Articles Tagged with ''machine learning''

Wageningen University researchers developed a hybrid machine learning modeling framework that considers crop growth stages, various future scenarios, and a large geographic region. The model predicted deoxynivalenol will present the greatest risk, with coastal countries, the UK, and northern France most affected.

Garlic carries a distinct bacterial signature reflective of the soil in which it was grown, enabling geographic identification based on microbial composition. A novel method using microbiome data and AI analysis potentially offers a low-cost authentication technique.

The low-cost approach enables simultaneous detection of multiple foodborne pathogens and spoilage microorganisms in a shorter timeframe than traditional detection methods, without requiring advanced technical training. 

The researchers positioned the machine learning model as a low-cost complement to traditional testing workflows, helping dairy processors enhance food safety while targeting laboratory resources.

A study used machine learning to analyze WGS data for Salmonella isolates from ten European nations. The findings reveal that poultry and pigs remain the dominant sources of human salmonellosis. Notable cross-border transmission underscores the need for internationally harmonized control strategies.

A new study led by the University of South Australia offers a promising real-time mycotoxin detection method for the food industry that is based in artificial intelligence (AI) technology, and overcomes some of the limitations of traditional detection methods.

Using an artificial intelligence (AI) model to standardize and analyze a massive, global set of whole genome sequencing (WGS) data for Cronobacter sakazakii, University of Maryland researchers have discovered genetic traits that may explain the pathogen’s persistence and virulence in low-moisture foods like powdered infant formula. 

In the study, researchers analyzed the entire genome of over 1,600 Listeria strains. These DNA profiles were used to train a machine learning model that learned to identify genetic patterns associated with resistance to disinfectants commonly used in the food industry. 

Using EU Rapid Alert System for Food and Feed (RASFF) data, researchers have developed an integrated artificial intelligence (AI) framework for conducting food safety risk assessments, and demonstrated its usefulness in decreasing the ambiguity of risk management decisions.

Researchers from CDC, FDA, and USDA trained an artificial intelligence (AI) machine learning model to conduct food source attribution for human cases of salmonellosis by analyzing whole genome sequencing (WGS) data for Salmonella isolates. The model showed promise, estimating that the majority of salmonellosis cases are caused by chicken and vegetables