bdmtoolbox: controlloop.cpp File Reference

controlloop.cpp File Reference

Application Estimator. More...

#include <estim/arx.h>
#include <stat/emix.h>
#include <base/datasources.h>
#include <base/loggers.h>
#include <design/arx_ctrl.h>

Functions

int main (int argc, char *argv[])

Detailed Description

Application Estimator.

The general task of estimation is defined on the following scheme:

inline_dotgraph_1.dot

Here,

  • Data Source is an object (class DS) providing sequential data, $ [d_1, d_2, \ldots d_t] $.
  • Bayesian Model is an object (class BM) performing Bayesian filtering,
  • Result Logger is an object (class logger) dedicated to storing important data from the experiment.

cmd

Execute command: 

$> estimator config_file.cfg

Full description of the experiment is in the file config_file.cfg which is expected to have the following structure: 

system = {type = "DS_offspring", ...};      // definition of a data source
estimator = {type = "BM_offspring", ...};   // definition of an estimator
logger = {type = "logger_type",...};        // definition of a logger
experiment = {ndat = 11000; };              // definition of number of data records

The above description must be specialized to specific classes. See, Running experiment estimator with ARX data fields how to do it for estimation of an ARX model.

Matlab usage

Execute command: 

>> estimator('config_file.cfg');

when using loggers storing results on hard drives, and 

>> Res=estimator('config_file.cfg');

when using logger of the type "mex_logger". The results will be stored in structure M.

Generated on Fri Aug 27 16:55:19 2010 for bdmtoolbox by  doxygen 1.6.0