Variable Selection Using Genetic Algorithm for Analysis of Near-Infrared Spectral Data Using Partial Least Squares

Author

Siang Soh, Chit ; Meng Ong, Kok ; Raveendran, P.

Author_Institution

Dept. of Electr. Eng., Malaya Univ., Kuala Lumpur

fYear

2006

Firstpage

1178

Lastpage

1181

Abstract

Genetic algorithm is used to perform variable selection to determine the ranges of wavelengths in NIR spectral data suitable to be used as predictors in multivariate calibration model via partial least squares. The NIR spectral data consists of three components of active substances, namely human serum albumin (HSA), gamma-globulin and glucose. The wavelength selection is able to improve the calibration model by selecting the wavelengths that contains information or correlated with the concentration of substances, while others non-chosen wavelengths, which contribute no information or contain noises, are excluded from the calibration model

Keywords

bio-optics; biochemistry; biomedical measurement; blood; calibration; genetic algorithms; infrared spectra; least squares approximations; medical computing; molecular biophysics; proteins; gamma-globulin; genetic algorithm; glucose; human serum albumin; multivariate calibration model; near-infrared spectral data analysis; partial least squares; variable selection; wavelength selection; Algorithm design and analysis; Blood; Calibration; Data engineering; Genetic algorithms; Input variables; Least squares methods; Predictive models; Spectral analysis; Sugar;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the

Conference_Location

Shanghai

Print_ISBN

0-7803-8741-4

Type

conf

DOI

10.1109/IEMBS.2005.1616633

Filename

1616633