Causal inference of whole‐grain foods’ risk based on a generative adversarial network and Bayesian network

Journal of Food Science, Journal Year: 2025, Volume and Issue: 90(1)

Published: Jan. 1, 2025

Abstract Whole‐grain foods (WGFs) constitute a large part of humans’ daily diet, making risk identification WGFs important for health and safety. However, existing research on has paid more attention to revealing the effects single hazardous substance or various substances food safety, neglecting mutual influence between individual basic information. Therefore, this paper proposes causal inference WGFs’ based generative adversarial network (GAN) Bayesian (BN) explore The experiment results show that proposed GAN outperformed several traditional data‐imputation methods, producing at least 13.65% reduction root mean square error (RMSE). classification accuracy BN model reached 91%. In conclusion, we distinguish provinces, periods, categories, cause absolute high mycotoxins compounds (MaCs) cadmium. Practical Application This can be applied impute missing values whole‐grain sampling data, causality among themselves, information in WGFs. Additionally, it infer potential (e.g., substances).

Language: Английский

Analysis of Machine Learning Algorithms for the Computer Simulation of Moisture Sorption Isotherms of Coffee Beans

Food and Bioprocess Technology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 18, 2025

Language: Английский