Determination of the characteristic wavelengths of photoacoustic glucose signals based on interval partial least square algorithm

Zhong Ren; Guodong Liu; Zhen Huang

doi:10.1117/12.2504063

15 November 2018 Determination of the characteristic wavelengths of photoacoustic glucose signals based on interval partial least square algorithm

Zhong Ren, Guodong Liu, Zhen Huang

Author Affiliations +

Proceedings Volume 10964, Tenth International Conference on Information Optics and Photonics; 1096409 (2018) https://doi.org/10.1117/12.2504063
Event: Tenth International Conference on Information Optics and Photonics (CIOP 2018), 2018, Beijing, China

Abstract

Glucose detection by means of the photoacoustic spectroscopy was performed in this paper. A set of photoacoustic detection system of glucose based on pulsed laser induced ultrasonic detection was established. Based on the photoacoustic system, a series of photoacoustic detection experiments for glucoses with different concentrations were performed. The time-resolved photoacoustic signals and photoacoustic peak-to-peak values of glucose under the excitation wavelengths of pulsed laser from 1300nm-2300nm were obtained. In order to get the optimal absorption wavelengths of glucose, the difference spectrum of photoacoustic peak-to-peak values between the glucoses and the pure water were used. At the same time, the interval partial least square algorithm was used to get the optimal absorption wavelength regions. The integrated wavelength region was divided into 10-15 sub-regions. For each sub-region, the model of partial least square was established, and the cross-validation method was also used. Results show that the wavelength regions of 1350-1440nm and 1490-1550nm are the optimal characteristic wavelength region. The prediction models were established in the optimal wavelength regions, four components of the partial least square algorithm were used. In the chosen optimal wavelengths, the correction coefficient between the glucose predicted concentration and original concentration can reach 0.9879 and 0.9969, respectively, the root mean square error of cross validations (RMSECV) are about 12.5mg/dl and 6.2mg/dl, respectively, the concentration bias is about 0.0581mg/dl, and 2.09mg/dl, respectively.

Citation Download Citation

Zhong Ren, Guodong Liu, and Zhen Huang "Determination of the characteristic wavelengths of photoacoustic glucose signals based on interval partial least square algorithm", Proc. SPIE 10964, Tenth International Conference on Information Optics and Photonics, 1096409 (15 November 2018); https://doi.org/10.1117/12.2504063

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available