Browse by author
Lookup NU author(s): Dr Jie ZhangORCiD, Lei Zhang
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
In this study, an electronic nose (E-nose) consisting of seven metal oxide semiconductorsensors is developed to identify milk sources (dairy farms) and to estimate the content of milkfat and protein which are the indicators of milk quality. The developed E-nose is a low cost andnon-destructive device. For milk source identification, the features based on milk odor features fromE-nose, composition features (Dairy Herd Improvement, DHI analytical data) from DHI analysis andfusion 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 modelof milk source (dairy farm) identification. The results show that the SVM model based on the fusionfeatures after LDA has the best performance with the accuracy of 95%. Estimation model of thecontent 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 thatthe RF models give the best performance (R2 = 0.9399 for milk fat; R2 = 0.9301 for milk protein) andindicate that the proposed method in this study can improve the estimation accuracy of milk fat andprotein, which provides a technical basis for predicting the quality of milk.
Author(s): Mu F, Gu Y, Zhang J, Zhang L
Publication type: Article
Publication status: Published
Journal: Sensors
Year: 2020
Volume: 20
Issue: 15
Print publication date: 30/07/2020
Online publication date: 30/07/2020
Acceptance date: 27/07/2020
Date deposited: 10/08/2020
ISSN (print): 1424-8220
ISSN (electronic): 1424-8220
Publisher: MDPI AG
URL: https://doi.org/10.3390/s20154238
DOI: 10.3390/s20154238
Altmetrics provided by Altmetric
