machine learning – Page 2

Heavy Metal Exposure During Pregnancy and Its Association With Adverse Birth Outcomes: A Cross-Sectional Study

mycolabadmin

This study examined how exposure to multiple heavy metals during pregnancy affects babies’ health in a Chinese population. Researchers measured metal levels in urine samples from nearly 500 pregnant women and found that higher combined metal exposure increased risks of premature birth and low birth weight. The metal arsenic was particularly harmful for preterm birth risk, while selenium, thallium, and manganese together increased low birth weight risk. These findings suggest that pregnant women in areas with heavy metal pollution should take steps to reduce their exposure.

Mushroom data creation, curation, and simulation to support classification tasks

mycolabadmin

This study creates a new dataset of over 61,000 mushroom records from 173 species to help computers learn to identify whether mushrooms are safe to eat or poisonous. The researchers extracted mushroom information from an identification textbook and used computer programs to generate realistic hypothetical mushroom entries. They tested different AI methods and found that random forests (a type of machine learning algorithm) worked best, achieving perfect accuracy in identifying poisonous versus edible mushrooms.

Artificial Neural Network Prediction of Mechanical Properties in Mycelium-Based Biocomposites

mycolabadmin

Scientists developed an artificial intelligence model that can predict how strong and durable mushroom-based composite materials will be. These composites are made by growing mushroom mycelium (fungal threads) through wood particles and other plant materials, creating an eco-friendly alternative to synthetic materials. The AI model learns from physical measurements and can accurately predict mechanical properties, potentially reducing the need for extensive testing and helping design better sustainable materials.

Advancing automated identification of airborne fungal spores: guidelines for cultivation and reference dataset creation

mycolabadmin

Researchers developed standardized procedures to grow fungal spores in laboratories and prepare them for testing with automated detection devices. They tested 17 different fungal species commonly found in the air and created reference datasets to train computer algorithms to identify these spores. Two different detection technologies were evaluated, showing promising accuracies (55-95%) for identifying various fungal spores. This work provides a blueprint for other scientists to create reliable training data for automated air quality monitoring systems that track allergens and disease-causing fungi.

Artificial Neural Network Prediction of Mechanical Properties in Mycelium-Based Biocomposites

mycolabadmin

Researchers used artificial intelligence to predict how strong mushroom-based materials would be. These eco-friendly composites are made from wood particles held together by fungal networks instead of synthetic glue. The AI model successfully learned to predict the strength of these materials based on which type of fungus was used and what wood particles they were grown on, potentially reducing the need for expensive testing.

Advancing automated identification of airborne fungal spores: guidelines for cultivation and reference dataset creation

mycolabadmin

Scientists developed systematic methods to grow and collect fungal spores in controlled conditions, then test them with automated air monitoring devices. Using two different monitoring systems that analyze spore images and fluorescence properties, they trained computer algorithms to recognize different fungal species. This work creates standardized guidelines that will help hospitals, allergy clinics, and agricultural services automatically detect and identify airborne fungal spores, which are important for managing allergies and plant diseases.

Large language models and their performance for the diagnosis of histoplasmosis

mycolabadmin

Researchers tested whether artificial intelligence chatbots like ChatGPT and Microsoft Copilot could help doctors diagnose histoplasmosis, a serious fungal infection affecting people with HIV/AIDS that is often missed. They presented 20 real patient case descriptions to different AI systems and found that Microsoft Copilot performed best, correctly identifying histoplasmosis in 90% of cases—about as good as laboratory tests. While the AI showed promise as a helpful tool to suggest this neglected disease during diagnosis, doctors would still need to verify findings with actual tests.

Classification of Mycena and Marasmius Species Using Deep Learning Models: An Ecological and Taxonomic Approach

mycolabadmin

Researchers developed an artificial intelligence system to automatically identify mushroom species from the Mycena and Marasmius groups by analyzing photographs. Using advanced computer vision and machine learning techniques, they achieved 98.9% accuracy in classification. This technology could help scientists, conservationists, and nature enthusiasts quickly identify mushroom species in the field, supporting biodiversity research and conservation efforts.

Automatic classification of fungal-fungal interactions using deep learning models

mycolabadmin

Researchers developed a computer artificial intelligence system that can automatically analyze images of fungal interactions to identify strains that could help control harmful crop diseases. Instead of having humans manually examine thousands of fungal culture plates—a slow and subjective process—the AI system can now classify the interactions between beneficial fungi and plant pathogens with 95% accuracy. This breakthrough significantly speeds up the search for natural alternatives to synthetic pesticides, supporting sustainable agriculture and food security.

The Use of Predictive Microbiology for the Prediction of the Shelf Life of Food Products

mycolabadmin

Food companies need to know how long products stay fresh and safe to eat. This review explains different scientific methods for predicting when food will spoil based on microbial growth. It compares traditional mathematical models with newer computer-based machine learning approaches, showing that newer methods can be more accurate and efficient for determining how long foods can be stored safely.

Research Keyword: machine learning