Transforming food consumer analysis: the role of machine learning in Food Consumer Demand 4.0

Le résumé fourni par la source

• The conception of Food Consumer Demand 4.0 was introduced for the first time. • The recent advances in food consumer analysis combined with ML were reviewed. • The advantages and disadvantages of common ML algorithms in food consumer analysis were summarized. • The application of ML in food consumer analysis showed high prediction accuracy. • Food consumer analysis combined with ML were promising. The evolution of food consumer demand can be divided into four stages: high-level food supply demand, high-safety food demand, high-nutritious food demand, and personalized customized food demand. Building upon the concept of Industry 4.0 and Agriculture 4.0, Food Consumer Demand 4.0 was introduced, leveraging the data-processing capabilities, rapid analysis, and precision of machine learning (ML) as a crucial tool for analyzing consumer demands in Food Consumer Demand 4.0. This paper focuses on the application and research progress of various ML algorithms in food consumer analysis, including Support Vector Machine (SVM), Logistic Regression (LR), K-Nearest Neighbor (KNN), Random Forest (RF), Naive Bayesian (NB), Artificial Neural Network (ANN), Principal Component Analysis (PCA), K-means, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Generative Adversarial Network (GAN), Transformer, etc. These algorithms are pivotal in food consumer analysis and hold promising potential when integrated with diverse analytical methods. ML serves a vital role in analyzing consumers' needs, addressing food safety concerns, evaluating dietary patterns, constructing dietary databases, and tailoring recipes for individual consumers. Nevertheless, existing ML models encounter challenges related to data volume dependency, interpretability, and energy consumption. Therefore, solving these problems and integrating ML with dynamic monitoring, scenario simulation, cloud-based data processing, and other technologies to deal with consumer demand will shape the future of food consumer analysis.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.