Proceedings of the PSK Conference (대한약학회:학술대회논문집)
- 2002.10a
- /
- Pages.402.2-402.2
- /
- 2002
Algorithm for finding the best regression models using NIR spectra
- Cho, Jung-Hwan (College of Pharmacy. Sookmyung Women′s University) ;
- Huh, Yun-Jung (College of Pharmacy. Sookmyung Women′s University) ;
- Park, Young-Joo (College of Pharmacy. Sookmyung Women′s University)
- Published : 2002.10.01
Abstract
An algorithm for finding the best regression models has been developed using NIR spectral data. In cases of regression analysis for quantitation with NIR spectral data, it is very critical to find essential features from the spectral data. This task was accessed in two ways. The first one was to use all-possible combinations of varibles (wavelengths). Correlation coefficients at each spectral points were calculated to get initial set of variables and all of the possible combinations of variable sets were tested with SEC. SEP and/or
Keywords