INVESTIGADORES
GOICOECHEA Hector Casimiro
artículos
Título:
Representative subset selection and standardization techniques.
Autor/es:
GABRIEL SIANO; GOICOECHEA, HÉCTOR C
Revista:
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
Editorial:
Elsevier
Referencias:
Lugar: Amstermam; Año: 2007 p. 204 - 212
ISSN:
0169-7439
Resumen:
Several algorithms related to the calibration transfer process were tested with the objective of comparing them in terms of its performance.
Firstly, three algorithms for representative subset selection (KennardStone, Leverage and OptiSim) were used and compared to select appropriate
samples to make the calibration transfer. Secondly, three algorithms of spectra standardization were tested using different values for input
parameters. The three methods tested were direct standardization (DS), piecewise direct standardization (PDS) and wavelet hybrid direct
standardization (WHDS), the latter was implemented testing a large number of available filters.
Two data sets were used: a) NIR data acquired from different NIR instruments, previously employed in other publications and available from
the PLS Toolbox, and b) UV data obtained in our laboratory from samples of penicillin dissolved in a culture medium representative of an
industrial process of penicillin production. The spectra were recorded at different rates and from samples undergone to drastic modification on the
pH, originating diverse data sets.
Results show that OptiSim can be recommended on KennardStone and Leverage for representative subset selection for data with similar
structure that the analyzed herein. On the other hand, the performance of WHDS was remarkably better than the other tested methods when NIR
data were analyzed. Finally, a strategy combining PDS optimization with WHDS results a good choice for more complex data. In addition, when
the data become more complex, using wider windows improve the PDS performance.Stone, Leverage and OptiSim) were used and compared to select appropriate
samples to make the calibration transfer. Secondly, three algorithms of spectra standardization were tested using different values for input
parameters. The three methods tested were direct standardization (DS), piecewise direct standardization (PDS) and wavelet hybrid direct
standardization (WHDS), the latter was implemented testing a large number of available filters.
Two data sets were used: a) NIR data acquired from different NIR instruments, previously employed in other publications and available from
the PLS Toolbox, and b) UV data obtained in our laboratory from samples of penicillin dissolved in a culture medium representative of an
industrial process of penicillin production. The spectra were recorded at different rates and from samples undergone to drastic modification on the
pH, originating diverse data sets.
Results show that OptiSim can be recommended on KennardStone and Leverage for representative subset selection for data with similar
structure that the analyzed herein. On the other hand, the performance of WHDS was remarkably better than the other tested methods when NIR
data were analyzed. Finally, a strategy combining PDS optimization with WHDS results a good choice for more complex data. In addition, when
the data become more complex, using wider windows improve the PDS performance.Stone and Leverage for representative subset selection for data with similar
structure that the analyzed herein. On the other hand, the performance of WHDS was remarkably better than the other tested methods when NIR
data were analyzed. Finally, a strategy combining PDS optimization with WHDS results a good choice for more complex data. In addition, when
the data become more complex, using wider windows improve the PDS performance.