Feasibility of Image Analysis Coupled with Machine Learning for Detection and Quantification of Extraneous Water in Milk

Asefa, Bezuayehu Gutema; Hagos, Legese; Kore, Tamirat; Emire, Shimelis Admassu

doi:10.1007/s12161-022-02352-w

Cited by 8 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method enhances the accuracy of regression predictions by combining multiple decision trees into an ensemble [17]. This method permits us to examine variable importance weights and is recognized to show exceptional performance in solving regression problems [18]. The extreme gradient boosting (XGBoost) machine learning algorithm was used to develop a marbling score prediction model.…”

Section: Development Of the Marbling Score Estimation Modelmentioning

confidence: 99%

Modeling of Ethiopian Beef Meat Marbling Score Using Image Processing for Rapid Meat Grading

Erena,

Belay,

Hailu

et al. 2024

J. Imaging

Self Cite

View full text Add to dashboard Cite

Meat characterized by a high marbling value is typically anticipated to display enhanced sensory attributes. This study aimed to predict the marbling scores of rib-eye, steaks sourced from the Longissimus dorsi muscle of different cattle types, namely Boran, Senga, and Sheko, by employing digital image processing and machine-learning algorithms. Marbling was analyzed using digital image processing coupled with an extreme gradient boosting (GBoost) machine learning algorithm. Meat texture was assessed using a universal texture analyzer. Sensory characteristics of beef were evaluated through quantitative descriptive analysis with a trained panel of twenty. Using selected image features from digital image processing, the marbling score was predicted with R2 (prediction) = 0.83. Boran cattle had the highest fat content in sirloin and chuck cuts (12.68% and 12.40%, respectively), followed by Senga (11.59% and 11.56%) and Sheko (11.40% and 11.17%). Tenderness scores for sirloin and chuck cuts differed among the three breeds: Boran (7.06 ± 2.75 and 3.81 ± 2.24, respectively), Senga (5.54 ± 1.90 and 5.25 ± 2.47), and Sheko (5.43 ± 2.76 and 6.33 ± 2.28 Nmm). Sheko and Senga had similar sensory attributes. Marbling scores were higher in Boran (4.28 ± 1.43 and 3.68 ± 1.21) and Senga (2.88 ± 0.69 and 2.83 ± 0.98) compared to Sheko (2.73 ± 1.28 and 2.90 ± 1.52). The study achieved a remarkable milestone in developing a digital tool for predicting marbling scores of Ethiopian beef breeds. Furthermore, the relationship between quality attributes and beef marbling score has been verified. After further validation, the output of this research can be utilized in the meat industry and quality control authorities.

show abstract

Section: Development Of the Marbling Score Estimation Modelmentioning

confidence: 99%

Modeling of Ethiopian Beef Meat Marbling Score Using Image Processing for Rapid Meat Grading

Erena,

Belay,

Hailu

et al. 2024

J. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the rapid development of computer technology, people gradually apply industrial equipment and artificial intelligence to dairy adulteration identification (Neto et al, 2019). The mainstream methods are sensor technology (Teixeira, Caramês, Baptista, Gigante, & Pallone, 2022) , machine learning models (Asefa, Hagos, Kore, & Emire, 2022), and deep learning models (Z. Huang et al, 2023) .…”

Section: Related Workmentioning

confidence: 99%

EnDairy: An Ensemble Learning-based Framework for Efficient Dairy Product Identification

Wang

Yan

et al. 2023

Preprint

View full text Add to dashboard Cite

Food safety has been a worldwide concern, and raw materials’ adulteration is oneof the significant factors contributing to this problem. Camel milk has high nutri-tional and economic value but faces adulteration problems. With time-consuming,poor stability, and low accuracy, the existing adulteration identification frame-works are limited applications. This paper proposes an efficient dairy adulterationidentification framework (EnDairy) based on an ensemble learning algorithmto solve these problems. Specifically, samples are identified by comparing theprobabilistic prediction values obtained and the optimal threshold by data pre-processing and weak learners iteration fusion into a strong learner. In this paper,we used a batch of camel milk data to verify the effectiveness of EnDairy in realscenarios. We tested its discriminative ability for data with missing values byfeature mask. The results show that EnDairy performs well; the AUC and Recallvalues are equal and 0.986 and 0.981 for the 10% and 20% feature mask treat-ments, respectively. The time taken by the identification model is only 0.637sand 0.648s. EnDairy ensures the accuracy of identification and effectively reducesthe economic and time costs, which can provide supportive information for camelmilk regulation, promote dairy product safety, and advance health for all.

show abstract

“…Ehsani et al applied boosted regression tree (BRT) [114] on NIR spectra collected by a portable spectrometer for a fast water quantification in cow's milk [115]. The presence of water in cow's milk was also inspected by Asefa et al [116], who proposed a procedure based on digital image analysis coupled with extreme gradient boosting (XGBoost) [117].…”

Section: Regressionmentioning

confidence: 99%

“…In some cases, they provide slightly better results than PLS, but in many other cases, the results are comparable. Ovine milk and caprine milk Cow milk MALDI-TOF-MS PLS, GLM-Lasso [113] Cow milk Water NIR (portable) BRT [115] Cow milk Water Digital image analysis XGBoost [116] Abbreviations: ATR = attenuated total reflection, BP-ANN = back propagation artificial neural networks, BRT = boosted regression trees, GA-PLS = genetic-algorithm partial least squares, GLM-Lasso = generalized linear model with lasso regularization, GR-NN = generalized regression neural networks, HSI = hyperspectral imaging, LS-SVM = least squares support vector machine, MALDI-TOF-MS = matrix-assisted laser desorption ionization time-of-flight mass spectrometry, MCR-ALS = multivariate curve resolution alternating least squares, MIR = mid-infrared, MLR = multiple linear regression, NIR = near-infrared, OPLS = orthogonal partial least squares, PARAFAC = parallel factor analysis, PCR = principal component regression, PLS = partial least squares, siPLS = synergy interval partial least squares, TD-NMR = time-domain nuclear magnetic resonance, U-PLS/RBL = unfolded partial least squares with residual bilinearization, Vis = visible, XGBoost = extreme gradient boosting.…”

Section: Regressionmentioning

confidence: 99%

How Chemometrics Can Fight Milk Adulteration

Grassi

Tarapoulouzi

D’Alessandro

et al. 2022

Foods

View full text Add to dashboard Cite

Adulteration and fraud are amongst the wrong practices followed nowadays due to the attitude of some people to gain more money or their tendency to mislead consumers. Obviously, the industry follows stringent controls and methodologies in order to protect consumers as well as the origin of the food products, and investment in these technologies is highly critical. In this context, chemometric techniques proved to be very efficient in detecting and even quantifying the number of substances used as adulterants. The extraction of relevant information from different kinds of data is a crucial feature to achieve this aim. However, these techniques are not always used properly. In fact, training is important along with investment in these technologies in order to cope effectively and not only reduce fraud but also advertise the geographical origin of the various food and drink products. The aim of this paper is to present an overview of the different chemometric techniques (from clustering to classification and regression applied to several analytical data) along with spectroscopy, chromatography, electrochemical sensors, and other on-site detection devices in the battle against milk adulteration. Moreover, the steps which should be followed to develop a chemometric model to face adulteration issues are carefully presented with the required critical discussion.

show abstract

Feasibility of Image Analysis Coupled with Machine Learning for Detection and Quantification of Extraneous Water in Milk

Cited by 8 publications

References 21 publications

Modeling of Ethiopian Beef Meat Marbling Score Using Image Processing for Rapid Meat Grading

Modeling of Ethiopian Beef Meat Marbling Score Using Image Processing for Rapid Meat Grading

EnDairy: An Ensemble Learning-based Framework for Efficient Dairy Product Identification

How Chemometrics Can Fight Milk Adulteration

Contact Info

Product

Resources

About