Volume 13, Issue 53 (2015)                   FSCT 2015, 13(53): 103-112 | Back to browse issues page

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Jajromi A, Taghi Zadeh M, Sazgar Nia A, Behzad K. Application of preprocessing techniques for visible/near infrared spectroscopy data in developing a model for the prediction of soluble solid and acidity of lime. FSCT 2015; 13 (53) :103-112
URL: http://fsct.modares.ac.ir/article-7-2955-en.html
Abstract:   (4277 Views)
Investigation of quality characteristics of food products during different manufacturing stages such as storage, processing and consumption is important to reduce food loss. In recent years many researches have established for developing rapid and non-destructive techniques for quality control. In this study the potential of visible and near infrared spectroscopy (Vis/NIRS) in determining the quality parameters of lime including total soluble solid and acidity in reflection mode was investigated in the wavelength range of 400 to 1000 nm.­ The effects of different pre-processing techniques and spectral treatments, such as standard normal variable transformation (SNV), multiplicative scatter correction (MSC), median filter, Savitzky & Golay and the derivatives were evaluated. The model was developed based on partial least squares (PLS) regression. The correlation coefficient (R2) and root mean square error of prediction (RMSEP) for predictive model of soluble solids content was 0.949, 0.105 °Brix respectively. These parameters of the model predicting acidity was found to be 0.909 and 0.118 respectively. These results showed the high potential of Vis/NIRS and the important role of preprocessing techniques in developing precise models for the prediction of lime internal quality characteristics.
Full-Text [PDF 313 kb]   (2358 Downloads)    

Received: 2015/06/10 | Accepted: 2015/11/11 | Published: 2016/06/21

Add your comments about this article : Your username or Email:

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.