{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T21:01:31Z","timestamp":1781557291891,"version":"3.54.5"},"reference-count":37,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T00:00:00Z","timestamp":1596067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In this study, an electronic nose (E-nose) consisting of seven metal oxide semiconductor sensors is developed to identify milk sources (dairy farms) and to estimate the content of milk fat and protein which are the indicators of milk quality. The developed E-nose is a low cost and non-destructive device. For milk source identification, the features based on milk odor features from E-nose, composition features (Dairy Herd Improvement, DHI analytical data) from DHI analysis and fusion features are analyzed by principal component analysis (PCA) and linear discriminant analysis (LDA) for dimension reduction and then three machine learning algorithms, logistic regression (LR), support vector machine (SVM), and random forest (RF), are used to construct the classification model of milk source (dairy farm) identification. The results show that the SVM model based on the fusion features after LDA has the best performance with the accuracy of 95%. Estimation model of the content of milk fat and protein from E-nose features using gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and random forest (RF) are constructed. The results show that the RF models give the best performance (R2 = 0.9399 for milk fat; R2 = 0.9301 for milk protein) and indicate that the proposed method in this study can improve the estimation accuracy of milk fat and protein, which provides a technical basis for predicting the quality of milk.<\/jats:p>","DOI":"10.3390\/s20154238","type":"journal-article","created":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T03:36:38Z","timestamp":1596080198000},"page":"4238","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":81,"title":["Milk Source Identification and Milk Quality Estimation Using an Electronic Nose and Machine Learning Techniques"],"prefix":"10.3390","volume":"20","author":[{"given":"Fanglin","family":"Mu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9745-664X","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Engineering, Merz Court, Newcastle University, Newcastle upon Tyne NE1 7RU, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,7,30]]},"reference":[{"key":"ref_1","first-page":"1276","article-title":"Composition, coagulation characteristics, and cheese making capacity of yak milk","volume":"103","author":"Zhang","year":"2020","journal-title":"J. Food Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.foodchem.2010.12.084","article-title":"Trace element levels in raw milk from northern and southern regions of Croatia","volume":"127","author":"Bilandzic","year":"2011","journal-title":"Food Chem."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1910","DOI":"10.3168\/jds.S0022-0302(69)86872-4","article-title":"Contribution of milk fat to the flavor of milk","volume":"52","author":"Tamsma","year":"1969","journal-title":"J. Dairy Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1007\/BF02666792","article-title":"The flavor potential of milk fat. A review of its chemical nature and biochemical origin","volume":"44","author":"Kinsella","year":"1967","journal-title":"J. Am. Oil Chem. Soc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1017\/S0022029900020768","article-title":"Mechanisms of formation of aroma compounds in milk and milk products","volume":"46","author":"Forss","year":"1979","journal-title":"J. Dairy Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1021\/bk-2007-0971.ch002","article-title":"Flavor analysis of dairy products","volume":"971","author":"Mcgorrin","year":"2007","journal-title":"ACS Symp. Ser."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"112","DOI":"10.3168\/jds.S0022-0302(68)86929-2","article-title":"Evidence for a dimethyl sulfide precursor in milk","volume":"51","author":"Keenan","year":"1968","journal-title":"J. Dairy Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.3168\/jds.2017-13141","article-title":"Effect of different forage types on the volatile and sensory properties of bovine milk","volume":"101","author":"Faulkner","year":"2018","journal-title":"J. Dairy Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1111\/j.1750-3841.2006.00051.x","article-title":"Interactions of milk proteins and volatile flavor compounds: Implications in the development of protein foods","volume":"71","author":"Kuhn","year":"2006","journal-title":"J. Food Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"277","DOI":"10.3952\/physics.v58i3.3816","article-title":"Region dependent C-13, N-15, O-18 isotope ratios in the cow milk","volume":"58","author":"Garbaras","year":"2018","journal-title":"Lith. J. Phys."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1002\/rcm.7840","article-title":"Changes in stable isotope ratios in PDO cheese related to the area of production and green forage availability. The case study of Pecorino Siciliano","volume":"31","author":"Valenti","year":"2017","journal-title":"Rapid Commun. Mass Spectrom."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.foodres.2018.06.066","article-title":"NMR metabolomic fingerprinting distinguishes milk from different farms","volume":"113","author":"Tenori","year":"2018","journal-title":"Food Res. Int."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.foodcont.2017.01.004","article-title":"Matching portable NIRS instruments for in situ monitoring indicators of milk composition","volume":"76","author":"Soldado","year":"2017","journal-title":"Food Control"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.17576\/jsm-2018-4711-10","article-title":"Rapid microbial detection model system in UHT milk products using poly (L-Lactic Acid) (PLLA) thin film","volume":"47","author":"Yusof","year":"2018","journal-title":"Sains Malays."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/j.ultsonch.2018.06.018","article-title":"Effect of thermoultrasound on aflatoxin M-1 levels, physicochemical and microbiological properties of milk during storage","volume":"48","year":"2018","journal-title":"Ultrason. Sonochem."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3856","DOI":"10.3168\/jds.2019-17145","article-title":"Symposium review: Real-time continuous decision making using big data on dairy farms","volume":"103","author":"Cabrera","year":"2020","journal-title":"J. Dairy Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Cui, S., Inocente, E.A.A., Acosta, N., Keener, H.M., Zhu, H., and Ling, P.P. (2019). Development of fast e-nose system for early-stage diagnosis of aphid-stressed tomato plants. Sensors, 19.","DOI":"10.3390\/s19163480"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yang, B., Qi, L., Wang, M., Hussain, S., Wang, H., Wang, B., and Ning, J. (2020). Cross-category tea polyphenols evaluation model based on feature fusion of electronic nose and hyperspectral imagery. Sensors, 20.","DOI":"10.3390\/s20010050"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, Q., Yan, B., Zhang, L., and Gu, Y. (2019). Bionic electronic nose based on MOS sensors array and machine learning algorithms used for wine properties detection. Sensors, 19.","DOI":"10.3390\/s19010045"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.jfoodeng.2008.11.002","article-title":"Preliminary study of ion mobility based electronic nose MGD-1 for discrimination of hard cheeses","volume":"92","author":"Gursoy","year":"2009","journal-title":"J. Food Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1016\/j.foodchem.2011.05.126","article-title":"Classification of Pecorino cheeses using electronic nose combined with artificial neural network and comparison with GC-MS analysis of volatile compounds","volume":"129","author":"Cevoli","year":"2011","journal-title":"Food Chem."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.msec.2014.09.030","article-title":"Aging time and brand determination of pasteurized milk using a multisensor e-nose combined with a voltammetric e-tongue","volume":"45","author":"Bougrini","year":"2014","journal-title":"Mater. Sci. Eng. C\u2014Mater."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Tong, L., Yi, H., Wang, J., Pan, M., Chi, X., Hao, H., and Ai, N. (2019). Effect of preheating treatment before defatting on the flavor quality of skim milk. Molecules, 24.","DOI":"10.3390\/molecules24152824"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1484","DOI":"10.1016\/j.foodchem.2016.11.002","article-title":"Evaluation of the synergism among volatile compounds in Oolong tea infusion by odour threshold with sensory analysis and E-nose","volume":"221","author":"Zhu","year":"2017","journal-title":"Food Chem."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.lwt.2019.04.099","article-title":"Aging discrimination of French cheese types based on the optimization of an electronic nose using multivariate computational approaches combined with response surface method (RSM)","volume":"111","author":"Yoosefian","year":"2019","journal-title":"LWT\u2014Food Sci. Technol."},{"key":"ref_26","first-page":"381","article-title":"Development of e-nose prototype for raw milk quality discrimination","volume":"67","author":"Sivalingam","year":"2012","journal-title":"Milchwiss.\u2014Milk Sci. Int."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"295","DOI":"10.3168\/jds.S0022-0302(02)74079-4","article-title":"The composition of bovine milk lipids: January 1995 to December 2000","volume":"85","author":"Jensen","year":"2002","journal-title":"J. Dairy Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"11349","DOI":"10.3168\/jds.2019-16847","article-title":"Dynamics of somatic cell count patterns as a proxy for transmission of mastitis pathogens","volume":"102","author":"Dalen","year":"2019","journal-title":"J. Dairy Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"11777","DOI":"10.3168\/jds.2018-16170","article-title":"Comparing dairy farm milk yield and components, somatic cell score, and reproductive performance among United States regions using summer to winter ratios","volume":"102","author":"Guinn","year":"2019","journal-title":"J. Dairy Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"11298","DOI":"10.3168\/jds.2019-16937","article-title":"Prediction of blood metabolites from milk mid-infrared spectra in early-lactation cows","volume":"102","author":"Benedet","year":"2019","journal-title":"J. Dairy Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.compag.2010.05.006","article-title":"Comparative analysis of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat","volume":"73","author":"Atzberger","year":"2010","journal-title":"Comput. Electron. Agric."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s10064-018-1256-z","article-title":"Spatial prediction of landslide susceptibility using data mining-based kernel logistic regression, naive Bayes and RBFNetwork models for the Long County area (China)","volume":"78","author":"Chen","year":"2019","journal-title":"Bull. Eng. Geol. Environ."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"15974","DOI":"10.3390\/s150715974","article-title":"Smart city mobility application-gradient boosting trees for mobility prediction and analysis based on crowdsourced data","volume":"15","author":"Semanjski","year":"2015","journal-title":"Sensors"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.enconman.2018.02.087","article-title":"Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China","volume":"164","author":"Fan","year":"2018","journal-title":"Energy Convers. Manag."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1016\/j.foodchem.2016.11.049","article-title":"Novel method for the producing area identification of Zhongning Goji berries by electronic nose","volume":"221","author":"Li","year":"2017","journal-title":"Food Chem."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/15\/4238\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:52:49Z","timestamp":1760176369000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/15\/4238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,30]]},"references-count":37,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2020,8]]}},"alternative-id":["s20154238"],"URL":"https:\/\/doi.org\/10.3390\/s20154238","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,30]]}}}