Abstract
To enable non-invasive blood glucose monitoring using near infrared spectroscopy, a modified sequential floating selection method is proposed to remove uninformative data from the spectrum. A linear discriminant function is then used for classification based on selected features. Experiments show that this approach is able to give promising prediction results by classifying near infrared spectroscopic data of blood glucose with good accuracy.
Original language | English |
---|---|
Pages (from-to) | 284-288 |
Number of pages | 5 |
Journal | Journal of Applied Spectroscopy |
Volume | 80 |
Issue number | 2 |
DOIs | |
Publication status | Published - 1 May 2013 |
Keywords
- Linear discriminant function
- Near infrared
- Sequential floating selection
- Spectroscopic data
ASJC Scopus subject areas
- Condensed Matter Physics
- Spectroscopy