Classification of Milk Samples Using CART
- 33 Downloads
Classification and regression tree (CART) analyses have not been explored yet in the field of food physicochemical analysis, to the best of our knowledge. In this work, we tested its classification performance on a set of physicochemical data from raw milk samples from Southern Brazil we already analyzed via well-known supervised methods in a previous work. CART performed better than most of the previously employed methods regarding specificity, sensitivity, and accuracy when classifying samples from the training set. These findings suggest CART could also be employed to classify milk samples as compliant or not to Brazilian regulations and possibly to other countries’ regulations as well.
KeywordsMilk Multivariate analysis Physicochemical analysis CART
Compliance with Ethical Standards
Conflict of Interest
Lucas Hansen declares that he has no conflict of interest. Marco Flôres Ferrão declares that he has no conflict of interest.
This article does not contain any studies with human or animal subjects.
Publication has been approved by all individual participants.
- Brasil (2006) Ministério da Agricultura, Pecuária e Abastecimento. Instrução Normativa n° 68 de 12 de dezembro de 2006. http://extranet.agricultura.gov.br/sislegis-consulta/consultarLegislacao.do?operacao=visualizar&id=17472. Accessed 02/09/19.
- Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth, BelmontGoogle Scholar
- De Carvalho BMA, de Carvalho LM, dos Reis JS, Coimbra LAM, de Souza EB, da Silva Júnior WB, Detmann E, de Carvalho GGP (2015) Rapid detection of whey in milk powder samples by spectrophotometric and multivariate calibration. Food Chem 174:1–7. https://doi.org/10.1016/j.foodchem.2014.11.003 CrossRefGoogle Scholar
- Falk FR, Miller NBA (1992) Primer for soft modelling, 1st edn. University of Akron, Akron, p 80Google Scholar
- Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugenics 7(2):179–188. https://doi.org/10.1111/j.1469-1809.1936.tb02137.x CrossRefGoogle Scholar
- Gondim C, dos S, Junqueira RG, de Souza SVC, Callao MP, Ruisánchez I (2017b) Determining performance parameters in qualitative multi-variate methods using probability of detection (POD) curves. Case study: two common milk adulterants. Talanta 168:23–30. https://doi.org/10.1186/s40550-016-0045-3 CrossRefGoogle Scholar
- India (2015) Ministry of Health and Family Welfare. Manual of methods of analysis of foods. Milk and Milk products, p 187Google Scholar
- ISO (1980) ISO 6092:1980. Dried milk – determination of titratable acidity (Routine method).Google Scholar
- ISO (2007) ISO 22662:2007. Milk and milk products – determination of lactose content by high-performance liquid chromatography (reference method)Google Scholar
- ISO (2008). ISO 488:2008 (IDF 105:2008). Milk – determination of fat content - Gerber butyrometersGoogle Scholar
- ISO (2009). ISO 5764:2009 (IDF 108:2009). Milk – determination of freezing point — thermistor cryoscope method (reference method)Google Scholar
- ISO (2010a) ISO 6731:2010 (IDF 21:2010). Milk, cream and evaporated milk – determination of total solids content (reference method).Google Scholar
- ISO (2010b) ISO 1211:2010 (IDF 1:2010). Milk – determination of fat content – gravimetric method (reference method).Google Scholar
- ISO (2010c) ISO 6091:2010. Dried milk – determination of titratable acidity (reference method)Google Scholar
- ISO (2016) ISO 8968-4:2016 (IDF 20-4). Milk and milk products – determination of nitrogen content–part 4: determination of protein and non-protein nitrogen content and true protein content calculation (reference method)Google Scholar
- Lane JH, Eynon L (1934) Determination of reducing sugars by Fehling’s solution with methylene blue indicator. Norman Rodger, London, p 8Google Scholar
- Liu J (2017) Terahertz spectroscopy and chemometric tools for rapid identification of adulterated dairy product. Opt Quant Electron 49(1). https://doi.org/10.1007/s11082-016-0848-8
- Loh W-Y (2008) Classification and regression tree methods. In: Ruggeri F, Kenett R, Faltin F (eds) Encyclopedia of statistics in quality and reliability. Wiley, pp 315–323Google Scholar
- Mackay H (1929) The detection of milk adulteration (note). Can Med Assoc J 21(3):309Google Scholar
- People’s Republic of China (2010a) Ministry of Health of the People’s Republic of China. GB 5413.5-2010. National food safety standard. Determination of lactose and sucrose in foods for infants and young children, milk and milk products.Google Scholar
- People’s Republic of China (2010b) Ministry of Health of the People’s Republic of China. GB 5009.4-2010. National food safety standard. Determination of Ash in Foods.Google Scholar
- People’s Republic of China (2010c) Ministry of Health of the People’s Republic of China. China GB 5413.33-2010. National food safety standard. Determination of specific gravity in raw milkGoogle Scholar
- People’s Republic of China (2010d) Ministry of Health of the People’s Republic of China. China GB 5009.5-2010 National Food Safety Standard Determination of protein in foodsGoogle Scholar
- People’s Republic of China (2010e) Ministry of Health of the People’s Republic of China. China GB 5413.34-2010 National food safety standard. Determination of acidity in milk and milk products.Google Scholar
- People’s Republic of China (2010f) Ministry of Health of the People’s Republic of China. China GB 5413.39—2010. National food safety standard. Determination of nonfat total milk solids in milk and milk productsGoogle Scholar
- Rezende PS, Carmo GPD, Esteves EG (2015) Optimization and validation of a method for the determination of the refractive index of milk serum based on the reaction between milk and copper(II) sulfate to detect milk dilutions. Talanta 138:196–202. https://doi.org/10.1016/j.talanta.2015.02.020 CrossRefGoogle Scholar
- Scholl PF, Bergana MM, Yakes BJ, Xie Z, Zbylut S, Downey G, Mossoba M, Jablonski J, Magaletta R, Holroyd SE, Buehler M, Qin J, Hurst W, LaPointe JH, Roberts D, Zrybko C, Mackey A, Holton JD, Israelson GA, Payne A, Kim MS, Chao K, Moore JC (2017) Effects of the adulteration technique on the near-infrareddetection of melamine in milk powder. J Agric Food Chem 65(28):5799–5809. https://doi.org/10.1021/acs.jafc.7b02083 CrossRefGoogle Scholar
- Vacchina V, Séby F, Chekri R, Verdeil J, Dumont J, Hulin M, Sirot V, Volatier JL, Serreau R, Rousseau A, Simon T, Guérin T (2017) Optimization and validation of the methods for the total mercury and methylmercury determination in breast milk. Talanta 167:404–410. https://doi.org/10.1016/j.talanta.2017.02.046 CrossRefGoogle Scholar
- Velioglu SD, Elioglu E, Boyaci IH (2017) Rapid discrimination between buffalo and cow milk and detection ofadulteration of buffalo milk with cow milk using synchronous fluorescence spectroscopy in combination with multivariate methods. J Dairy Res 84:2214–2219. https://doi.org/10.1017/S0022029917000073 Google Scholar