input
variables can be used any parameters, which can influence on the
process. Computer is found structure of model and measure of
influence of parameters on the output variable itself. That model is
better that leads to the minimal value of external criterion. This
inductive approach is different from commonly used deductive
techniques or neural networks.
The GMDH was developed for complex systems modeling, prediction,
identification and approximation of multivariate processes, decision
support after "what-if" scenario, diagnostics, pattern recognition and
clusterization of data sample. It was proved, that for inaccurate,
noisy or small data can be found best optimal simplified model,
accuracy of which is higher and structure is simpler than structure of
usual full physical model.
Recent developments of the GMDH have led to neuronets with active
neurons, which realize twice-multilayered structure: neurons are
multilayered and they are connected into multilayered structure. This
gives possibility to optimize the set of input variables at each
layer, while the accuracy increases. The accuracy of forecasting,
approximation or pattern recognition can be increased beyond the
limits which are reached by neuronet with single neurons.
Not only GMDH algorithms, but many modeling or pattern recognition
algorithms can be used as active neurons. Its accuracy can be
increased in two ways:
- each output of algorithm (active neuron) generate new variable
which can be used as a new factor in next layers of neuronet;
- the set of input factors can be optimized at each layer. In usual
once-multilayered NN the set of input variables can be chosen once
only. The output variables of previous layers in such networks are
very effective secondary inputs for the neurons of next layers.
Neuronets with active neurons and basic GMDH algorithms was described in
Selforganization of Neuronets with Active Neurons.
Ivakhnenko,A.G.,Ivakhnenko,G.A.,Muller,J.A. Pattern recognition and
image analysis, 1994, vol.4, no.2;
Self-Organization of Nets of Active Neurons.
Ivakhnenko A.G., Muller J.-A. SAMS, 1995, vol.20, pp.93-106.
The GMDH theory and source code of some algorithms was also published in
"Inductive Learning Algorithms for Complex System Modeling",
Madala H.R. and Ivakhnenko A.G., 1994, ISBN: 0-8493-4438-7, CRC Press;
and
"Self-organizing Methods in Modelling (Statistics: Textbooks and
Monographs,vol.54)", Farlow, S.J. (ed.), 1984, ISBN: 0-8247-7161-3,
Marcel Dekker Inc.
This method is described now at http://come.to/GMDH
Regards,
Gregory Ivakhnenko
--
National Institute for Strategic Studies
Kyiv, Ukraina
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|