Application of visible and near-infrared spectroscopy for evaluation of ewes milk with different feeds
A. Bahri A B , S. Nawar C E , H. Selmi D , M. Amraoui A , H. Rouissi A and A. M. Mouazen C E
+ Author Affiliations
- Author Affiliations
A Department of Animal Production, Higher School of Agriculture of Mateur, 7030 Mateur, Tunisia.
B National Agronomy Institute Tunis, 43 Avenue Charles Nicolle, Tunis 1082.
C Department of Environment, Ghent University, Coupure links 653, 9000 Gent, Belgium.
D Sylvo-Pastoral Institute of Tabarka, University of Jandouba, BP.n°345, Tabarka 8110, Tunisia.
E Corresponding author. Email: said.nawar@ugent.be; abdul.mouazen@ugent.be
Animal Production Science 59(6) 1190-1200 https://doi.org/10.1071/AN17240
Submitted: 19 April 2017 Accepted: 29 May 2018 Published: 1 August 2018
Abstract
Rapid measurement optical techniques have the advantage over traditional methods of being faster and non-destructive. In this work visible and near-infrared spectroscopy (vis-NIRS) was used to investigate differences between measured values of key milk properties (e.g. fat, protein and lactose) in 30 samples of ewes milk according to three feed systems; faba beans, field peas and control diet. A mobile fibre-optic vis-NIR spectrophotometer (350–2500 nm) was used to collect reflectance spectra from milk samples. Principal component analysis was used to explore differences between milk samples according to the feed supplied, and a partial least-squares regression and random forest regression were adopted to develop calibration models for the prediction of milk properties. Results of the principal component analysis showed clear separation between the three groups of milk samples according to the diet of the ewes throughout the lactation period. Milk fat, protein and lactose were predicted with good accuracy by means of partial least-squares regression (R2 = 0.70–0.83 and ratio of prediction deviation, which is the ratio of standard deviation to root mean square error of prediction = 1.85–2.44). However, the best prediction results were obtained with random forest regression models (R2 = 0.86–0.90; ratio of prediction deviation = 2.73–3.26). The adoption of the vis-NIRS coupled with multivariate modelling tools can be recommended for exploring to differences between milk samples according to different feed systems, and to predict key milk properties, based particularly on the random forest regression modelling technique.
Additional keywords: chemometrics, feeding, random forest.
References
Abdel Rahman AM, Pawling J, Ryczko M, Caudy AA, Dennis JW (2014) Targeted metabolomics in cultured cells and tissues by mass spectrometry: method development and validation. Analytica Chimica Acta 845, 53–61.| Targeted metabolomics in cultured cells and tissues by mass spectrometry: method development and validation.Crossref | GoogleScholarGoogle Scholar |
Adamopoulos KG, Goula AM, Petropakis HJ (2001) Quality control during processing of Feta cheese NIR application. Journal of Food Composition and Analysis 14, 431–440.
| Quality control during processing of Feta cheese NIR application.Crossref | GoogleScholarGoogle Scholar |
Aernouts B, Polshin E, Lammertyn J, Saeys W (2011) Visible and near-infrared spectroscopic analysis of raw milk for cow health monitoring: Reflectance or transmittance? Journal of Dairy Science 94, 5315–5329.
| Visible and near-infrared spectroscopic analysis of raw milk for cow health monitoring: Reflectance or transmittance?Crossref | GoogleScholarGoogle Scholar |
Aske N, Kallevik H, Sjoblom J (2001) Determination of saturate, aromatic, resin, and asphaltenic (SARA) components in crude oils by means of infrared and near-infrared spectroscopy. Energy & Fuels 15, 1304–1312.
| Determination of saturate, aromatic, resin, and asphaltenic (SARA) components in crude oils by means of infrared and near-infrared spectroscopy.Crossref | GoogleScholarGoogle Scholar |
Balthazar CF, Pimentel TC, Ferrao LL, Almada CN, Santillo A, Albenzio M, Mollakhalili N, Mortazavian AM, Nascimento JS, Silva MC, Freitas MQ, Sant’Ana AS, Granato D, Cruz AG (2017) Sheep milk: physicochemical characteristics and relevance for functional food development. Comprehensive Reviews in Food Science and Food Safety 16, 247–262.
| Sheep milk: physicochemical characteristics and relevance for functional food development.Crossref | GoogleScholarGoogle Scholar |
Bertrand D, Scotter CNG (1992) Application of multivariate analyses to NIR spectra of gelatinized starch. Applied Spectroscopy 46, 1420–1425.
| Application of multivariate analyses to NIR spectra of gelatinized starch.Crossref | GoogleScholarGoogle Scholar |
Birlouez-Aragon I, Sabat P, Gouti N (2002) A new method for discriminating milk heat treatment. International Dairy Journal 12, 59–67.
| A new method for discriminating milk heat treatment.Crossref | GoogleScholarGoogle Scholar |
Borin A, Ferrao MF, Mell C, Maretto DA, Poppi RJ (2006) Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk. Analytica Chimica Acta 579, 25–32.
| Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk.Crossref | GoogleScholarGoogle Scholar |
Boulesteix AL, Janitza S, Kruppa J, König IR (2012) Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics. Data Mining and Knowledge Discovery 2, 493–507.
| Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics.Crossref | GoogleScholarGoogle Scholar |
Breiman L (2001) Statistical modeling: the two cultures. Statistical Science 16, 199–231.
| Statistical modeling: the two cultures.Crossref | GoogleScholarGoogle Scholar |
Carrouée B, Crepon K, Peyronnet C (2003) Les protéagineux: intérêt dans les systèmes de production fourragers français et européens. Fourrages (Versailles) 174, 163–182.
Chang CW, Laird DA, Mausbach MJ, Hurburgh CR (2001) Near-infrared reflectance spectroscopy – principal components regression analyses of soil properties. Soil Science Society of America Journal 65, 480–490.
| Near-infrared reflectance spectroscopy – principal components regression analyses of soil properties.Crossref | GoogleScholarGoogle Scholar |
Chen JY, Iyo C, Kawano S (1999) Development of calibration with sample set compensation for determining the fat content of unhomogenised raw milk by a simple near infrared transmittance method. Journal of Near Infrared Spectroscopy 7, 265–273.
| Development of calibration with sample set compensation for determining the fat content of unhomogenised raw milk by a simple near infrared transmittance method.Crossref | GoogleScholarGoogle Scholar |
Colombani C, Fritz S, Guillaume F (2012) A comparison of partial least squares (PLS) and sparse PLS regressions in genomic selection in French dairy cattle. Journal of Dairy Science 95, 2120–2131.
| A comparison of partial least squares (PLS) and sparse PLS regressions in genomic selection in French dairy cattle.Crossref | GoogleScholarGoogle Scholar |
Coppa M, Martin B, Agabriel C, Chassaing C, Sibra C, Constant I, Graulet B, Andueza D (2012) Authentication of cow feeding and geographic origin on milk using visible and near-infrared spectroscopy. Journal of Dairy Science 95, 5544–5551.
| Authentication of cow feeding and geographic origin on milk using visible and near-infrared spectroscopy.Crossref | GoogleScholarGoogle Scholar |
Efron B (1979) Bootstrap methods: another look at the jackknife. Annals of Statistics 7, 1–26.
| Bootstrap methods: another look at the jackknife.Crossref | GoogleScholarGoogle Scholar |
Efron B, Tibshirani R (1994) An introduction to the bootstrap. (Chapman & Hall, Inc.: New York)
Ferragina A, Campos GDL, Vazquez AI, Cecchinato A, Bittante G (2015) Bayesian regression models outperform partial least squares methods for predicting milk components and technological properties using infrared spectral data. Journal of Dairy Science 98, 8133–8151.
| Bayesian regression models outperform partial least squares methods for predicting milk components and technological properties using infrared spectral data.Crossref | GoogleScholarGoogle Scholar |
Geladi P, Kowalski B (1986) Partial least-squares regression: a tutorial. Analytica Chimica Acta 185, 1–17.
| Partial least-squares regression: a tutorial.Crossref | GoogleScholarGoogle Scholar |
Hammami M, Dridi S, Zaïdi F, Maâmouri O, Rouissi H, Bleckerc C, Karoui R (2013) The use of front-face fluorescence spectroscopy for differentiating between the quality of sheep milks from different genotypes and 2 feeding systems. International Journal of Food Properties 16, 1322–1338.
| The use of front-face fluorescence spectroscopy for differentiating between the quality of sheep milks from different genotypes and 2 feeding systems.Crossref | GoogleScholarGoogle Scholar |
Hastie T, Tibshirani R, Friedman J (2009) ‘The elements of statistical learning; Springer Series in statistics.’ (Springer New York: New York)
Ho TK (1998) The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 832–844.
| The random subspace method for constructing decision forests.Crossref | GoogleScholarGoogle Scholar |
Hourant P, Baeten V, Morales MT, Meurens M, Aparicio R (2000) Oil and fat classification by selected bands of near-infrared spectroscopy. Applied Spectroscopy 54, 1168–1174.
| Oil and fat classification by selected bands of near-infrared spectroscopy.Crossref | GoogleScholarGoogle Scholar |
Hu W (2009) Identifying predictive markers of chemosensitivity of breast cancer with random forests. Cancer 13, 59–64.
Jankovská R, Sustová K (2003) Analysis of cow milk by near infrared spectroscopy. Czech Journal of Food Sciences 21, 123–128.
| Analysis of cow milk by near infrared spectroscopy.Crossref | GoogleScholarGoogle Scholar |
Jolliffe IT (1986) ‘Principal component analysis.’ (Springer: New York)
Karoui R, Hammami M, Rouissi H, Blecker C (2011) Mid infrared and fluorescence spectroscopies coupled with factorial discriminant analysis technique to identify sheep milk from different feeding systems. Food Chemistry 127, 743–748.
| Mid infrared and fluorescence spectroscopies coupled with factorial discriminant analysis technique to identify sheep milk from different feeding systems.Crossref | GoogleScholarGoogle Scholar |
Kawamura S, Kawasaki M, Nakatsuji H, Natsuga M (2007) Near-infrared spectroscopic sensing system for online monitoring of milk quality during milking. Sensing and Instrumentation for Food Quality and Safety 1, 37–43.
| Near-infrared spectroscopic sensing system for online monitoring of milk quality during milking.Crossref | GoogleScholarGoogle Scholar |
Klassen M, Cummings M, Saldana G (2008) Investigation of random forest performance with cancer microarray data. In ‘Proceedings of the ISCA 23rd international conference on computers and their applications, CATA Cancun, Mexico’. (Ed T Philip) pp. 64–69. (International Society for Computers and Their Applications: Cary, NC)
Knorr D, Zenker M, Heinz V, Lee DU (2004) Applications and potential of ultrasonics in food processing. Trends in Food Science & Technology 15, 261–266.
| Applications and potential of ultrasonics in food processing.Crossref | GoogleScholarGoogle Scholar |
Kulmyrzaev A, Bertrand D, Dufour E (2008) Characterization of different blue cheeses using a custom-design multispectral imager. Dairy Science & Technology 88, 537–548.
| Characterization of different blue cheeses using a custom-design multispectral imager.Crossref | GoogleScholarGoogle Scholar |
Leadley CE, Williams A (2006) Pulsed electric field processing, power ultrasound and other emerging technologies. In ‘Food processing hand book’. (Ed. JG Brennan) (Wiley-VchVerlag GmbH & Co. KGaA: Weinheim)
Liaw A, Wiener M (2015) Breiman and Cutler’s Random Forests for Classification and Regression Version (4.6–12). Available at https://cran.r-project.org/web/packages/randomForest/randomForest.pdf [Verified 14 January 2016]
Löw F, Schorcht G, Michel U, Dech S, Conrad C (2012) Per-field crop classification in irrigated agricultural regions in Middle Asia using random forest and support vector machine ensemble. In SPIE remote sensing, Edinburgh, United Kingdom.
Maeda H, Ozaki Y, Tanaka M, Hayashi N, Kojima T (1995) Near infrared spectroscopy and chemometrics studies of temperature-dependent spectral variations of water: relationship between spectral changes and hydrogen bonds. Journal of Near Infrared Spectroscopy 3, 191–201.
| Near infrared spectroscopy and chemometrics studies of temperature-dependent spectral variations of water: relationship between spectral changes and hydrogen bonds.Crossref | GoogleScholarGoogle Scholar |
Martin B, Jestin M, Constant I, Agabriel C, Andueza D (2006) Traceability of tanker milk origin (plain – mountain) using visible or near infrared spectroscopic. 3R. Rencontre Recherche Ruminant 13, 194
Melfsen A, Hartung E, Haeussermann A (2012) Accuracy of milk composition analysis with near infrared spectroscopy in diffuse reflection mode. Biosystems Engineering 112, 210–217.
| Accuracy of milk composition analysis with near infrared spectroscopy in diffuse reflection mode.Crossref | GoogleScholarGoogle Scholar |
Mevik BH, Wehrens R, Liland KH (2015) The pls package: principal component and partial least squares regression. Available at http://mevik.net/work/software/pls.html [Verified 1 May 2016]
Moser G, Tier B, Crump R, Khatkar M, Raadsma H (2009) A comparison of five methods to predict genomic breeding values of dairy bulls from genome-wide SNP markers. Genetics, Selection, Evolution 31, 41–56.
Mouazen AM, Dridi S, Rouissi H, De Baerdemaeker J, Ramon H (2007) Feasibility study on using VISNIR spectroscopy coupled with factorial discriminant analysis technique to identify sheep milk from different genotypes and feeding systems. Journal of Near Infrared Spectroscopy 15, 359–369.
| Feasibility study on using VISNIR spectroscopy coupled with factorial discriminant analysis technique to identify sheep milk from different genotypes and feeding systems.Crossref | GoogleScholarGoogle Scholar |
Mouazen AM, Dridi S, Rouissi H, De Baerdemaeker J, Ramon H (2009) Prediction of selected ewe’s milk properties and differentiating between pasture and box feeding using visible and near infrared spectroscopy. Biosystems Engineering 104, 353–361.
| Prediction of selected ewe’s milk properties and differentiating between pasture and box feeding using visible and near infrared spectroscopy.Crossref | GoogleScholarGoogle Scholar |
Naes T, Isaksson T, Fearn T, Davies T (2002) ‘A user friendly guide to multivariate calibration and classification.’ (NIR Publications: Chichester, UK)
Núñez-Sánchez N, Martínez-Marín AL, Polvillo O, Fernández-Cabanás VM, Carrizosa J, Urrutia B, Serradilla JM (2016) Near Infrared Spectroscopy (NIRS) for the determination of the milk fat fatty acid profile of goats. Food Chemistry 190, 244–252.
| Near Infrared Spectroscopy (NIRS) for the determination of the milk fat fatty acid profile of goats.Crossref | GoogleScholarGoogle Scholar |
Osborne BG, Fearn T, Hindle PH (1993) Practical NlR spectroscopy with applications. In ‘Food and beverage analysis’. (Eds BG Osborne, T Fearn, PH Hindle) pp. 11–35. (Longman: Essex)
Peters J, DeBaets B, Verhoest NEC, Samson R, Degroeve S, DeBecker P, Huybrechts W (2007) Random Forests as a tool for ecohydrological distribution modelling. Ecological Modelling 207, 304–318.
| Random Forests as a tool for ecohydrological distribution modelling.Crossref | GoogleScholarGoogle Scholar |
Prasad AM, Iverson LR, Liaw A (2006) Newer classification and regression tree techniques: Bagging and random forest for ecological prediction. Ecosystems 9, 181–199.
| Newer classification and regression tree techniques: Bagging and random forest for ecological prediction.Crossref | GoogleScholarGoogle Scholar |
Qi Y (2012) ‘Random forest for bioinformatics. Ensemble machine learning.’ (Springer)
Qiu S, Wang J, Gao L (2014) Discrimination and characterization of strawberry juice based on electronic nose and tongue: comparison of different juice processing approaches by LDA, PLSR, RF, and SVM. Journal of Agricultural and Food Chemistry 62, 6426–6434.
| Discrimination and characterization of strawberry juice based on electronic nose and tongue: comparison of different juice processing approaches by LDA, PLSR, RF, and SVM.Crossref | GoogleScholarGoogle Scholar |
Raharintsoa C, Gaulard ML, Alais C (1978) Effet des ultrasons cavitants sur la coagulation du lait par les enzymes. Le Lait INRA Editions 58, 559–574.
| Effet des ultrasons cavitants sur la coagulation du lait par les enzymes.Crossref | GoogleScholarGoogle Scholar |
Rinnan A, Berg FVD, Engelsen SB (2009) Review of the most common pre-processing techniques for near-infrared spectra. Trends in Analytical Chemistry 28, 1201–1222.
| Review of the most common pre-processing techniques for near-infrared spectra.Crossref | GoogleScholarGoogle Scholar |
Rouissi H, Rekik B, Selmi H, Hammami M, Ben Gara A (2008) Milk production performances of Tunisian Sicilo-Sarde dairy ewes fed local concentrate. LRRD Livestock Research for Rural Development 20, 102–108.
Růžičková J, Šustová K (2006) Determination of selected parameters of quality of the dairy products by NIR spectroscopy. Czech Journal of Food Sciences 24, 255–260.
| Determination of selected parameters of quality of the dairy products by NIR spectroscopy.Crossref | GoogleScholarGoogle Scholar |
SAS (2002) ‘User’s guide. Statistics version.’ 8th edn. (SAS Institute Inc.: Cary, NC)
Šašić S, Ozaki Y (2001) Short-wave near-infrared spectroscopy of biological fluids. Quantitative analysis of fat, protein, and lactose in raw milk by partial least-squares regression and band assignment. Analytical Chemistry 73, 64–71.
| Short-wave near-infrared spectroscopy of biological fluids. Quantitative analysis of fat, protein, and lactose in raw milk by partial least-squares regression and band assignment.Crossref | GoogleScholarGoogle Scholar |
Shenk JS, Workman J, Westerhaus MO (1992) Application of NIR spectroscopy to agricultural products. In ‘Handbook of near-infrared analysis’. pp. 383–431. (Eds D Burns, E Ciurczak) (Marcel Dekker: New York)
Soria AC, Villamiel M (2010) Effect of ultrasound on the technological properties and bioactivity of food: a review. Trends in Food Science & Technology 21, 323–331.
| Effect of ultrasound on the technological properties and bioactivity of food: a review.Crossref | GoogleScholarGoogle Scholar |
Soyeurt H, Dehareng F, Gengler N, McParland S, Wall E, Berry DP, Coffey M, Dardenne P (2011) Mid-infrared prediction of bovine milk fatty acids across multiple breeds, production systems, and countries. Journal of Dairy Science 94, 1657–1667.
| Mid-infrared prediction of bovine milk fatty acids across multiple breeds, production systems, and countries.Crossref | GoogleScholarGoogle Scholar |
Statnikov A, Wang L, Aliferis CF (2008) A comprehensive comparison of randomforests and support vector machines for microarray-based cancer classification. BMC Bioinformatics 9, 319–329.
| A comprehensive comparison of randomforests and support vector machines for microarray-based cancer classification.Crossref | GoogleScholarGoogle Scholar |
Tsenkova R, Atanassova S, Itoh K, Ozaki Y, Toyoda K (2000) Near infrared spectroscopy for biomonitoring: Cow milk composition measurement in a spectral region from 1100 to 2400 nanometers. Journal of Animal Science 78, 515–522.
| Near infrared spectroscopy for biomonitoring: Cow milk composition measurement in a spectral region from 1100 to 2400 nanometers.Crossref | GoogleScholarGoogle Scholar |
Tsenkova R, Atanassova S, Kawano S, Toyoda K (2001) Somatic cell count determination in cow’s milk by near-infrared spectroscopy: a new diagnostic tool. Journal of Animal Science 79, 2550–2557.
| Somatic cell count determination in cow’s milk by near-infrared spectroscopy: a new diagnostic tool.Crossref | GoogleScholarGoogle Scholar |
Tsenkova R, Atanassova S, Morita H, Ikuta K, Toyoda K, Iordanova IK, Hakogi E (2006) Near infrared spectra of cows’ milk for milk quality evaluation: disease diagnosis and pathogen identification. Journal of Near Infrared Spectroscopy 14, 363–370.
| Near infrared spectra of cows’ milk for milk quality evaluation: disease diagnosis and pathogen identification.Crossref | GoogleScholarGoogle Scholar |
Valenti B, Martin B, Andueza D, Leroux C, Labonne C, Lahalle F, Larroque H, Brunschwige P, Lecomte C, Brochard M, Ferlay A (2013) Infrared spectroscopic methods for the discrimination of cows’ milk according to the feeding system, cow breed and altitude of the dairy farm. International Dairy Journal 32, 26–32.
| Infrared spectroscopic methods for the discrimination of cows’ milk according to the feeding system, cow breed and altitude of the dairy farm.Crossref | GoogleScholarGoogle Scholar |
Wold S, Sjostrom M, Eriksson L (2001) PLS-regression: a basic tool of chemometrics. Chemometrics and Intelligent Laboratory Systems 58, 109–130.
| PLS-regression: a basic tool of chemometrics.Crossref | GoogleScholarGoogle Scholar |
Workman J (2007) Practical guide to interpretive near-infrared spectroscopy. (CRC Press)
