Rapid and Accurate Estimation of Milk Fat by Near Infrared Spectroscopy: Comparison of Different Pre-processing and Regression Methods
Abstract views: 3
/ 
PDF downloads: 1
Keywords:
Near-Infrared Spectroscopy, Regression, Pre-Processing, Fat Detection, ChemometryAbstract
This study aims to rapidly and accurately estimate the fat content of milk using near-infrared
spectroscopy and various chemometric analysis methods. In the study, different pre-processing techniques
such as standard normal variate, multiplicative scatter correction, Savitzky-Golay smoothing, and spectral
differentiation were applied along with various modeling approaches such as partial least squares
regression, ridge regression, support vector regression, lasso regression, and random forest regression.
The findings show that pre-processing methods have a decisive impact on model success. In particular,
the use of standard normal variate and first derivative pre-processing methods in combination with partial
least squares regression and ridge regression resulted in the highest accuracy and lowest error values. The
results suggest that near-infrared spectroscopy can be an effective and reliable tool for automation and
real-time monitoring of quality control processes in the dairy industry.
Downloads
References
A. Haug, A. T. Høstmark, and O. M. Harstad, “Bovine milk in human nutrition - A review,” Lipids Health Dis, vol. 6, 2007, doi: 10.1186/1476-511X-6-25,.
R. G. Jensen, “The Composition of Bovine Milk Lipids: January 1995 to December 2000,” J. Dairy Sci, vol. 85, pp. 295–350, 2002, doi: 10.3168/jds.S0022-0302(02)74079-4.
D. M. Barbano, Y. Ma, and M. V. Santos, “Influence of raw milk quality on fluid milk shelf life.,” J Dairy Sci, vol. 89 Suppl 1, pp. E15–E19, Mar. 2006, doi: 10.3168/jds.s0022-0302(06)72360-8.
B. T. Kao, K. A. Lewis, E. J. DePeters, and A. L. Van Eenennaam, “Endogenous production and elevated levels of long-chain n-3 fatty acids in the milk of transgenic mice,” J Dairy Sci, vol. 89, no. 8, pp. 3195–3201, Aug. 2006, doi: 10.3168/jds.S0022-0302(06)72594-2.
R. Karoui and J. De Baerdemaeker, “A review of the analytical methods coupled with chemometric tools for the determination of the quality and identity of dairy products,” Food Chem, vol. 102, no. 3, pp. 621–640, Jan. 2007, doi: 10.1016/J.FOODCHEM.2006.05.042.
B. M. Nicolaï et al., “Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review,” Postharvest Biol Technol, vol. 46, no. 2, pp. 99–118, Nov. 2007, doi: 10.1016/J.POSTHARVBIO.2007.06.024.
R. Tsenkova, S. Atanassova, K. Toyoda, Y. Ozaki, K. Itoh, and T. Fearn, “Near-Infrared Spectroscopy for Dairy Management: Measurement of Unhomogenized Milk Composition,” J Dairy Sci, vol. 82, no. 11, pp. 2344–2351, Nov. 1999, doi: 10.3168/JDS.S0022-0302(99)75484-6.
L. R. Joppa, G. A. Hareland, and R. G. Cantrell, “Quality Characteristics of the Langdon Durum-dicoccoides Chromosome Substitution Lines,” Crop Sci, vol. 31, no. 6, pp. 1513–1517, Nov. 1991, doi: 10.2135/CROPSCI1991.0011183X003100060024X.
J. A. Diaz-Olivares et al., “Near-infrared spectra dataset of milk composition in transmittance mode,” Data Brief, vol. 51, p. 109767, Dec. 2023, doi: 10.1016/J.DIB.2023.109767.
G. K. Krug, “COMPUTER AIDED DESIGN OF EXPERIMENTS.,” Periodica Polytechnica Electrical Engineering, vol. 19, no. 3, pp. 181–189, 1975, doi: 10.2307/1266770.
Å. Rinnan, F. van den Berg, and S. B. Engelsen, “Review of the most common pre-processing techniques for near-infrared spectra,” TrAC Trends in Analytical Chemistry, vol. 28, no. 10, pp. 1201–1222, Nov. 2009, doi: 10.1016/J.TRAC.2009.07.007.
R. J. Barnes, M. S. Dhanoa, and S. J. Lister, “Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra,” Appl Spectrosc, vol. 43, no. 5, pp. 772–777, 1989, doi: 10.1366/0003702894202201;JOURNAL:JOURNAL:ASPC;CTYPE:STRING:JOURNAL.
P. Geladi, D. MacDougall, and H. Martens, “Linearization and Scatter-Correction for Near-Infrared Reflectance Spectra of Meat,” Appl Spectrosc, vol. 39, no. 3, pp. 491–500, 1985, doi: 10.1366/0003702854248656.
A. Savitzky and M. J. E. Golay, “Smoothing and Differentiation of Data by Simplified Least Squares Procedures,” Anal Chem, vol. 36, no. 8, pp. 1627–1639, Jul. 1964, doi: 10.1021/AC60214A047/ASSET/AC60214A047.FP.PNG_V03.
S. Wold, M. Sjöström, and L. Eriksson, “PLS-regression: a basic tool of chemometrics,” Chemometrics and Intelligent Laboratory Systems, vol. 58, no. 2, pp. 109–130, Oct. 2001, doi: 10.1016/S0169-7439(01)00155-1.
A. E. Hoerl and R. W. Kennard, “Ridge Regression: Biased Estimation for Nonorthogonal Problems,” vol. 12, no. 1.
R. Tibshirani, “Regression Shrinkage and Selection via the Lasso,” Source: Journal of the Royal Statistical Society. Series B (Methodological), vol. 58, no. 1, pp. 267–288, 1996.
H. Drucker, C. J. Burges, L. Kaufman, A. Smola, and V. Vapnik, “Support Vector Regression Machines,” Adv Neural Inf Process Syst, vol. 9, 1996.
L. Breiman, “Random forests,” Mach Learn, vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.
J. A. Diaz-Olivares, I. Adriaens, E. Stevens, W. Saeys, and B. Aernouts, “Online milk composition analysis with an on-farm near-infrared sensor,” Comput Electron Agric, vol. 178, p. 105734, Nov. 2020, doi: 10.1016/J.COMPAG.2020.105734.
V. Fonseca Diaz, B. De Ketelaere, B. Aernouts, and W. Saeys, “Cost-efficient unsupervised sample selection for multivariate calibration,” Chemometrics and Intelligent Laboratory Systems, vol. 215, p. 104352, Aug. 2021, doi: 10.1016/J.CHEMOLAB.2021.104352.
