Milk infrared spectra from multiple instruments improve performance of prediction models

Lorenzi, Claudia De; Franzoi, Marco; Marchi, Massimo De

doi:10.1016/j.idairyj.2021.105094

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It evaluates the performance of supervised clustering, which compares the clustering results with the true labels. It is calculated by matching each clustered cluster with its corresponding true label and then calculating the ratio of correctly classified samples to the total number of samples 33 . The formula is:…”

Section: Accuracymentioning

confidence: 99%

Clustering Explanation based on Multi-Hyperrectangle

Zeng,

Zhong,

Pan

2024

Preprint

View full text Add to dashboard Cite

Clustering plays a crucial role in data mining and pattern recognition, but the interpretation of clustering results is often challenging. Existing interpretation methods usually lack an intuitive and accurate description of irregular shapes and high-dimensional data. This paper proposes a clustering explanation method based on a Multi-HyperRectangle (MHR), for extracting post hoc explanations of clustering results. MHR first generates initial hyperrectangles to cover a cluster, and then gradually merges these hyperrectangles to obtain the optimal shape that fits the cluster. Furthermore, we propose a refinement method to improve the tightness of the hyperrectangles to make the interpretation results more precise and easier to understand. Experimental results show that MHR has significant advantages in terms of tightness and accuracy of cluster interpretation.

show abstract

Section: Accuracymentioning

confidence: 99%

Clustering Explanation based on Multi-Hyperrectangle

Zeng,

Zhong,

Pan

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Currently, among various optical methods for the product quality estimation of milk and dairy products, near-infrared reflective spectroscopy has become the most widespread [3]. The infrared spectra of milk have been studied for changes detected during milk coagulation [4], the presence of impurities [5], fat and protein amount estimation [6], etc. Near-IR spectroscopy methods are used for analyzing milk powder [7], goat's milk [8], buttermilk/yogurt [9], cheese [10], melted butter (ghee) [11], and ice cream [12].…”

Section: Introductionmentioning

confidence: 99%

Photoluminescence Spectral Patterns and Parameters of Milk While Souring

Belyakov,

Samarin,

Ruzhev

et al. 2023

Agriculture

View full text Add to dashboard Cite

For the efficient production and processing of milk, it is important to control its quality indicators. Optical spectroscopy, in combination with statistical analysis methods, can be a useful method of evaluation due to its speed, non-invasiveness, and relative cheapness. This investigation is aimed at studying of the interrelations of the spectral patterns, the absorption parameters, and the photoluminescence values of cow’s milk during its souring. The spectral characteristics of excitation and photoluminescence were measured on a diffraction spectrofluorometer in the range of 200–500 nm. For establishing an effective control procedure during milk souring, the most informative method is found to be the use of the excitation wavelengths of 232 nm, 322 nm, 385 nm and 442 nm. These ranges correspond to the amino acids of milk proteins, the fatty acids of milk fat, and the aromatic fragments of vitamins. When using the photoluminescence flux ratios Φ232/Φ322 and Φ385/Φ442, linearly approximated dependences on acidity can be obtained with determination coefficients of 0.88–0.94. The proposed photoluminescent method can be used as a non-destructive and fast-acting tool for monitoring the properties of milk during fermentation, as well as for the subsequent creation of a portable and inexpensive sensor based on this method.

show abstract

Milk infrared spectra from multiple instruments improve performance of prediction models

Cited by 2 publications

References 20 publications

Clustering Explanation based on Multi-Hyperrectangle

Clustering Explanation based on Multi-Hyperrectangle

Photoluminescence Spectral Patterns and Parameters of Milk While Souring

Contact Info

Product

Resources

About