Related Experiment Video
Updated: Jun 16, 2026
10:25
Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
Published on: June 28, 2016
[Fast determination of melamine content in milk base on Vis/NIR spectroscopy method]
Shi-Lin Yuan1, Yong He, Tian-Yun Ma
1College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310029, China.
Guang Pu Xue Yu Guang Pu Fen Xi = Guang Pu
|January 28, 2010
Summary
Near Infrared Reflectance Spectroscopy (NIRS) can rapidly detect melamine adulteration in milk. This study developed models using Partial Least Squares and Least Squares-Support Vector Machine for accurate milk analysis.
Area of Science:
- Food Science
- Analytical Chemistry
- Spectroscopy
Context:
- Milk adulteration with melamine poses significant food safety risks.
- Accurate and rapid detection methods are crucial for ensuring milk quality and consumer safety.
Purpose:
- To investigate the feasibility of Near Infrared Reflectance Spectroscopy (NIRS) for detecting melamine in milk.
- To develop and validate predictive models for melamine quantification in milk samples.
Summary:
- 160 milk samples were adulterated with varying melamine concentrations.
- Spectral data was acquired using a Handheld Field Spec spectrometer.
- Moving average smoothing was identified as the optimal pretreatment method.
- Partial Least Squares (PLS) and Least Squares-Support Vector Machine (LS-SVM) models were developed and validated.
- High correlation coefficients (r=0.9174 for PLS, r=0.9109 for LS-SVM) and low Root Mean Standard Errors of Prediction (RMSEP=0.0304 for PLS, RMSEP=0.0467 for LS-SVM) were achieved.
Impact:
- NIRS offers a rapid, non-destructive, and potentially cost-effective method for melamine detection in milk.
- This technology can aid regulatory bodies and the dairy industry in quality control.
- Enhances food safety by enabling quick identification of adulterated milk products.
