A comprehensive review of machine learning and its application to dairy products.

Machine learning (ML) technology is a powerful tool in food science and engineering offering numerous advantages, from recognizing patterns and predicting outcomes to customizing and adjusting to individual needs. Its further development can enable researchers and industries to significantly enhance the efficiency of dairy processing while providing valuable insights into the field. This paper presents an overview of the role of machine learning in the dairy industry and its potential to improve the efficiency of dairy processing. We performed a systematic search for articles published between January 2003 and January 2023 related to machine learning in dairy products and highlighted the algorithms used. 48 studies are discussed to assist researchers in identifying the best methods that could be applied in their field and providing relevant ideas for future research directions. Moreover, a step-by-step guide to the machine learning process, including a classification of different machine learning algorithms, is provided. This review focuses on state-of-the-art machine learning applications in milk products and their transformation into other dairy products, but it also presents future perspectives and conclusions. The study serves as a valuable guide for individuals in the dairy industry interested in learning about or getting involved with ML.

Sensory characterization of functional guava symbiotic petit cheese product.

The consumption of functional dairy products continues to rise due to consumer needs. This study aimed to develop a dairy guava functional symbiotic petit cheese product that included probiotics (Bifidobacterium animalis subsp. lactis BB-12, Chr. Hansen, Denmark) and prebiotics (inulin), which had adequate organoleptic characteristics. Moreover, adequate physicochemical, microbiological, and sensory characteristics during its shelf life were expected. A pasteurized skim milk curd flavored with a guava pulp was stabilized with gelatin to formulate this product. As sweeteners, iso maltol, erythritol, and Luo Han Guo extract from monk fruit (Siraitia Grosvenorii) were added. The prebiotic used was inulin, and the probiotic (Bifidobacterium animalis subsp. lactis BB-12, Chr. Hansen, Denmark). The product was kept refrigerated (4 °C) during the shelf life of 28 days. For the organoleptic analysis (100 consumers), the evaluations performed were: (1) overall liking (OL), (2) CATA (Check all that apply) testing 19 attributes, and (3) purchase intention was evaluated. Results were analyzed with FIZZ Software Biosystèmes. During shelf life, (1) physicochemical, microbiological, and sensory tests were performed. The product was evaluated as "liked much'' (7.16 out of 9); it was described as a creamy (71 %) natural product (73 %) with a fruity odor (57 %). It could be suitable for marketing because 82 % of the consumers would buy it. The product's probiotic character (over 1 × 106) was established through a microbiological count. On day one, the CFU was found to be 4.15 × 108, and after 28 days, 1.98 × 108 CFU of viable Bifidobacterium animalis subsp. lactis BB-12, leading us to establish its probiotic characteristics. The shelf life was estimated at 21 days.

Physicochemical, Microbiological and Technological Properties of Red Deer (Cervus elaphus) Milk during Lactation.

This study describes chemical, physical, microbiological and technological characteristics of red deer milk and the effect of lactation on these parameters in order to know their potential aptitude to elaborate dairy products. During 18 weeks, milk from five hinds was monitored for composition, bacteriology, somatic cell count (SCC), physical properties and rennet coagulation. Mean values (g/100 g) for fat, protein, lactose and dry matter were 10.4, 7.1, 4.3 and 24.2, respectively, and for urea, 265 mg/100 mL. Except for lactose, a significant increase in these components was observed (p < 0.01) as lactation progressed. The average values for bacteriology and SCC were 5.3 log cfu/mL and 4.7 log cells/mL, respectively. Regarding physical properties, conductivity (mean: 2.8 ms/cm), viscosity (3.1 Cp), coordinates L* (89.9) and a* (-3.1) and milk fat globule diameter (D4,3: 6.1 µm) increased along with lactation while density (1.038 g/mL) decreased (p < 0.01). The pH (6.7), acidity (22.9° Dornic), coordinate b* (8.4) and ethanol stability (66.6% v/v) were stable during the study period. The stage of lactation also has a significant impact on milk coagulation properties and mean curd yield was 3.29 g/10 mL. These results suggest that red deer milk could be a potential innovative source of milk for the dairy industry.

Volatile Transference and Antimicrobial Activity of Cheeses Made with Ewes' Milk Fortified with Essential Oils.

During the last decades, essential oils (EOs) have been proven to be a natural alternative to additives or pasteurization for the prevention of microbial spoilage in several food matrices. In this work, we tested the antimicrobial activity of EOs from Melissa officinalis, Ocimum basilicum, and Thymus vulgaris against three different microorganisms: Escherichia coli, Clostridium tyrobutyricum, and Penicillium verrucosum. Pressed ewes' cheese made from milk fortified with EOs (250 mg/kg) was used as a model. The carryover effect of each oil was studied by analyzing the volatile fraction of dairy samples along the cheese-making process using headspace stir bar sorptive extraction coupled to gas chromatography/mass spectrometry. Results showed that the EOs contained in T. vulgaris effectively reduced the counts of C. tyrobutyricum and inhibited completely the growth of P. verrucosum without affecting the natural flora present in the cheese. By contrast, the inhibitory effect of M. officinalis against lactic acid bacteria starter cultures rendered this oil unsuitable for this matrix.

Chemical features mining provides new descriptive structure-odor relationships.

An important goal in researching the biology of olfaction is to link the perception of smells to the chemistry of odorants. In other words, why do some odorants smell like fruits and others like flowers? While the so-called stimulus-percept issue was resolved in the field of color vision some time ago, the relationship between the chemistry and psycho-biology of odors remains unclear up to the present day. Although a series of investigations have demonstrated that this relationship exists, the descriptive and explicative aspects of the proposed models that are currently in use require greater sophistication. One reason for this is that the algorithms of current models do not consistently consider the possibility that multiple chemical rules can describe a single quality despite the fact that this is the case in reality, whereby two very different molecules can evoke a similar odor. Moreover, the available datasets are often large and heterogeneous, thus rendering the generation of multiple rules without any use of a computational approach overly complex. We considered these two issues in the present paper. First, we built a new database containing 1689 odorants characterized by physicochemical properties and olfactory qualities. Second, we developed a computational method based on a subgroup discovery algorithm that discriminated perceptual qualities of smells on the basis of physicochemical properties. Third, we ran a series of experiments on 74 distinct olfactory qualities and showed that the generation and validation of rules linking chemistry to odor perception was possible. Taken together, our findings provide significant new insights into the relationship between stimulus and percept in olfaction. In addition, by automatically extracting new knowledge linking chemistry of odorants and psychology of smells, our results provide a new computational framework of analysis enabling scientists in the field to test original hypotheses using descriptive or predictive modeling.

Learning to name smells increases activity in heteromodal semantic areas.

Semantic description of odors is a cognitively demanding task. Learning to name smells is, however, possible with training. This study set out to examine how improvement in olfactory semantic knowledge following training reorganizes the neural representation of smells. First, 19 nonexpert volunteers were trained for 3 days; they were exposed (i) to odorants presented without verbal labels (perceptual learning) and (ii) to other odorants paired with lexicosemantic labels (associative learning). Second, the same participants were tested in a brain imaging study (fMRI) measuring hemodynamic responses to learned odors presented in both the perceptual and associative learning conditions. The lexicosemantic training enhanced the ability to describe smells semantically. Neurally, this change was associated with enhanced activity in a set of heteromodal areas-including superior frontal gyrus-and parietal areas. These findings demonstrate that odor-name associative learning induces recruitment of brain areas involved in the integration and representation of semantic attributes of sensory events. They also offer new insights into the brain plasticity underlying the acquisition of olfactory expertise in lay people. Hum Brain Mapp 38:5958-5969, 2017. © 2017 Wiley Periodicals, Inc.