Integration of independent component analysis with near infrared spectroscopy for evaluation of rice freshness

Yung-Kun Chuang; Suming Chen; Stephen R. Delwiche; Y. Martin Lo; Chao-Yin Tsai; I-Chang Yang; Yi-Ping Hu

doi:10.1117/12.921309

4 May 2012 Integration of independent component analysis with near infrared spectroscopy for evaluation of rice freshness

Yung-Kun Chuang, Suming Chen, Stephen R. Delwiche, Y. Martin Lo, Chao-Yin Tsai, I-Chang Yang, Yi-Ping Hu

Author Affiliations +

Proceedings Volume 8369, Sensing for Agriculture and Food Quality and Safety IV; 83690X (2012) https://doi.org/10.1117/12.921309
Event: SPIE Defense, Security, and Sensing, 2012, Baltimore, Maryland, United States

Abstract

Determination of freshness is an important issue for rice quality. Near infrared (NIR) spectroscopy, a rapid nondestructive inspection method based on specific absorptions within a given range of wavelengths corresponding to the constituents in the sample, has been widely applied for evaluation of internal quality of agricultural products. Since NIR spectra of a mixture may be approximated as the linear addition of individual spectra of the constituents in the mixture, such a mixture spectrum thus can be regarded as 'blind sources' as the proportion of constituents in the samples remains unknown. A multiuse statistical approach, independent component analysis (ICA), is capable of disassembling the mixture signals of Gaussian distribution into non-Gaussian independent constituents, and (with assumption of independent constituent spectral response) can give a complete explanation about the property of constituents in the mixture. By example, a total of 180 white rice samples were collected from 6 crop seasons (from 2006 to 2010) for the purpose of developing an ICA NIR based procedure for rice freshness. , Values of pH were determined by a conventional (bromothymol blue methyl red) method. The calibration model of white rice yielded R_c = 0.939, SEC = 0.202, r_p = 0.803 and SEP = 0.233 using original full wavelength range (400 to 2498 nm) spectra and 5 independent components (ICs). Freshness of the white rice can be distinguished either visually by 3-dimensional diagram composed from ICs 2, 3 and 4, or statistically by a calibration model. The results show that ICA with NIR can quickly identify and effectively quantify the pH value in white rice with high predictability, and has the potential to be a useful tool for evaluating rice freshness.

Citation Download Citation

Yung-Kun Chuang, Suming Chen, Stephen R. Delwiche, Y. Martin Lo, Chao-Yin Tsai, I-Chang Yang, and Yi-Ping Hu "Integration of independent component analysis with near infrared spectroscopy for evaluation of rice freshness", Proc. SPIE 8369, Sensing for Agriculture and Food Quality and Safety IV, 83690X (4 May 2012); https://doi.org/10.1117/12.921309

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