A Deep Learning Method for Yogurt Preferences Prediction Using Sensory Attributes

Predicting tactile sensory attributes of personal care emulsions based on instrumental characterizations: A review

Emulsions in the form of creams, lotions, gels or foams are the most widely used personal care formulations to improve the condition and feel of the skin. Achieving an optimal balance between their performance, effectiveness and sensory profile is essential, with the sensory profile being a key factor in consumer satisfaction and the success of these products in the market. Well-established methods using highly trained and semi-trained panels (e.g. Spectrum descriptive analysis, Flash Profile method, Quantitative Descriptive Analysis method and 'Check-all-that-apply') are available and commonly used for the sensory assessment of personal care products. Nevertheless, a common drawback among all these methods is their inherent cost, both in terms of financial resources and time requirements. In recent years, research studies have emerged to address this limitation by investigating potential correlations between tactile sensory attributes and instrumental data associated with the physical characteristics of topical formulations. In other words, significant efforts have been invested in the development of robust instrumental methods specifically designed to accurately predict the sensory description that a panel of assessors could establish. These methods are not only faster, cheaper and more objective compared to traditional sensory testing, but they can also be applied to formulations that have not undergone extensive safety and toxicological testing. This review summarizes the most relevant findings, trends and current challenges in predicting tactile sensory attributes of personal care emulsions based on instrumental parameters.

A machine learning method for juice human sensory hedonic prediction using electronic sensory features

This study proposed a method that combines fused electronic sensory analysis technology with artificial neural network to predict the human sensory hedonic of fruit juice. Quantitative descriptive analysis (QDA) and the scoring test method were utilized for human sensory evaluation. The first step involved modeling the fused e-sensory features with human sensory attributes, followed by establishing a fitting model of human sensory attributes and acceptance. The R2 and RMSE values obtained were 0.77 and 0.42 (QDA method), and 0.63 and 0.63 (scoring test method). Finally, the relationship between the fusion e-sensory features and the human sensory hedonic was established. Model-1 achieved an R2 of 0.95 and an RMSE of 0.04, while model-2 achieved an R2 value of 0.88 and an RMSE value of 0.21. This study demonstrates the potential of fusing e-sensory technologies to replace human senses, which may lead to the development of devices with simultaneous multiple senses.

Special Issue: Processing Foods: Process Optimization and Quality Assessment

For a long time, the basic as well as the only function of foods is to provide the nutrients and energy needed for human physiological processes [...]

Refining Preference-Based Recommendation with Associative Rules and Process Mining Using Correlation Distance

Online services, ambient services, and recommendation systems take user preferences into data processing so that the services can be tailored to the customer’s preferences. Associative rules have been used to capture combinations of frequently preferred items. However, for some item sets X and Y, only the frequency of occurrences is taken into consideration, and most of the rules have weak correlations between item sets. In this paper, we proposed a method to extract associative rules with a high correlation between multivariate attributes based on intuitive preference settings, process mining, and correlation distance. The main contribution of this paper is the intuitive preference that is optimized to extract newly discovered preferences, i.e., implicit preferences. As a result, the rules output from the methods has around 70% of improvement in correlation value even if customers do not specify their preference at all.

Effects of COVID-19 on sensory and cognitive perception of mild and severe diagnosed and recovered patients versus healthy consumers

The objective of this research was to analyze the effects of the SARS-CoV-2 virus on the sensory and cognitive perception of mild and severe COVID-19 diagnosed and recovered consumers versus healthy consumers. Three groups of 50 consumers each (healthy vs. mild and severe COVID-19 diagnosed with 30 days after recovery) were used for the evaluation of instant coffee stimuli in concentrations: 4.40, 2.93, 2.20, 1.76, and 1.47% weight (w)/volume (v) and determine their discriminating power, emotions, and memories. Sensory tests were performed remotely. Results indicated that healthy consumers perceived higher intensities in most of the sensory attributes (with the exception of Burnt-A, Bitter-T, Acid-T, and Astringent-T attributes) compared to consumers who presented mild and severe COVID-19. Therefore, consumers diagnosed with mild and severe COVID-19 had a higher discrimination power in the attributes smell, basic tastes, and flavor. Healthy consumers could only discriminate two attributes that correspond to basic flavors. Consumers with mild and severe COVID-19 diagnosis elicited the highest number of negatives emotions (such as bored, disgusted, worried, guilty, wild, and aggressive) and negative memories (disease, pain, death, hurt, obesity, conflict personal, addiction, stench poverty, and accident) than healthy consumers. It is concluded that there were no significant differences between the consumer panels for the identification of sensory attributes. However, P-Healthy consumers perceived the highest intensities in most sensory attributes compared to those in the PCOVID19-Mild and PCOVID19-Severe panels. Finally, consumers diagnosed with mild or severe COVID-19 used a higher number of emotions and memories than those of the healthy panel.

Practical applications

Investigating the effects of COVID-19 on sensory and cognitive perception can be useful for industry and researchers in the sensory field who wish to understand the effects of the disease in order to generate new protocols for the selection and training of people, as well as the possible development and innovation of new products focused on perception of consumers recovered from COVID-19.

Machine Learning in Chemical Product Engineering: The State of the Art and a Guide for Newcomers

Chemical Product Engineering (CPE) is marked by numerous challenges, such as the complexity of the properties–structure–ingredients–process relationship of the different products and the necessity to discover and develop constantly and quickly new molecules and materials with tailor-made properties. In recent years, artificial intelligence (AI) and machine learning (ML) methods have gained increasing attention due to their performance in tackling particularly complex problems in various areas, such as computer vision and natural language processing. As such, they present a specific interest in addressing the complex challenges of CPE. This article provides an updated review of the state of the art regarding the implementation of ML techniques in different types of CPE problems with a particular focus on four specific domains, namely the design and discovery of new molecules and materials, the modeling of processes, the prediction of chemical reactions/retrosynthesis and the support for sensorial analysis. This review is further completed by general guidelines for the selection of an appropriate ML technique given the characteristics of each problem and by a critical discussion of several key issues associated with the development of ML modeling approaches. Accordingly, this paper may serve both the experienced researcher in the field as well as the newcomer.