Abstract | ||
---|---|---|
We present results concerning the parameter estimates obtained by prediction error methods in the case of input that are insufficiently rich. Such input signals are typical of industrial measurements where occasional stepwise reference changes occur. As is intuitively obvious, the data located around the input signal discontinuities carry most of the useful information. Using singular value decomposition (SVD) techniques, we show that in noise undermodeling situations, the remaining data may introduce large bias on the model parameters with a possible increase of their total mean square error. A data selection criterion is then proposed to discard such poorly informative data to increase the accuracy of the transfer function estimate. The system discussed in particular is a SISO ARMAX system |
Year | DOI | Venue |
---|---|---|
1996 | 10.1109/78.536685 | IEEE Transactions on Signal Processing |
Keywords | Field | DocType |
possible increase,remaining data,prediction error method,input signal,industrial measurement,data selection criterion,discarding data,total mean square error,system identification,informative data,siso armax system,input signal discontinuity,white noise,predictive models,mean square error,frequency,filtering,computational modeling,singular value decomposition,transfer functions,transfer function,parameter estimation,accuracy,noise | Least squares,Signal processing,Singular value decomposition,Classification of discontinuities,Control theory,Mean squared error,Transfer function,Estimation theory,System identification,Mathematics | Journal |
Volume | Issue | ISSN |
44 | 9 | 1053-587X |
Citations | PageRank | References |
4 | 0.80 | 1 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
P. Carrette | 1 | 6 | 1.53 |
Georges Bastin | 2 | 1039 | 177.30 |
Y.Y. Genin | 3 | 4 | 0.80 |
M. Gevers | 4 | 4 | 0.80 |